Diefolio
English

GeForce RTX 4090 vs GeForce RTX 4080 SUPER

GeForce RTX 4090 vs GeForce RTX 4080 SUPER: GeForce RTX 4090 has 24GB of dedicated VRAM and 16,384 CUDA cores. / GeForce RTX 4080 SUPER has 16GB of dedicated VRAM and 10,240 CUDA cores.

Comparison notes

Compare the documented configurations and measurement conditions. 24GB of VRAM does not guarantee compatibility with every AI model. Check the model, quantization, context length and runtime; CUDA core counts across generations are not measured performance ratios. RTX 4080 and RTX 4080 SUPER are separate products. Equal memory capacity does not imply equal gaming or rendering performance; check board, driver and test conditions.

Reviewed: 2026-10-11

Explore workloads and conditions →

Evidence at a glance · 16

Benchmarks and test conditions

3DMark Time Spy · Graphics

GeForce RTX 4090 36,671 points

Source aggregate · Median · Source sample size: 39

Time Spy (build unknown) · GPU

GeForce RTX 4080 SUPER 28,378 points

Source aggregate · Median · Source sample size: 3

Time Spy (build unknown) · GPU

Inspect full results for conditions and sources. Conditions can differ per product.

3DMark Fire Strike · Graphics

GeForce RTX 4090 75,641 points

Source aggregate · Median · Source sample size: 37

Fire Strike (build unknown) · GPU

GeForce RTX 4080 SUPER 59,075 points

Source aggregate · Median · Source sample size: 3

Fire Strike (build unknown) · GPU

Inspect full results for conditions and sources. Conditions can differ per product.

Geekbench GPU 6.7 OpenCL

GeForce RTX 4090 328,983 points

Source aggregate · Median · Source sample size: 21

6.7 · GPU

GeForce RTX 4080 SUPER 256,624 points

Source aggregate · Median · Source sample size: 2

6.7 · GPU

Inspect full results for conditions and sources. Conditions can differ per product.

All measurement results (32)

Up to 24 results with representative scores are shown per product, prioritizing shared test conditions. Explore the comparison tool for all results and individual submissions. Results with matching tests, versions and environments appear in the same row. An unavailable result is missing evidence in this selection, not a zero score. These results do not establish an OS effect or an overall winner.

Parameter and conditionsGeForce RTX 4090GeForce RTX 4080 SUPER
Both products have resultsBlender · 5.1.1 · classroom · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.2",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 8,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 16,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "classroom",
  "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
  "version": "5.1.1"
}

Blender scene rendering

2,761.484129730943 samples/min

Provisional median · Limited submissionsn = 25

5.1.1 · classroom · OPTIX · Windows · 1P · 8 cores · 16 threads

2,761.48 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
2,430.37 / 3,084.14
Measurement dates
2026-05-06 – 2026-07-23
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 25

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2761.484129730943,
    "observed_max": 3084.144109959965,
    "observed_min": 2430.3673355088586,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 25,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.2",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 8,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 16,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "classroom",
    "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
    "version": "5.1.1"
  },
  "condition_id": "0a8a06589960539c89a4",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "a04f0044-12b7-4fbd-8558-eb901a78347b",
    "b5b6c3f8-ec31-4adf-80f8-38a72648601a",
    "4969a621-990d-4dc0-8068-f87afad862d1"
  ],
  "measured_from": "2026-05-06T16:17:53.364298+00:00",
  "measured_to": "2026-07-23T20:25:01.159256+00:00",
  "median": 2761.484129730943,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 25,
  "sample_status": "provisional"
}

Blender scene rendering

2,131.7649482559796 samples/min

Provisional median · Limited submissionsn = 11

5.1.1 · classroom · OPTIX · Windows · 1P · 8 cores · 16 threads

2,131.76 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
1,882.07 / 2,204.8
Measurement dates
2026-04-18 – 2026-07-05
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 11

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2131.7649482559796,
    "observed_max": 2204.796384582139,
    "observed_min": 1882.0734978161518,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 11,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.2",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 8,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 16,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "classroom",
    "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
    "version": "5.1.1"
  },
  "condition_id": "552cf75d946770e1e512",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "6509dfad-30a7-4e51-8171-4fa5910e556e",
    "0e6b8006-7c2e-4d65-9d85-72ab02052417",
    "ed14fc57-faca-48bd-916e-02d0a2b56ee5"
  ],
  "measured_from": "2026-04-18T23:18:39.933807+00:00",
  "measured_to": "2026-07-05T17:43:48.391264+00:00",
  "median": 2131.7649482559796,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 11,
  "sample_status": "provisional"
}
Both products have resultsBlender · 5.1.1 · monster + junkshop + classroom · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.2",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 8,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 16,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "monster + junkshop + classroom",
  "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
  "version": "5.1.1"
}

Blender complete benchmark

11,321.40509884421 samples/min

Provisional median · Limited submissionsn = 25

5.1.1 · monster + junkshop + classroom · OPTIX · Windows · 1P · 8 cores · 16 threads

11,321.41 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
9,764.59 / 12,347.31
Measurement dates
2026-05-06 – 2026-07-23
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 25

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 11321.40509884421,
    "observed_max": 12347.309495451687,
    "observed_min": 9764.590394450453,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 25,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.2",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 8,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 16,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster + junkshop + classroom",
    "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
    "version": "5.1.1"
  },
  "condition_id": "1dab7407dccf99b0d037",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "a04f0044-12b7-4fbd-8558-eb901a78347b",
    "b5b6c3f8-ec31-4adf-80f8-38a72648601a",
    "4969a621-990d-4dc0-8068-f87afad862d1"
  ],
  "measured_from": "2026-05-06T16:17:53.364298+00:00",
  "measured_to": "2026-07-23T20:25:01.159256+00:00",
  "median": 11321.40509884421,
  "parameter_id": "benchmark.blender.total_samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 25,
  "sample_status": "provisional"
}

Blender complete benchmark

8,383.237057503911 samples/min

Provisional median · Limited submissionsn = 11

5.1.1 · monster + junkshop + classroom · OPTIX · Windows · 1P · 8 cores · 16 threads

8,383.24 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
7,180.15 / 8,670.62
Measurement dates
2026-04-18 – 2026-07-05
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 11

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 8383.237057503911,
    "observed_max": 8670.624612860207,
    "observed_min": 7180.149599400593,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 11,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.2",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 8,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 16,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster + junkshop + classroom",
    "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
    "version": "5.1.1"
  },
  "condition_id": "79a69a08b80b02132ee7",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "6509dfad-30a7-4e51-8171-4fa5910e556e",
    "0e6b8006-7c2e-4d65-9d85-72ab02052417",
    "ed14fc57-faca-48bd-916e-02d0a2b56ee5"
  ],
  "measured_from": "2026-04-18T23:18:39.933807+00:00",
  "measured_to": "2026-07-05T17:43:48.391264+00:00",
  "median": 8383.237057503911,
  "parameter_id": "benchmark.blender.total_samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 11,
  "sample_status": "provisional"
}
Both products have resultsBlender · 5.1.1 · junkshop · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.2",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 8,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 16,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "junkshop",
  "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
  "version": "5.1.1"
}

Blender scene rendering

3,484.2355275484206 samples/min

Provisional median · Limited submissionsn = 25

5.1.1 · junkshop · OPTIX · Windows · 1P · 8 cores · 16 threads

3,484.24 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
2,892.11 / 3,800.05
Measurement dates
2026-05-06 – 2026-07-23
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 25

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 3484.2355275484206,
    "observed_max": 3800.048123315248,
    "observed_min": 2892.1067313454882,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 25,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.2",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 8,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 16,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "junkshop",
    "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
    "version": "5.1.1"
  },
  "condition_id": "5104ae6c61bfdde48b65",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "a04f0044-12b7-4fbd-8558-eb901a78347b",
    "b5b6c3f8-ec31-4adf-80f8-38a72648601a",
    "4969a621-990d-4dc0-8068-f87afad862d1"
  ],
  "measured_from": "2026-05-06T16:17:18.190645+00:00",
  "measured_to": "2026-07-23T20:24:19.447929+00:00",
  "median": 3484.2355275484206,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 25,
  "sample_status": "provisional"
}

Blender scene rendering

2,631.270270403679 samples/min

Provisional median · Limited submissionsn = 11

5.1.1 · junkshop · OPTIX · Windows · 1P · 8 cores · 16 threads

2,631.27 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
2,128.84 / 2,705.06
Measurement dates
2026-04-18 – 2026-07-05
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 11

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2631.270270403679,
    "observed_max": 2705.058353523495,
    "observed_min": 2128.8366355857847,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 11,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.2",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 8,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 16,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "junkshop",
    "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
    "version": "5.1.1"
  },
  "condition_id": "c2f3e118356ce681f7dd",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "6509dfad-30a7-4e51-8171-4fa5910e556e",
    "0e6b8006-7c2e-4d65-9d85-72ab02052417",
    "ed14fc57-faca-48bd-916e-02d0a2b56ee5"
  ],
  "measured_from": "2026-04-18T23:17:59.872842+00:00",
  "measured_to": "2026-07-05T17:43:12.290788+00:00",
  "median": 2631.270270403679,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 11,
  "sample_status": "provisional"
}
Both products have resultsBlender · 5.1.1 · monster · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.2",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 8,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 16,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "monster",
  "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
  "version": "5.1.1"
}

Blender scene rendering

5,022.506326099379 samples/min

Provisional median · Limited submissionsn = 25

5.1.1 · monster · OPTIX · Windows · 1P · 8 cores · 16 threads

5,022.51 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
4,169.53 / 5,463.12
Measurement dates
2026-05-06 – 2026-07-23
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 25

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 5022.506326099379,
    "observed_max": 5463.117262176474,
    "observed_min": 4169.525838246759,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 25,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.2",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 8,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 16,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster",
    "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
    "version": "5.1.1"
  },
  "condition_id": "6d0b21353e9d9c7c546f",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "a04f0044-12b7-4fbd-8558-eb901a78347b",
    "b5b6c3f8-ec31-4adf-80f8-38a72648601a",
    "4969a621-990d-4dc0-8068-f87afad862d1"
  ],
  "measured_from": "2026-05-06T16:16:38.529015+00:00",
  "measured_to": "2026-07-23T20:23:27.180147+00:00",
  "median": 5022.506326099379,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 25,
  "sample_status": "provisional"
}

Blender scene rendering

3,689.4884062463448 samples/min

Provisional median · Limited submissionsn = 11

5.1.1 · monster · OPTIX · Windows · 1P · 8 cores · 16 threads

3,689.49 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
3,169.24 / 3,811.55
Measurement dates
2026-04-18 – 2026-07-05
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 11

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 3689.4884062463448,
    "observed_max": 3811.5494785720325,
    "observed_min": 3169.239465998656,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 11,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.2",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 8,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 16,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster",
    "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
    "version": "5.1.1"
  },
  "condition_id": "35c077aa3da4ca992f85",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "6509dfad-30a7-4e51-8171-4fa5910e556e",
    "0e6b8006-7c2e-4d65-9d85-72ab02052417",
    "ed14fc57-faca-48bd-916e-02d0a2b56ee5"
  ],
  "measured_from": "2026-04-18T23:17:10.437843+00:00",
  "measured_to": "2026-07-05T17:42:30.241083+00:00",
  "median": 3689.4884062463448,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 11,
  "sample_status": "provisional"
}
Both products have resultsBlender · 4.5.0 · classroom · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 16,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 24,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "classroom",
  "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
  "version": "4.5.0"
}

Blender scene rendering

2,852.399815642552 samples/min

Median and quartilesn = 33

4.5.0 · classroom · OPTIX · Windows · 1P · 16 cores · 24 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
2,777.99
P50 · Median
2,852.4
P75
2,895.81

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
2,532.05 / 2,998.49
Measurement dates
2025-07-25 – 2026-03-08
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 33

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2852.399815642552,
    "observed_max": 2998.4926575459644,
    "observed_min": 2532.053487801554,
    "percentiles": {
      "p25": 2777.986215440814,
      "p50": 2852.399815642552,
      "p75": 2895.8143644199313
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 33,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 24,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "classroom",
    "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
    "version": "4.5.0"
  },
  "condition_id": "b89faf128c2f780b6fd3",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "4b4267b4-9d00-4077-85fe-2aabc82d78c4",
    "5af570aa-7dd2-41f5-a568-07a219c1bd0a",
    "980bde14-9645-45ac-ade4-6017bbf95e94"
  ],
  "measured_from": "2025-07-25T14:06:49.080736+00:00",
  "measured_to": "2026-03-08T20:31:15.306844+00:00",
  "median": 2852.399815642552,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 2777.986215440814,
    "p50": 2852.399815642552,
    "p75": 2895.8143644199313
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 33,
  "sample_status": "quartiles"
}

Blender scene rendering

2,169.4937948277034 samples/min

Provisional median · Limited submissionsn = 14

4.5.0 · classroom · OPTIX · Windows · 1P · 16 cores · 24 threads

2,169.49 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
2,003.66 / 2,316.95
Measurement dates
2025-08-14 – 2026-03-01
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 14

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2169.4937948277034,
    "observed_max": 2316.952577624595,
    "observed_min": 2003.6562980765518,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 14,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 24,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "classroom",
    "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
    "version": "4.5.0"
  },
  "condition_id": "e9d925d7bef256f1a693",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "ff6bae74-0735-4cef-8b4a-f0e9af355767",
    "4f3619a5-4f12-4c2c-8ffd-2bd7eabaedf8",
    "cdca4c00-2477-470b-8f72-b9c0aa310fc7"
  ],
  "measured_from": "2025-08-14T07:16:02.166830+00:00",
  "measured_to": "2026-03-01T09:04:08.167774+00:00",
  "median": 2169.4937948277034,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 14,
  "sample_status": "provisional"
}
Both products have resultsBlender · 4.5.0 · monster + junkshop + classroom · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 16,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 24,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "monster + junkshop + classroom",
  "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
  "version": "4.5.0"
}

Blender complete benchmark

11,305.605054123425 samples/min

Median and quartilesn = 33

4.5.0 · monster + junkshop + classroom · OPTIX · Windows · 1P · 16 cores · 24 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
11,014.97
P50 · Median
11,305.61
P75
11,454.87

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
10,197.74 / 12,089.52
Measurement dates
2025-07-25 – 2026-03-08
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 33

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 11305.605054123425,
    "observed_max": 12089.524914889054,
    "observed_min": 10197.740346325285,
    "percentiles": {
      "p25": 11014.971555796257,
      "p50": 11305.605054123425,
      "p75": 11454.865719579007
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 33,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 24,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster + junkshop + classroom",
    "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
    "version": "4.5.0"
  },
  "condition_id": "01245e0ba9c067ef6e62",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "4b4267b4-9d00-4077-85fe-2aabc82d78c4",
    "5af570aa-7dd2-41f5-a568-07a219c1bd0a",
    "980bde14-9645-45ac-ade4-6017bbf95e94"
  ],
  "measured_from": "2025-07-25T14:06:49.080736+00:00",
  "measured_to": "2026-03-08T20:31:15.306844+00:00",
  "median": 11305.605054123425,
  "parameter_id": "benchmark.blender.total_samples_per_minute",
  "percentiles": {
    "p25": 11014.971555796257,
    "p50": 11305.605054123425,
    "p75": 11454.865719579007
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 33,
  "sample_status": "quartiles"
}

Blender complete benchmark

8,608.461190297823 samples/min

Provisional median · Limited submissionsn = 14

4.5.0 · monster + junkshop + classroom · OPTIX · Windows · 1P · 16 cores · 24 threads

8,608.46 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
7,884.73 / 9,224.11
Measurement dates
2025-08-14 – 2026-03-01
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 14

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 8608.461190297823,
    "observed_max": 9224.110985319836,
    "observed_min": 7884.72985641597,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 14,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 24,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster + junkshop + classroom",
    "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
    "version": "4.5.0"
  },
  "condition_id": "0ae0accd457b1f6641be",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "ff6bae74-0735-4cef-8b4a-f0e9af355767",
    "4f3619a5-4f12-4c2c-8ffd-2bd7eabaedf8",
    "cdca4c00-2477-470b-8f72-b9c0aa310fc7"
  ],
  "measured_from": "2025-08-14T07:16:02.166830+00:00",
  "measured_to": "2026-03-01T09:04:08.167774+00:00",
  "median": 8608.461190297823,
  "parameter_id": "benchmark.blender.total_samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 14,
  "sample_status": "provisional"
}
Both products have resultsBlender · 4.5.0 · junkshop · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 16,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 24,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "junkshop",
  "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
  "version": "4.5.0"
}

Blender scene rendering

2,803.046244396757 samples/min

Median and quartilesn = 33

4.5.0 · junkshop · OPTIX · Windows · 1P · 16 cores · 24 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
2,756.88
P50 · Median
2,803.05
P75
2,836.17

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
2,486.31 / 3,062.98
Measurement dates
2025-07-25 – 2026-03-08
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 33

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2803.046244396757,
    "observed_max": 3062.9812313184552,
    "observed_min": 2486.313629540434,
    "percentiles": {
      "p25": 2756.882430533558,
      "p50": 2803.046244396757,
      "p75": 2836.168461271585
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 33,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 24,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "junkshop",
    "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
    "version": "4.5.0"
  },
  "condition_id": "d9be52c9f99d0056c924",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "4b4267b4-9d00-4077-85fe-2aabc82d78c4",
    "5af570aa-7dd2-41f5-a568-07a219c1bd0a",
    "980bde14-9645-45ac-ade4-6017bbf95e94"
  ],
  "measured_from": "2025-07-25T14:06:07.646109+00:00",
  "measured_to": "2026-03-08T20:30:34.524011+00:00",
  "median": 2803.046244396757,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 2756.882430533558,
    "p50": 2803.046244396757,
    "p75": 2836.168461271585
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 33,
  "sample_status": "quartiles"
}

Blender scene rendering

2,157.9466180497348 samples/min

Provisional median · Limited submissionsn = 14

4.5.0 · junkshop · OPTIX · Windows · 1P · 16 cores · 24 threads

2,157.95 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
1,978.48 / 2,332.12
Measurement dates
2025-08-14 – 2026-03-01
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 14

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2157.9466180497348,
    "observed_max": 2332.1205420618867,
    "observed_min": 1978.4754736598964,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 14,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 24,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "junkshop",
    "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
    "version": "4.5.0"
  },
  "condition_id": "b4b1335a6efef418edbd",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "ff6bae74-0735-4cef-8b4a-f0e9af355767",
    "4f3619a5-4f12-4c2c-8ffd-2bd7eabaedf8",
    "cdca4c00-2477-470b-8f72-b9c0aa310fc7"
  ],
  "measured_from": "2025-08-14T07:15:25.968981+00:00",
  "measured_to": "2026-03-01T09:03:31.547523+00:00",
  "median": 2157.9466180497348,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 14,
  "sample_status": "provisional"
}
Both products have resultsBlender · 4.5.0 · monster · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 16,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 24,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "monster",
  "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
  "version": "4.5.0"
}

Blender scene rendering

5,673.980956805273 samples/min

Median and quartilesn = 33

4.5.0 · monster · OPTIX · Windows · 1P · 16 cores · 24 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
5,506.59
P50 · Median
5,673.98
P75
5,723.08

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
5,179.37 / 6,043.83
Measurement dates
2025-07-25 – 2026-03-08
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 33

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 5673.980956805273,
    "observed_max": 6043.8253054552515,
    "observed_min": 5179.373228983298,
    "percentiles": {
      "p25": 5506.588359105658,
      "p50": 5673.980956805273,
      "p75": 5723.080384230446
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 33,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 24,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster",
    "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
    "version": "4.5.0"
  },
  "condition_id": "472eb3be12ca5e6d0f74",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "4b4267b4-9d00-4077-85fe-2aabc82d78c4",
    "5af570aa-7dd2-41f5-a568-07a219c1bd0a",
    "980bde14-9645-45ac-ade4-6017bbf95e94"
  ],
  "measured_from": "2025-07-25T14:05:16.079484+00:00",
  "measured_to": "2026-03-08T20:29:41.349239+00:00",
  "median": 5673.980956805273,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 5506.588359105658,
    "p50": 5673.980956805273,
    "p75": 5723.080384230446
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 33,
  "sample_status": "quartiles"
}

Blender scene rendering

4,281.410527653991 samples/min

Provisional median · Limited submissionsn = 14

4.5.0 · monster · OPTIX · Windows · 1P · 16 cores · 24 threads

4,281.41 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
3,902.6 / 4,577.67
Measurement dates
2025-08-14 – 2026-03-01
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 14

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 4281.410527653991,
    "observed_max": 4577.6652040645695,
    "observed_min": 3902.598084679522,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 14,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 24,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster",
    "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
    "version": "4.5.0"
  },
  "condition_id": "184e066f2be34440ace1",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "ff6bae74-0735-4cef-8b4a-f0e9af355767",
    "4f3619a5-4f12-4c2c-8ffd-2bd7eabaedf8",
    "cdca4c00-2477-470b-8f72-b9c0aa310fc7"
  ],
  "measured_from": "2025-08-14T07:14:40.386389+00:00",
  "measured_to": "2026-03-01T09:02:46.662053+00:00",
  "median": 4281.410527653991,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 14,
  "sample_status": "provisional"
}
Both products have resultsBlender · 4.5.0 · classroom · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 16,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 32,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "classroom",
  "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
  "version": "4.5.0"
}

Blender scene rendering

2,779.3343262225426 samples/min

Submitted benchmark distributionn = 189

4.5.0 · classroom · OPTIX · Windows · 1P · 16 cores · 32 threads

1,624.88–1,695.34: 1 Submissions1,695.34–1,765.8: 0 Submissions1,765.8–1,836.26: 0 Submissions1,836.26–1,906.72: 0 Submissions1,906.72–1,977.18: 0 Submissions1,977.18–2,047.63: 0 Submissions2,047.63–2,118.09: 0 Submissions2,118.09–2,188.55: 1 Submissions2,188.55–2,259.01: 0 Submissions2,259.01–2,329.47: 2 Submissions2,329.47–2,399.92: 5 Submissions2,399.92–2,470.38: 7 Submissions2,470.38–2,540.84: 10 Submissions2,540.84–2,611.3: 27 Submissions2,611.3–2,681.76: 19 Submissions2,681.76–2,752.22: 11 Submissions2,752.22–2,822.67: 30 Submissions2,822.67–2,893.13: 46 Submissions2,893.13–2,963.59: 26 Submissions2,963.59–3,034.05: 4 Submissionsn = 461,624.883,034.05

Box: middle 50% (P25–P75)Vertical line: median (P50)Horizontal line: P5–P95

P5
2,410.36
P25
2,600.8
P50 · Median
2,779.33
P75
2,861.57
P95
2,932.98

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
1,624.88 / 3,034.05
Measurement dates
2025-07-17 – 2026-03-07
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 189

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "histogram": [
      {
        "count": 1,
        "from": 1624.884949063824,
        "to": 1695.3430996040947
      },
      {
        "count": 0,
        "from": 1695.3430996040947,
        "to": 1765.8012501443654
      },
      {
        "count": 0,
        "from": 1765.8012501443654,
        "to": 1836.2594006846361
      },
      {
        "count": 0,
        "from": 1836.2594006846361,
        "to": 1906.7175512249069
      },
      {
        "count": 0,
        "from": 1906.7175512249069,
        "to": 1977.1757017651776
      },
      {
        "count": 0,
        "from": 1977.1757017651776,
        "to": 2047.6338523054483
      },
      {
        "count": 0,
        "from": 2047.6338523054483,
        "to": 2118.092002845719
      },
      {
        "count": 1,
        "from": 2118.092002845719,
        "to": 2188.5501533859897
      },
      {
        "count": 0,
        "from": 2188.5501533859897,
        "to": 2259.0083039262604
      },
      {
        "count": 2,
        "from": 2259.0083039262604,
        "to": 2329.466454466531
      },
      {
        "count": 5,
        "from": 2329.466454466531,
        "to": 2399.924605006802
      },
      {
        "count": 7,
        "from": 2399.924605006802,
        "to": 2470.3827555470725
      },
      {
        "count": 10,
        "from": 2470.3827555470725,
        "to": 2540.8409060873432
      },
      {
        "count": 27,
        "from": 2540.8409060873432,
        "to": 2611.299056627614
      },
      {
        "count": 19,
        "from": 2611.299056627614,
        "to": 2681.7572071678846
      },
      {
        "count": 11,
        "from": 2681.7572071678846,
        "to": 2752.2153577081554
      },
      {
        "count": 30,
        "from": 2752.2153577081554,
        "to": 2822.673508248426
      },
      {
        "count": 46,
        "from": 2822.673508248426,
        "to": 2893.1316587886968
      },
      {
        "count": 26,
        "from": 2893.1316587886968,
        "to": 2963.5898093289675
      },
      {
        "count": 4,
        "from": 2963.5898093289675,
        "to": 3034.047959869238
      }
    ],
    "independent_system_count": null,
    "median": 2779.3343262225426,
    "observed_max": 3034.047959869238,
    "observed_min": 1624.884949063824,
    "percentiles": {
      "p25": 2600.7986442906986,
      "p5": 2410.355021649777,
      "p50": 2779.3343262225426,
      "p75": 2861.5679723085123,
      "p95": 2932.983879822206
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 189,
    "sample_status": "distribution",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "classroom",
    "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
    "version": "4.5.0"
  },
  "condition_id": "a0574cda9d59dcc42835",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "38a146b5-486a-4b18-a7db-c2845574b867",
    "7e2319a5-eb57-49bb-a42c-6b46b0e017a8",
    "d302b8c3-4b10-4708-913a-39bc78d1cbe6"
  ],
  "measured_from": "2025-07-17T08:07:58.287714+00:00",
  "measured_to": "2026-03-07T13:41:07.931524+00:00",
  "median": 2779.3343262225426,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 2600.7986442906986,
    "p5": 2410.355021649777,
    "p50": 2779.3343262225426,
    "p75": 2861.5679723085123,
    "p95": 2932.983879822206
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 189,
  "sample_status": "distribution"
}

Blender scene rendering

2,112.991701675228 samples/min

Median and quartilesn = 43

4.5.0 · classroom · OPTIX · Windows · 1P · 16 cores · 32 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
1,977.92
P50 · Median
2,112.99
P75
2,144.51

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
4.95 / 2,266.6
Measurement dates
2025-07-18 – 2026-03-01
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 43

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2112.991701675228,
    "observed_max": 2266.5987320480253,
    "observed_min": 4.94509420692928,
    "percentiles": {
      "p25": 1977.9213379343994,
      "p50": 2112.991701675228,
      "p75": 2144.5067381992208
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 43,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "classroom",
    "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
    "version": "4.5.0"
  },
  "condition_id": "3e0dbe2fbbef6713ee06",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "e1b7f537-ff17-40bf-be9c-66e16be74ace",
    "accfcf06-5c09-4274-bd10-b3b0f67d5cc4",
    "b5f37b45-6f84-4bef-b759-37e8d4455c38"
  ],
  "measured_from": "2025-07-18T19:39:15.935937+00:00",
  "measured_to": "2026-03-01T10:33:56.194884+00:00",
  "median": 2112.991701675228,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 1977.9213379343994,
    "p50": 2112.991701675228,
    "p75": 2144.5067381992208
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 43,
  "sample_status": "quartiles"
}
Both products have resultsBlender · 4.5.0 · monster + junkshop + classroom · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 16,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 32,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "monster + junkshop + classroom",
  "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
  "version": "4.5.0"
}

Blender complete benchmark

11,015.77299971176 samples/min

Submitted benchmark distributionn = 189

4.5.0 · monster + junkshop + classroom · OPTIX · Windows · 1P · 16 cores · 32 threads

8,216.84–8,411.61: 1 Submissions8,411.61–8,606.38: 1 Submissions8,606.38–8,801.15: 0 Submissions8,801.15–8,995.92: 1 Submissions8,995.92–9,190.69: 0 Submissions9,190.69–9,385.46: 1 Submissions9,385.46–9,580.23: 1 Submissions9,580.23–9,775: 5 Submissions9,775–9,969.77: 6 Submissions9,969.77–10,164.54: 11 Submissions10,164.54–10,359.31: 14 Submissions10,359.31–10,554.08: 14 Submissions10,554.08–10,748.85: 18 Submissions10,748.85–10,943.62: 15 Submissions10,943.62–11,138.39: 26 Submissions11,138.39–11,333.16: 27 Submissions11,333.16–11,527.93: 24 Submissions11,527.93–11,722.7: 20 Submissions11,722.7–11,917.47: 2 Submissions11,917.47–12,112.24: 2 Submissionsn = 278,216.8412,112.24

Box: middle 50% (P25–P75)Vertical line: median (P50)Horizontal line: P5–P95

P5
9,790.08
P25
10,497.89
P50 · Median
11,015.77
P75
11,333.76
P95
11,617

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
8,216.84 / 12,112.24
Measurement dates
2025-07-17 – 2026-03-07
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 189

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "histogram": [
      {
        "count": 1,
        "from": 8216.840633958622,
        "to": 8411.610564644076
      },
      {
        "count": 1,
        "from": 8411.610564644076,
        "to": 8606.380495329531
      },
      {
        "count": 0,
        "from": 8606.380495329531,
        "to": 8801.150426014985
      },
      {
        "count": 1,
        "from": 8801.150426014985,
        "to": 8995.920356700439
      },
      {
        "count": 0,
        "from": 8995.920356700439,
        "to": 9190.690287385893
      },
      {
        "count": 1,
        "from": 9190.690287385893,
        "to": 9385.460218071348
      },
      {
        "count": 1,
        "from": 9385.460218071348,
        "to": 9580.230148756802
      },
      {
        "count": 5,
        "from": 9580.230148756802,
        "to": 9775.000079442256
      },
      {
        "count": 6,
        "from": 9775.000079442256,
        "to": 9969.770010127711
      },
      {
        "count": 11,
        "from": 9969.770010127711,
        "to": 10164.539940813165
      },
      {
        "count": 14,
        "from": 10164.539940813165,
        "to": 10359.309871498619
      },
      {
        "count": 14,
        "from": 10359.309871498619,
        "to": 10554.079802184075
      },
      {
        "count": 18,
        "from": 10554.079802184075,
        "to": 10748.849732869528
      },
      {
        "count": 15,
        "from": 10748.849732869528,
        "to": 10943.619663554982
      },
      {
        "count": 26,
        "from": 10943.619663554982,
        "to": 11138.389594240438
      },
      {
        "count": 27,
        "from": 11138.389594240438,
        "to": 11333.159524925892
      },
      {
        "count": 24,
        "from": 11333.159524925892,
        "to": 11527.929455611345
      },
      {
        "count": 20,
        "from": 11527.929455611345,
        "to": 11722.6993862968
      },
      {
        "count": 2,
        "from": 11722.6993862968,
        "to": 11917.469316982255
      },
      {
        "count": 2,
        "from": 11917.469316982255,
        "to": 12112.239247667709
      }
    ],
    "independent_system_count": null,
    "median": 11015.77299971176,
    "observed_max": 12112.239247667709,
    "observed_min": 8216.840633958622,
    "percentiles": {
      "p25": 10497.88622858252,
      "p5": 9790.07981066835,
      "p50": 11015.77299971176,
      "p75": 11333.763639417308,
      "p95": 11616.999208145216
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 189,
    "sample_status": "distribution",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster + junkshop + classroom",
    "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
    "version": "4.5.0"
  },
  "condition_id": "2a1f6d0a2fe56f576876",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "38a146b5-486a-4b18-a7db-c2845574b867",
    "7e2319a5-eb57-49bb-a42c-6b46b0e017a8",
    "d302b8c3-4b10-4708-913a-39bc78d1cbe6"
  ],
  "measured_from": "2025-07-17T08:07:58.287714+00:00",
  "measured_to": "2026-03-07T13:41:07.931524+00:00",
  "median": 11015.77299971176,
  "parameter_id": "benchmark.blender.total_samples_per_minute",
  "percentiles": {
    "p25": 10497.88622858252,
    "p5": 9790.07981066835,
    "p50": 11015.77299971176,
    "p75": 11333.763639417308,
    "p95": 11616.999208145216
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 189,
  "sample_status": "distribution"
}

Blender complete benchmark

8,378.177608688 samples/min

Median and quartilesn = 43

4.5.0 · monster + junkshop + classroom · OPTIX · Windows · 1P · 16 cores · 32 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
7,952.12
P50 · Median
8,378.18
P75
8,528.13

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
63.07 / 9,105.98
Measurement dates
2025-07-18 – 2026-03-01
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 43

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 8378.177608688,
    "observed_max": 9105.979578391632,
    "observed_min": 63.07365701717211,
    "percentiles": {
      "p25": 7952.119814401386,
      "p50": 8378.177608688,
      "p75": 8528.12700552632
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 43,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster + junkshop + classroom",
    "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
    "version": "4.5.0"
  },
  "condition_id": "e490aa06bd376fa0492c",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "e1b7f537-ff17-40bf-be9c-66e16be74ace",
    "accfcf06-5c09-4274-bd10-b3b0f67d5cc4",
    "b5f37b45-6f84-4bef-b759-37e8d4455c38"
  ],
  "measured_from": "2025-07-18T19:39:15.935937+00:00",
  "measured_to": "2026-03-01T10:33:56.194884+00:00",
  "median": 8378.177608688,
  "parameter_id": "benchmark.blender.total_samples_per_minute",
  "percentiles": {
    "p25": 7952.119814401386,
    "p50": 8378.177608688,
    "p75": 8528.12700552632
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 43,
  "sample_status": "quartiles"
}
Both products have resultsBlender · 4.5.0 · junkshop · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 16,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 32,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "junkshop",
  "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
  "version": "4.5.0"
}

Blender scene rendering

2,737.686119684976 samples/min

Submitted benchmark distributionn = 189

4.5.0 · junkshop · OPTIX · Windows · 1P · 16 cores · 32 threads

1,799.7–1,861.45: 1 Submissions1,861.45–1,923.19: 0 Submissions1,923.19–1,984.93: 0 Submissions1,984.93–2,046.68: 0 Submissions2,046.68–2,108.42: 1 Submissions2,108.42–2,170.16: 1 Submissions2,170.16–2,231.91: 1 Submissions2,231.91–2,293.65: 1 Submissions2,293.65–2,355.39: 2 Submissions2,355.39–2,417.14: 3 Submissions2,417.14–2,478.88: 9 Submissions2,478.88–2,540.63: 16 Submissions2,540.63–2,602.37: 14 Submissions2,602.37–2,664.11: 15 Submissions2,664.11–2,725.86: 23 Submissions2,725.86–2,787.6: 43 Submissions2,787.6–2,849.34: 32 Submissions2,849.34–2,911.09: 17 Submissions2,911.09–2,972.83: 7 Submissions2,972.83–3,034.57: 3 Submissionsn = 431,799.73,034.57

Box: middle 50% (P25–P75)Vertical line: median (P50)Horizontal line: P5–P95

P5
2,417.48
P25
2,593.22
P50 · Median
2,737.69
P75
2,803.19
P95
2,911.69

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
1,799.7 / 3,034.57
Measurement dates
2025-07-17 – 2026-03-07
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 189

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "histogram": [
      {
        "count": 1,
        "from": 1799.7040057548388,
        "to": 1861.4474258482091
      },
      {
        "count": 0,
        "from": 1861.4474258482091,
        "to": 1923.1908459415795
      },
      {
        "count": 0,
        "from": 1923.1908459415795,
        "to": 1984.9342660349498
      },
      {
        "count": 0,
        "from": 1984.9342660349498,
        "to": 2046.6776861283201
      },
      {
        "count": 1,
        "from": 2046.6776861283201,
        "to": 2108.4211062216905
      },
      {
        "count": 1,
        "from": 2108.4211062216905,
        "to": 2170.164526315061
      },
      {
        "count": 1,
        "from": 2170.164526315061,
        "to": 2231.907946408431
      },
      {
        "count": 1,
        "from": 2231.907946408431,
        "to": 2293.6513665018015
      },
      {
        "count": 2,
        "from": 2293.6513665018015,
        "to": 2355.3947865951723
      },
      {
        "count": 3,
        "from": 2355.3947865951723,
        "to": 2417.1382066885426
      },
      {
        "count": 9,
        "from": 2417.1382066885426,
        "to": 2478.881626781913
      },
      {
        "count": 16,
        "from": 2478.881626781913,
        "to": 2540.6250468752833
      },
      {
        "count": 14,
        "from": 2540.6250468752833,
        "to": 2602.3684669686536
      },
      {
        "count": 15,
        "from": 2602.3684669686536,
        "to": 2664.111887062024
      },
      {
        "count": 23,
        "from": 2664.111887062024,
        "to": 2725.8553071553943
      },
      {
        "count": 43,
        "from": 2725.8553071553943,
        "to": 2787.5987272487646
      },
      {
        "count": 32,
        "from": 2787.5987272487646,
        "to": 2849.342147342135
      },
      {
        "count": 17,
        "from": 2849.342147342135,
        "to": 2911.0855674355053
      },
      {
        "count": 7,
        "from": 2911.0855674355053,
        "to": 2972.8289875288756
      },
      {
        "count": 3,
        "from": 2972.8289875288756,
        "to": 3034.572407622246
      }
    ],
    "independent_system_count": null,
    "median": 2737.686119684976,
    "observed_max": 3034.572407622246,
    "observed_min": 1799.7040057548388,
    "percentiles": {
      "p25": 2593.2243339263086,
      "p5": 2417.480839564081,
      "p50": 2737.686119684976,
      "p75": 2803.1903236131548,
      "p95": 2911.687232491626
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 189,
    "sample_status": "distribution",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "junkshop",
    "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
    "version": "4.5.0"
  },
  "condition_id": "5804e5289647688a364f",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "38a146b5-486a-4b18-a7db-c2845574b867",
    "7e2319a5-eb57-49bb-a42c-6b46b0e017a8",
    "d302b8c3-4b10-4708-913a-39bc78d1cbe6"
  ],
  "measured_from": "2025-07-17T08:07:13.753374+00:00",
  "measured_to": "2026-03-07T13:40:27.100256+00:00",
  "median": 2737.686119684976,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 2593.2243339263086,
    "p5": 2417.480839564081,
    "p50": 2737.686119684976,
    "p75": 2803.1903236131548,
    "p95": 2911.687232491626
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 189,
  "sample_status": "distribution"
}

Blender scene rendering

2,106.0438577157834 samples/min

Median and quartilesn = 43

4.5.0 · junkshop · OPTIX · Windows · 1P · 16 cores · 32 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
1,986.97
P50 · Median
2,106.04
P75
2,139.95

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
52.64 / 2,320.62
Measurement dates
2025-07-18 – 2026-03-01
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 43

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2106.0438577157834,
    "observed_max": 2320.6150294379854,
    "observed_min": 52.64345433125244,
    "percentiles": {
      "p25": 1986.967613696967,
      "p50": 2106.0438577157834,
      "p75": 2139.9512313453847
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 43,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "junkshop",
    "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
    "version": "4.5.0"
  },
  "condition_id": "5fa32764d6c99a4af2ca",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "e1b7f537-ff17-40bf-be9c-66e16be74ace",
    "accfcf06-5c09-4274-bd10-b3b0f67d5cc4",
    "b5f37b45-6f84-4bef-b759-37e8d4455c38"
  ],
  "measured_from": "2025-07-18T19:38:39.901318+00:00",
  "measured_to": "2026-03-01T10:33:19.414976+00:00",
  "median": 2106.0438577157834,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 1986.967613696967,
    "p50": 2106.0438577157834,
    "p75": 2139.9512313453847
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 43,
  "sample_status": "quartiles"
}
Both products have resultsBlender · 4.5.0 · monster · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 16,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 32,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "monster",
  "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
  "version": "4.5.0"
}

Blender scene rendering

5,511.153674745089 samples/min

Submitted benchmark distributionn = 189

4.5.0 · monster · OPTIX · Windows · 1P · 16 cores · 32 threads

4,249.31–4,339.02: 1 Submissions4,339.02–4,428.74: 0 Submissions4,428.74–4,518.45: 1 Submissions4,518.45–4,608.17: 0 Submissions4,608.17–4,697.88: 1 Submissions4,697.88–4,787.6: 1 Submissions4,787.6–4,877.32: 4 Submissions4,877.32–4,967.03: 7 Submissions4,967.03–5,056.75: 6 Submissions5,056.75–5,146.46: 17 Submissions5,146.46–5,236.18: 9 Submissions5,236.18–5,325.89: 8 Submissions5,325.89–5,415.61: 23 Submissions5,415.61–5,505.32: 14 Submissions5,505.32–5,595.04: 30 Submissions5,595.04–5,684.76: 24 Submissions5,684.76–5,774.47: 28 Submissions5,774.47–5,864.19: 11 Submissions5,864.19–5,953.9: 2 Submissions5,953.9–6,043.62: 2 Submissionsn = 304,249.316,043.62

Box: middle 50% (P25–P75)Vertical line: median (P50)Horizontal line: P5–P95

P5
4,885.66
P25
5,241.49
P50 · Median
5,511.15
P75
5,669.79
P95
5,790.41

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
4,249.31 / 6,043.62
Measurement dates
2025-07-17 – 2026-03-07
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 189

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "histogram": [
      {
        "count": 1,
        "from": 4249.3054960245845,
        "to": 4339.021165232167
      },
      {
        "count": 0,
        "from": 4339.021165232167,
        "to": 4428.736834439748
      },
      {
        "count": 1,
        "from": 4428.736834439748,
        "to": 4518.452503647331
      },
      {
        "count": 0,
        "from": 4518.452503647331,
        "to": 4608.168172854913
      },
      {
        "count": 1,
        "from": 4608.168172854913,
        "to": 4697.883842062494
      },
      {
        "count": 1,
        "from": 4697.883842062494,
        "to": 4787.599511270077
      },
      {
        "count": 4,
        "from": 4787.599511270077,
        "to": 4877.315180477659
      },
      {
        "count": 7,
        "from": 4877.315180477659,
        "to": 4967.030849685241
      },
      {
        "count": 6,
        "from": 4967.030849685241,
        "to": 5056.746518892823
      },
      {
        "count": 17,
        "from": 5056.746518892823,
        "to": 5146.462188100405
      },
      {
        "count": 9,
        "from": 5146.462188100405,
        "to": 5236.177857307987
      },
      {
        "count": 8,
        "from": 5236.177857307987,
        "to": 5325.893526515569
      },
      {
        "count": 23,
        "from": 5325.893526515569,
        "to": 5415.609195723151
      },
      {
        "count": 14,
        "from": 5415.609195723151,
        "to": 5505.324864930733
      },
      {
        "count": 30,
        "from": 5505.324864930733,
        "to": 5595.040534138316
      },
      {
        "count": 24,
        "from": 5595.040534138316,
        "to": 5684.756203345897
      },
      {
        "count": 28,
        "from": 5684.756203345897,
        "to": 5774.471872553479
      },
      {
        "count": 11,
        "from": 5774.471872553479,
        "to": 5864.187541761062
      },
      {
        "count": 2,
        "from": 5864.187541761062,
        "to": 5953.903210968643
      },
      {
        "count": 2,
        "from": 5953.903210968643,
        "to": 6043.6188801762255
      }
    ],
    "independent_system_count": null,
    "median": 5511.153674745089,
    "observed_max": 6043.6188801762255,
    "observed_min": 4249.3054960245845,
    "percentiles": {
      "p25": 5241.491232967713,
      "p5": 4885.659511682764,
      "p50": 5511.153674745089,
      "p75": 5669.786330421297,
      "p95": 5790.413745649459
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 189,
    "sample_status": "distribution",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster",
    "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
    "version": "4.5.0"
  },
  "condition_id": "edad593e694517044189",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "38a146b5-486a-4b18-a7db-c2845574b867",
    "7e2319a5-eb57-49bb-a42c-6b46b0e017a8",
    "d302b8c3-4b10-4708-913a-39bc78d1cbe6"
  ],
  "measured_from": "2025-07-17T08:06:10.828476+00:00",
  "measured_to": "2026-03-07T13:39:35.297234+00:00",
  "median": 5511.153674745089,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 5241.491232967713,
    "p5": 4885.659511682764,
    "p50": 5511.153674745089,
    "p75": 5669.786330421297,
    "p95": 5790.413745649459
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 189,
  "sample_status": "distribution"
}

Blender scene rendering

4,147.953646302404 samples/min

Median and quartilesn = 43

4.5.0 · monster · OPTIX · Windows · 1P · 16 cores · 32 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
3,960.77
P50 · Median
4,147.95
P75
4,245.6

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
5.49 / 4,518.77
Measurement dates
2025-07-18 – 2026-03-01
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 43

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 4147.953646302404,
    "observed_max": 4518.765816905621,
    "observed_min": 5.485108478990389,
    "percentiles": {
      "p25": 3960.7714801557067,
      "p50": 4147.953646302404,
      "p75": 4245.597994846419
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 43,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster",
    "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
    "version": "4.5.0"
  },
  "condition_id": "a09b7347b84b5299ae18",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "e1b7f537-ff17-40bf-be9c-66e16be74ace",
    "accfcf06-5c09-4274-bd10-b3b0f67d5cc4",
    "b5f37b45-6f84-4bef-b759-37e8d4455c38"
  ],
  "measured_from": "2025-07-18T19:37:54.476121+00:00",
  "measured_to": "2026-03-01T10:32:34.169945+00:00",
  "median": 4147.953646302404,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 3960.7714801557067,
    "p50": 4147.953646302404,
    "p75": 4245.597994846419
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 43,
  "sample_status": "quartiles"
}
Both products have resultsBlender · 4.5.0 · classroom · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 24,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 32,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "classroom",
  "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
  "version": "4.5.0"
}

Blender scene rendering

2,769.8395522721466 samples/min

Median and quartilesn = 96

4.5.0 · classroom · OPTIX · Windows · 1P · 24 cores · 32 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
2,621.73
P50 · Median
2,769.84
P75
2,834.9

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
801.52 / 3,103.47
Measurement dates
2025-07-18 – 2026-03-06
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 96

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2769.8395522721466,
    "observed_max": 3103.471570054612,
    "observed_min": 801.5166168444246,
    "percentiles": {
      "p25": 2621.7296970609877,
      "p50": 2769.8395522721466,
      "p75": 2834.901588768835
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 96,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 24,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "classroom",
    "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
    "version": "4.5.0"
  },
  "condition_id": "66fa01f94972f3ff6f4b",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "a4ca3e8a-c0d2-4311-abba-846258a70bbc",
    "cd492926-c08f-4a8c-8515-c131827ad9c6",
    "e5825aaf-40f7-4d2f-ba62-95533ce47f47"
  ],
  "measured_from": "2025-07-18T04:57:22.606209+00:00",
  "measured_to": "2026-03-06T08:44:27.289606+00:00",
  "median": 2769.8395522721466,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 2621.7296970609877,
    "p50": 2769.8395522721466,
    "p75": 2834.901588768835
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 96,
  "sample_status": "quartiles"
}

Blender scene rendering

2,109.389337018081 samples/min

Median and quartilesn = 44

4.5.0 · classroom · OPTIX · Windows · 1P · 24 cores · 32 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
2,017.34
P50 · Median
2,109.39
P75
2,151.03

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
1,923.11 / 2,243.21
Measurement dates
2025-07-25 – 2026-02-24
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 44

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2109.389337018081,
    "observed_max": 2243.2073182385175,
    "observed_min": 1923.111440461752,
    "percentiles": {
      "p25": 2017.3437597155698,
      "p50": 2109.389337018081,
      "p75": 2151.0316914693312
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 44,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 24,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "classroom",
    "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
    "version": "4.5.0"
  },
  "condition_id": "28c82e317f22e1d02416",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "7b637bf9-1c2f-46b1-8e09-c4e32fdd1199",
    "8a1a528d-d4d1-4e47-9d4a-aace7211875f",
    "ca8e8a7c-784a-4f45-9767-5e33e613c8a4"
  ],
  "measured_from": "2025-07-25T23:05:33.254474+00:00",
  "measured_to": "2026-02-24T19:23:37.066096+00:00",
  "median": 2109.389337018081,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 2017.3437597155698,
    "p50": 2109.389337018081,
    "p75": 2151.0316914693312
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 44,
  "sample_status": "quartiles"
}
Both products have resultsBlender · 4.5.0 · monster + junkshop + classroom · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 24,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 32,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "monster + junkshop + classroom",
  "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
  "version": "4.5.0"
}

Blender complete benchmark

11,031.780267727516 samples/min

Median and quartilesn = 96

4.5.0 · monster + junkshop + classroom · OPTIX · Windows · 1P · 24 cores · 32 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
10,487.03
P50 · Median
11,031.78
P75
11,239.74

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
3,247.95 / 12,367.52
Measurement dates
2025-07-18 – 2026-03-06
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 96

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 11031.780267727516,
    "observed_max": 12367.515921053055,
    "observed_min": 3247.9503236845762,
    "percentiles": {
      "p25": 10487.026290820857,
      "p50": 11031.780267727516,
      "p75": 11239.738622339602
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 96,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 24,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster + junkshop + classroom",
    "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
    "version": "4.5.0"
  },
  "condition_id": "7b35c802dabeb0380b3b",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "a4ca3e8a-c0d2-4311-abba-846258a70bbc",
    "cd492926-c08f-4a8c-8515-c131827ad9c6",
    "e5825aaf-40f7-4d2f-ba62-95533ce47f47"
  ],
  "measured_from": "2025-07-18T04:57:22.606209+00:00",
  "measured_to": "2026-03-06T08:44:27.289606+00:00",
  "median": 11031.780267727516,
  "parameter_id": "benchmark.blender.total_samples_per_minute",
  "percentiles": {
    "p25": 10487.026290820857,
    "p50": 11031.780267727516,
    "p75": 11239.738622339602
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 96,
  "sample_status": "quartiles"
}

Blender complete benchmark

8,419.216855851613 samples/min

Median and quartilesn = 44

4.5.0 · monster + junkshop + classroom · OPTIX · Windows · 1P · 24 cores · 32 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
8,057.15
P50 · Median
8,419.22
P75
8,540.79

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
7,628.42 / 9,019
Measurement dates
2025-07-25 – 2026-02-24
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 44

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 8419.216855851613,
    "observed_max": 9019.002303395035,
    "observed_min": 7628.4161766602065,
    "percentiles": {
      "p25": 8057.146800602071,
      "p50": 8419.216855851613,
      "p75": 8540.790891942182
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 44,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 24,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster + junkshop + classroom",
    "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
    "version": "4.5.0"
  },
  "condition_id": "5934d6071dae1f160169",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "7b637bf9-1c2f-46b1-8e09-c4e32fdd1199",
    "8a1a528d-d4d1-4e47-9d4a-aace7211875f",
    "ca8e8a7c-784a-4f45-9767-5e33e613c8a4"
  ],
  "measured_from": "2025-07-25T23:05:33.254474+00:00",
  "measured_to": "2026-02-24T19:23:37.066096+00:00",
  "median": 8419.216855851613,
  "parameter_id": "benchmark.blender.total_samples_per_minute",
  "percentiles": {
    "p25": 8057.146800602071,
    "p50": 8419.216855851613,
    "p75": 8540.790891942182
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 44,
  "sample_status": "quartiles"
}
Both products have resultsBlender · 4.5.0 · junkshop · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 24,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 32,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "junkshop",
  "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
  "version": "4.5.0"
}

Blender scene rendering

2,740.5394181724205 samples/min

Median and quartilesn = 96

4.5.0 · junkshop · OPTIX · Windows · 1P · 24 cores · 32 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
2,557.12
P50 · Median
2,740.54
P75
2,788.99

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
824.7 / 3,107.87
Measurement dates
2025-07-18 – 2026-03-06
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 96

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2740.5394181724205,
    "observed_max": 3107.8728090086815,
    "observed_min": 824.7011373063777,
    "percentiles": {
      "p25": 2557.121498933202,
      "p50": 2740.5394181724205,
      "p75": 2788.987860005457
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 96,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 24,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "junkshop",
    "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
    "version": "4.5.0"
  },
  "condition_id": "0f6edf12704ed0a3941e",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "a4ca3e8a-c0d2-4311-abba-846258a70bbc",
    "cd492926-c08f-4a8c-8515-c131827ad9c6",
    "e5825aaf-40f7-4d2f-ba62-95533ce47f47"
  ],
  "measured_from": "2025-07-18T04:56:44.075713+00:00",
  "measured_to": "2026-03-06T08:43:48.339359+00:00",
  "median": 2740.5394181724205,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 2557.121498933202,
    "p50": 2740.5394181724205,
    "p75": 2788.987860005457
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 96,
  "sample_status": "quartiles"
}

Blender scene rendering

2,115.6107928042356 samples/min

Median and quartilesn = 44

4.5.0 · junkshop · OPTIX · Windows · 1P · 24 cores · 32 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
2,013.17
P50 · Median
2,115.61
P75
2,152.1

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
1,915.32 / 2,300.03
Measurement dates
2025-07-25 – 2026-02-24
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 44

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2115.6107928042356,
    "observed_max": 2300.0304710853716,
    "observed_min": 1915.3180880865066,
    "percentiles": {
      "p25": 2013.1741410248824,
      "p50": 2115.6107928042356,
      "p75": 2152.102045289246
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 44,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 24,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "junkshop",
    "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
    "version": "4.5.0"
  },
  "condition_id": "c17a9beda76e1def60ad",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "7b637bf9-1c2f-46b1-8e09-c4e32fdd1199",
    "8a1a528d-d4d1-4e47-9d4a-aace7211875f",
    "ca8e8a7c-784a-4f45-9767-5e33e613c8a4"
  ],
  "measured_from": "2025-07-25T23:04:57.470232+00:00",
  "measured_to": "2026-02-24T19:23:00.931030+00:00",
  "median": 2115.6107928042356,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 2013.1741410248824,
    "p50": 2115.6107928042356,
    "p75": 2152.102045289246
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 44,
  "sample_status": "quartiles"
}
Both products have resultsBlender · 4.5.0 · monster · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 24,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 32,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "monster",
  "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
  "version": "4.5.0"
}

Blender scene rendering

5,521.0521429860055 samples/min

Median and quartilesn = 96

4.5.0 · monster · OPTIX · Windows · 1P · 24 cores · 32 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
5,230.52
P50 · Median
5,521.05
P75
5,620.49

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
1,621.73 / 6,156.17
Measurement dates
2025-07-18 – 2026-03-06
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 96

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 5521.0521429860055,
    "observed_max": 6156.171541989762,
    "observed_min": 1621.7325695337738,
    "percentiles": {
      "p25": 5230.519570984314,
      "p50": 5521.0521429860055,
      "p75": 5620.4940645032875
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 96,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 24,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster",
    "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
    "version": "4.5.0"
  },
  "condition_id": "21a95749d36ec873e63b",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "a4ca3e8a-c0d2-4311-abba-846258a70bbc",
    "cd492926-c08f-4a8c-8515-c131827ad9c6",
    "e5825aaf-40f7-4d2f-ba62-95533ce47f47"
  ],
  "measured_from": "2025-07-18T04:55:56.124339+00:00",
  "measured_to": "2026-03-06T08:42:53.384657+00:00",
  "median": 5521.0521429860055,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 5230.519570984314,
    "p50": 5521.0521429860055,
    "p75": 5620.4940645032875
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 96,
  "sample_status": "quartiles"
}

Blender scene rendering

4,188.042830560318 samples/min

Median and quartilesn = 44

4.5.0 · monster · OPTIX · Windows · 1P · 24 cores · 32 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
4,029.36
P50 · Median
4,188.04
P75
4,255.35

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
3,789.99 / 4,475.76
Measurement dates
2025-07-25 – 2026-02-24
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 44

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 4188.042830560318,
    "observed_max": 4475.764514071147,
    "observed_min": 3789.9866481119475,
    "percentiles": {
      "p25": 4029.3603726327756,
      "p50": 4188.042830560318,
      "p75": 4255.346029946801
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 44,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 24,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster",
    "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
    "version": "4.5.0"
  },
  "condition_id": "c070cfa5c54092ae38a3",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "7b637bf9-1c2f-46b1-8e09-c4e32fdd1199",
    "8a1a528d-d4d1-4e47-9d4a-aace7211875f",
    "ca8e8a7c-784a-4f45-9767-5e33e613c8a4"
  ],
  "measured_from": "2025-07-25T23:04:13.777882+00:00",
  "measured_to": "2026-02-24T19:22:15.952002+00:00",
  "median": 4188.042830560318,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 4029.3603726327756,
    "p50": 4188.042830560318,
    "p75": 4255.346029946801
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 44,
  "sample_status": "quartiles"
}
One-sided evidenceBlender · 4.3.0 · classroom · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4090",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 16,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 32,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "classroom",
  "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
  "version": "4.3.0"
}

Blender scene rendering

2,773.0171777017786 samples/min

Submitted benchmark distributionn = 229

4.3.0 · classroom · OPTIX · Windows · 1P · 16 cores · 32 threads

1,593.73–1,672.19: 2 Submissions1,672.19–1,750.65: 1 Submissions1,750.65–1,829.1: 0 Submissions1,829.1–1,907.56: 1 Submissions1,907.56–1,986.01: 4 Submissions1,986.01–2,064.47: 1 Submissions2,064.47–2,142.93: 1 Submissions2,142.93–2,221.38: 1 Submissions2,221.38–2,299.84: 6 Submissions2,299.84–2,378.29: 3 Submissions2,378.29–2,456.75: 2 Submissions2,456.75–2,535.21: 5 Submissions2,535.21–2,613.66: 14 Submissions2,613.66–2,692.12: 23 Submissions2,692.12–2,770.57: 46 Submissions2,770.57–2,849.03: 71 Submissions2,849.03–2,927.49: 25 Submissions2,927.49–3,005.94: 14 Submissions3,005.94–3,084.4: 3 Submissions3,084.4–3,162.85: 6 Submissionsn = 711,593.733,162.85

Box: middle 50% (P25–P75)Vertical line: median (P50)Horizontal line: P5–P95

P5
2,239.44
P25
2,678.52
P50 · Median
2,773.02
P75
2,838.92
P95
2,976.73

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
1,593.73 / 3,162.85
Measurement dates
2024-11-20 – 2026-02-18
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 229

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "histogram": [
      {
        "count": 2,
        "from": 1593.7348292520535,
        "to": 1672.1907931045257
      },
      {
        "count": 1,
        "from": 1672.1907931045257,
        "to": 1750.6467569569982
      },
      {
        "count": 0,
        "from": 1750.6467569569982,
        "to": 1829.1027208094704
      },
      {
        "count": 1,
        "from": 1829.1027208094704,
        "to": 1907.5586846619428
      },
      {
        "count": 4,
        "from": 1907.5586846619428,
        "to": 1986.014648514415
      },
      {
        "count": 1,
        "from": 1986.014648514415,
        "to": 2064.4706123668875
      },
      {
        "count": 1,
        "from": 2064.4706123668875,
        "to": 2142.92657621936
      },
      {
        "count": 1,
        "from": 2142.92657621936,
        "to": 2221.382540071832
      },
      {
        "count": 6,
        "from": 2221.382540071832,
        "to": 2299.8385039243044
      },
      {
        "count": 3,
        "from": 2299.8385039243044,
        "to": 2378.294467776777
      },
      {
        "count": 2,
        "from": 2378.294467776777,
        "to": 2456.750431629249
      },
      {
        "count": 5,
        "from": 2456.750431629249,
        "to": 2535.2063954817213
      },
      {
        "count": 14,
        "from": 2535.2063954817213,
        "to": 2613.6623593341938
      },
      {
        "count": 23,
        "from": 2613.6623593341938,
        "to": 2692.118323186666
      },
      {
        "count": 46,
        "from": 2692.118323186666,
        "to": 2770.5742870391387
      },
      {
        "count": 71,
        "from": 2770.5742870391387,
        "to": 2849.0302508916106
      },
      {
        "count": 25,
        "from": 2849.0302508916106,
        "to": 2927.4862147440826
      },
      {
        "count": 14,
        "from": 2927.4862147440826,
        "to": 3005.942178596555
      },
      {
        "count": 3,
        "from": 3005.942178596555,
        "to": 3084.3981424490275
      },
      {
        "count": 6,
        "from": 3084.3981424490275,
        "to": 3162.8541063015
      }
    ],
    "independent_system_count": null,
    "median": 2773.0171777017786,
    "observed_max": 3162.8541063015,
    "observed_min": 1593.7348292520535,
    "percentiles": {
      "p25": 2678.5211705120087,
      "p5": 2239.442600317592,
      "p50": 2773.0171777017786,
      "p75": 2838.920972376302,
      "p95": 2976.725319056946
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 229,
    "sample_status": "distribution",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "classroom",
    "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
    "version": "4.3.0"
  },
  "condition_id": "a299b14cb6606e2ea270",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "4171ff67-883a-4712-a8f6-936002c06726",
    "ae46ed4d-6482-44d2-9694-d24b07da4cb8",
    "56289697-f21c-47eb-8893-b16e2d34b504"
  ],
  "measured_from": "2024-11-20T21:54:24.584004+00:00",
  "measured_to": "2026-02-18T14:43:08.136343+00:00",
  "median": 2773.0171777017786,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 2678.5211705120087,
    "p5": 2239.442600317592,
    "p50": 2773.0171777017786,
    "p75": 2838.920972376302,
    "p95": 2976.725319056946
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 229,
  "sample_status": "distribution"
}
No comparable data
One-sided evidenceBlender · 4.3.0 · monster + junkshop + classroom · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4090",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 16,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 32,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "monster + junkshop + classroom",
  "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
  "version": "4.3.0"
}

Blender complete benchmark

11,005.639510848376 samples/min

Submitted benchmark distributionn = 229

4.3.0 · monster + junkshop + classroom · OPTIX · Windows · 1P · 16 cores · 32 threads

6,234.79–6,550.79: 2 Submissions6,550.79–6,866.78: 1 Submissions6,866.78–7,182.78: 0 Submissions7,182.78–7,498.78: 0 Submissions7,498.78–7,814.77: 4 Submissions7,814.77–8,130.77: 0 Submissions8,130.77–8,446.77: 2 Submissions8,446.77–8,762.76: 4 Submissions8,762.76–9,078.76: 2 Submissions9,078.76–9,394.76: 5 Submissions9,394.76–9,710.75: 3 Submissions9,710.75–10,026.75: 5 Submissions10,026.75–10,342.75: 11 Submissions10,342.75–10,658.74: 17 Submissions10,658.74–10,974.74: 50 Submissions10,974.74–11,290.74: 72 Submissions11,290.74–11,606.73: 13 Submissions11,606.73–11,922.73: 28 Submissions11,922.73–12,238.72: 3 Submissions12,238.72–12,554.72: 7 Submissionsn = 726,234.7912,554.72

Box: middle 50% (P25–P75)Vertical line: median (P50)Horizontal line: P5–P95

P5
8,647.85
P25
10,693.2
P50 · Median
11,005.64
P75
11,221.3
P95
11,903.06

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
6,234.79 / 12,554.72
Measurement dates
2024-11-20 – 2026-02-18
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 229

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "histogram": [
      {
        "count": 2,
        "from": 6234.791994408175,
        "to": 6550.788440424106
      },
      {
        "count": 1,
        "from": 6550.788440424106,
        "to": 6866.784886440037
      },
      {
        "count": 0,
        "from": 6866.784886440037,
        "to": 7182.7813324559675
      },
      {
        "count": 0,
        "from": 7182.7813324559675,
        "to": 7498.777778471898
      },
      {
        "count": 4,
        "from": 7498.777778471898,
        "to": 7814.77422448783
      },
      {
        "count": 0,
        "from": 7814.77422448783,
        "to": 8130.770670503761
      },
      {
        "count": 2,
        "from": 8130.770670503761,
        "to": 8446.767116519692
      },
      {
        "count": 4,
        "from": 8446.767116519692,
        "to": 8762.763562535623
      },
      {
        "count": 2,
        "from": 8762.763562535623,
        "to": 9078.760008551553
      },
      {
        "count": 5,
        "from": 9078.760008551553,
        "to": 9394.756454567483
      },
      {
        "count": 3,
        "from": 9394.756454567483,
        "to": 9710.752900583415
      },
      {
        "count": 5,
        "from": 9710.752900583415,
        "to": 10026.749346599347
      },
      {
        "count": 11,
        "from": 10026.749346599347,
        "to": 10342.745792615278
      },
      {
        "count": 17,
        "from": 10342.745792615278,
        "to": 10658.742238631208
      },
      {
        "count": 50,
        "from": 10658.742238631208,
        "to": 10974.738684647138
      },
      {
        "count": 72,
        "from": 10974.738684647138,
        "to": 11290.73513066307
      },
      {
        "count": 13,
        "from": 11290.73513066307,
        "to": 11606.731576679002
      },
      {
        "count": 28,
        "from": 11606.731576679002,
        "to": 11922.728022694931
      },
      {
        "count": 3,
        "from": 11922.728022694931,
        "to": 12238.724468710861
      },
      {
        "count": 7,
        "from": 12238.724468710861,
        "to": 12554.720914726793
      }
    ],
    "independent_system_count": null,
    "median": 11005.639510848376,
    "observed_max": 12554.720914726793,
    "observed_min": 6234.791994408175,
    "percentiles": {
      "p25": 10693.202006419431,
      "p5": 8647.847007393224,
      "p50": 11005.639510848376,
      "p75": 11221.298097382321,
      "p95": 11903.059296482019
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 229,
    "sample_status": "distribution",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster + junkshop + classroom",
    "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
    "version": "4.3.0"
  },
  "condition_id": "9ae933aa7a2dbfc778e8",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "4171ff67-883a-4712-a8f6-936002c06726",
    "ae46ed4d-6482-44d2-9694-d24b07da4cb8",
    "56289697-f21c-47eb-8893-b16e2d34b504"
  ],
  "measured_from": "2024-11-20T21:54:24.584004+00:00",
  "measured_to": "2026-02-18T14:43:08.136343+00:00",
  "median": 11005.639510848376,
  "parameter_id": "benchmark.blender.total_samples_per_minute",
  "percentiles": {
    "p25": 10693.202006419431,
    "p5": 8647.847007393224,
    "p50": 11005.639510848376,
    "p75": 11221.298097382321,
    "p95": 11903.059296482019
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 229,
  "sample_status": "distribution"
}
No comparable data
One-sided evidenceBlender · 4.3.0 · junkshop · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4090",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 16,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 32,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "junkshop",
  "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
  "version": "4.3.0"
}

Blender scene rendering

2,704.1357422963956 samples/min

Submitted benchmark distributionn = 229

4.3.0 · junkshop · OPTIX · Windows · 1P · 16 cores · 32 threads

46.99–201.99: 2 Submissions201.99–356.98: 0 Submissions356.98–511.97: 0 Submissions511.97–666.97: 0 Submissions666.97–821.96: 0 Submissions821.96–976.96: 0 Submissions976.96–1,131.95: 0 Submissions1,131.95–1,286.94: 0 Submissions1,286.94–1,441.94: 0 Submissions1,441.94–1,596.93: 2 Submissions1,596.93–1,751.93: 1 Submissions1,751.93–1,906.92: 3 Submissions1,906.92–2,061.91: 4 Submissions2,061.91–2,216.91: 4 Submissions2,216.91–2,371.9: 6 Submissions2,371.9–2,526.89: 15 Submissions2,526.89–2,681.89: 57 Submissions2,681.89–2,836.88: 93 Submissions2,836.88–2,991.88: 33 Submissions2,991.88–3,146.87: 9 Submissionsn = 9346.993,146.87

Box: middle 50% (P25–P75)Vertical line: median (P50)Horizontal line: P5–P95

P5
2,067.96
P25
2,616.79
P50 · Median
2,704.14
P75
2,758.52
P95
2,969.6

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
46.99 / 3,146.87
Measurement dates
2024-11-20 – 2026-02-18
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 229

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "histogram": [
      {
        "count": 2,
        "from": 46.992542544567854,
        "to": 201.98641404587522
      },
      {
        "count": 0,
        "from": 201.98641404587522,
        "to": 356.98028554718263
      },
      {
        "count": 0,
        "from": 356.98028554718263,
        "to": 511.97415704849004
      },
      {
        "count": 0,
        "from": 511.97415704849004,
        "to": 666.9680285497974
      },
      {
        "count": 0,
        "from": 666.9680285497974,
        "to": 821.9619000511047
      },
      {
        "count": 0,
        "from": 821.9619000511047,
        "to": 976.9557715524122
      },
      {
        "count": 0,
        "from": 976.9557715524122,
        "to": 1131.9496430537195
      },
      {
        "count": 0,
        "from": 1131.9496430537195,
        "to": 1286.943514555027
      },
      {
        "count": 0,
        "from": 1286.943514555027,
        "to": 1441.9373860563344
      },
      {
        "count": 2,
        "from": 1441.9373860563344,
        "to": 1596.9312575576416
      },
      {
        "count": 1,
        "from": 1596.9312575576416,
        "to": 1751.925129058949
      },
      {
        "count": 3,
        "from": 1751.925129058949,
        "to": 1906.9190005602566
      },
      {
        "count": 4,
        "from": 1906.9190005602566,
        "to": 2061.9128720615636
      },
      {
        "count": 4,
        "from": 2061.9128720615636,
        "to": 2216.906743562871
      },
      {
        "count": 6,
        "from": 2216.906743562871,
        "to": 2371.9006150641785
      },
      {
        "count": 15,
        "from": 2371.9006150641785,
        "to": 2526.8944865654857
      },
      {
        "count": 57,
        "from": 2526.8944865654857,
        "to": 2681.888358066793
      },
      {
        "count": 93,
        "from": 2681.888358066793,
        "to": 2836.8822295681007
      },
      {
        "count": 33,
        "from": 2836.8822295681007,
        "to": 2991.876101069408
      },
      {
        "count": 9,
        "from": 2991.876101069408,
        "to": 3146.869972570715
      }
    ],
    "independent_system_count": null,
    "median": 2704.1357422963956,
    "observed_max": 3146.869972570715,
    "observed_min": 46.992542544567854,
    "percentiles": {
      "p25": 2616.7900765145787,
      "p5": 2067.961838197187,
      "p50": 2704.1357422963956,
      "p75": 2758.5178736523435,
      "p95": 2969.6024842811876
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 229,
    "sample_status": "distribution",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "junkshop",
    "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
    "version": "4.3.0"
  },
  "condition_id": "a9f99d8d13181277b0c9",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "4171ff67-883a-4712-a8f6-936002c06726",
    "ae46ed4d-6482-44d2-9694-d24b07da4cb8",
    "56289697-f21c-47eb-8893-b16e2d34b504"
  ],
  "measured_from": "2024-11-20T21:53:42.999719+00:00",
  "measured_to": "2026-02-18T14:42:27.249088+00:00",
  "median": 2704.1357422963956,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 2616.7900765145787,
    "p5": 2067.961838197187,
    "p50": 2704.1357422963956,
    "p75": 2758.5178736523435,
    "p95": 2969.6024842811876
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 229,
  "sample_status": "distribution"
}
No comparable data
One-sided evidenceBlender · 4.3.0 · monster · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4090",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 16,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 32,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "monster",
  "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
  "version": "4.3.0"
}

Blender scene rendering

5,530.80339223808 samples/min

Submitted benchmark distributionn = 229

4.3.0 · monster · OPTIX · Windows · 1P · 16 cores · 32 threads

3,069.23–3,229.5: 2 Submissions3,229.5–3,389.77: 0 Submissions3,389.77–3,550.04: 1 Submissions3,550.04–3,710.31: 0 Submissions3,710.31–3,870.58: 2 Submissions3,870.58–4,030.85: 2 Submissions4,030.85–4,191.12: 0 Submissions4,191.12–4,351.39: 1 Submissions4,351.39–4,511.65: 4 Submissions4,511.65–4,671.92: 3 Submissions4,671.92–4,832.19: 5 Submissions4,832.19–4,992.46: 5 Submissions4,992.46–5,152.73: 8 Submissions5,152.73–5,313: 17 Submissions5,313–5,473.27: 37 Submissions5,473.27–5,633.54: 77 Submissions5,633.54–5,793.81: 25 Submissions5,793.81–5,954.07: 27 Submissions5,954.07–6,114.34: 5 Submissions6,114.34–6,274.61: 8 Submissionsn = 773,069.236,274.61

Box: middle 50% (P25–P75)Vertical line: median (P50)Horizontal line: P5–P95

P5
4,507.2
P25
5,368.04
P50 · Median
5,530.8
P75
5,652.73
P95
5,969.59

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
3,069.23 / 6,274.61
Measurement dates
2024-11-20 – 2026-02-18
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 229

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "histogram": [
      {
        "count": 2,
        "from": 3069.2339911507415,
        "to": 3229.5029120248146
      },
      {
        "count": 0,
        "from": 3229.5029120248146,
        "to": 3389.7718328988876
      },
      {
        "count": 1,
        "from": 3389.7718328988876,
        "to": 3550.0407537729607
      },
      {
        "count": 0,
        "from": 3550.0407537729607,
        "to": 3710.3096746470333
      },
      {
        "count": 2,
        "from": 3710.3096746470333,
        "to": 3870.5785955211063
      },
      {
        "count": 2,
        "from": 3870.5785955211063,
        "to": 4030.8475163951794
      },
      {
        "count": 0,
        "from": 4030.8475163951794,
        "to": 4191.116437269252
      },
      {
        "count": 1,
        "from": 4191.116437269252,
        "to": 4351.385358143325
      },
      {
        "count": 4,
        "from": 4351.385358143325,
        "to": 4511.654279017398
      },
      {
        "count": 3,
        "from": 4511.654279017398,
        "to": 4671.923199891471
      },
      {
        "count": 5,
        "from": 4671.923199891471,
        "to": 4832.192120765544
      },
      {
        "count": 5,
        "from": 4832.192120765544,
        "to": 4992.461041639617
      },
      {
        "count": 8,
        "from": 4992.461041639617,
        "to": 5152.72996251369
      },
      {
        "count": 17,
        "from": 5152.72996251369,
        "to": 5312.998883387763
      },
      {
        "count": 37,
        "from": 5312.998883387763,
        "to": 5473.267804261835
      },
      {
        "count": 77,
        "from": 5473.267804261835,
        "to": 5633.536725135909
      },
      {
        "count": 25,
        "from": 5633.536725135909,
        "to": 5793.8056460099815
      },
      {
        "count": 27,
        "from": 5793.8056460099815,
        "to": 5954.0745668840555
      },
      {
        "count": 5,
        "from": 5954.0745668840555,
        "to": 6114.343487758128
      },
      {
        "count": 8,
        "from": 6114.343487758128,
        "to": 6274.612408632201
      }
    ],
    "independent_system_count": null,
    "median": 5530.80339223808,
    "observed_max": 6274.612408632201,
    "observed_min": 3069.2339911507415,
    "percentiles": {
      "p25": 5368.0415836601915,
      "p5": 4507.201258554848,
      "p50": 5530.80339223808,
      "p75": 5652.7320495865815,
      "p95": 5969.589141632598
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 229,
    "sample_status": "distribution",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 16,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster",
    "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
    "version": "4.3.0"
  },
  "condition_id": "d53f622cba3102295e18",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "4171ff67-883a-4712-a8f6-936002c06726",
    "ae46ed4d-6482-44d2-9694-d24b07da4cb8",
    "56289697-f21c-47eb-8893-b16e2d34b504"
  ],
  "measured_from": "2024-11-20T21:52:55.203989+00:00",
  "measured_to": "2026-02-18T14:41:43.361362+00:00",
  "median": 5530.80339223808,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 5368.0415836601915,
    "p5": 4507.201258554848,
    "p50": 5530.80339223808,
    "p75": 5652.7320495865815,
    "p95": 5969.589141632598
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 229,
  "sample_status": "distribution"
}
No comparable data
One-sided evidenceBlender · 4.5.0 · classroom · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4090",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 12,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 24,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "classroom",
  "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
  "version": "4.5.0"
}

Blender scene rendering

2,785.2549627760764 samples/min

Provisional median · Limited submissionsn = 28

4.5.0 · classroom · OPTIX · Windows · 1P · 12 cores · 24 threads

2,785.25 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
2,286.39 / 3,002.85
Measurement dates
2025-07-23 – 2026-02-10
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 28

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2785.2549627760764,
    "observed_max": 3002.848212274733,
    "observed_min": 2286.3930392560655,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 28,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 12,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 24,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "classroom",
    "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
    "version": "4.5.0"
  },
  "condition_id": "c8e7958f12887937d8e4",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "e6bc714c-1d16-4d18-b62b-aedec000330c",
    "cde9a1c7-e032-42f8-9526-f1dca6f2b2fc",
    "b444b238-be42-4fba-9f44-574611629d2e"
  ],
  "measured_from": "2025-07-23T08:30:15.762186+00:00",
  "measured_to": "2026-02-10T16:45:53.675255+00:00",
  "median": 2785.2549627760764,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 28,
  "sample_status": "provisional"
}
No comparable data
One-sided evidenceBlender · 4.5.0 · monster + junkshop + classroom · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4090",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 12,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 24,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "monster + junkshop + classroom",
  "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
  "version": "4.5.0"
}

Blender complete benchmark

11,043.433364380238 samples/min

Provisional median · Limited submissionsn = 28

4.5.0 · monster + junkshop + classroom · OPTIX · Windows · 1P · 12 cores · 24 threads

11,043.43 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
9,060.03 / 11,590.42
Measurement dates
2025-07-23 – 2026-02-10
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 28

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 11043.433364380238,
    "observed_max": 11590.420519338546,
    "observed_min": 9060.029961397559,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 28,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 12,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 24,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster + junkshop + classroom",
    "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
    "version": "4.5.0"
  },
  "condition_id": "250935bb03b6fa5c7632",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "e6bc714c-1d16-4d18-b62b-aedec000330c",
    "cde9a1c7-e032-42f8-9526-f1dca6f2b2fc",
    "b444b238-be42-4fba-9f44-574611629d2e"
  ],
  "measured_from": "2025-07-23T08:30:15.762186+00:00",
  "measured_to": "2026-02-10T16:45:53.675255+00:00",
  "median": 11043.433364380238,
  "parameter_id": "benchmark.blender.total_samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 28,
  "sample_status": "provisional"
}
No comparable data
One-sided evidenceBlender · 4.5.0 · junkshop · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4090",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 12,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 24,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "junkshop",
  "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
  "version": "4.5.0"
}

Blender scene rendering

2,752.755493681165 samples/min

Provisional median · Limited submissionsn = 28

4.5.0 · junkshop · OPTIX · Windows · 1P · 12 cores · 24 threads

2,752.76 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
2,195.45 / 2,885.21
Measurement dates
2025-07-23 – 2026-02-10
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 28

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2752.755493681165,
    "observed_max": 2885.211837653116,
    "observed_min": 2195.4543545533384,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 28,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 12,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 24,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "junkshop",
    "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
    "version": "4.5.0"
  },
  "condition_id": "65b89f2bb2a454db4b60",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "e6bc714c-1d16-4d18-b62b-aedec000330c",
    "cde9a1c7-e032-42f8-9526-f1dca6f2b2fc",
    "b444b238-be42-4fba-9f44-574611629d2e"
  ],
  "measured_from": "2025-07-23T08:29:37.669594+00:00",
  "measured_to": "2026-02-10T16:45:14.019986+00:00",
  "median": 2752.755493681165,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 28,
  "sample_status": "provisional"
}
No comparable data
One-sided evidenceBlender · 4.5.0 · monster · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4090",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 12,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 24,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "monster",
  "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
  "version": "4.5.0"
}

Blender scene rendering

5,510.27741577375 samples/min

Provisional median · Limited submissionsn = 28

4.5.0 · monster · OPTIX · Windows · 1P · 12 cores · 24 threads

5,510.28 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
4,578.18 / 5,795.07
Measurement dates
2025-07-23 – 2026-02-10
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 28

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 5510.27741577375,
    "observed_max": 5795.071888215647,
    "observed_min": 4578.182567588154,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 28,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4090",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 12,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 24,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster",
    "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
    "version": "4.5.0"
  },
  "condition_id": "3d6631848441e78b4157",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "e6bc714c-1d16-4d18-b62b-aedec000330c",
    "cde9a1c7-e032-42f8-9526-f1dca6f2b2fc",
    "b444b238-be42-4fba-9f44-574611629d2e"
  ],
  "measured_from": "2025-07-23T08:28:46.807433+00:00",
  "measured_to": "2026-02-10T16:44:24.925339+00:00",
  "median": 5510.27741577375,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4090",
  "run_count": 28,
  "sample_status": "provisional"
}
No comparable data
One-sided evidenceBlender · 4.5.0 · classroom · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 8,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 16,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "classroom",
  "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
  "version": "4.5.0"
}
No comparable data

Blender scene rendering

2,132.5493315221565 samples/min

Median and quartilesn = 33

4.5.0 · classroom · OPTIX · Windows · 1P · 8 cores · 16 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
2,005.24
P50 · Median
2,132.55
P75
2,164.23

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
1,748.54 / 2,248.25
Measurement dates
2025-07-21 – 2026-02-22
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 33

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2132.5493315221565,
    "observed_max": 2248.2504643313177,
    "observed_min": 1748.5403968482017,
    "percentiles": {
      "p25": 2005.2366347147154,
      "p50": 2132.5493315221565,
      "p75": 2164.2279355322407
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 33,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 8,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 16,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "classroom",
    "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
    "version": "4.5.0"
  },
  "condition_id": "c81869d34bd95151cb40",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "efd82d09-8cd6-41c6-82e2-cfe3c5009169",
    "cffa79ca-6c63-4fc5-8a32-d2f4d5f4cfec",
    "72a78e1c-aed4-46be-9fdd-f9c06799c911"
  ],
  "measured_from": "2025-07-21T00:33:42.197110+00:00",
  "measured_to": "2026-02-22T23:33:34.662036+00:00",
  "median": 2132.5493315221565,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 2005.2366347147154,
    "p50": 2132.5493315221565,
    "p75": 2164.2279355322407
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 33,
  "sample_status": "quartiles"
}
One-sided evidenceBlender · 4.5.0 · monster + junkshop + classroom · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 8,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 16,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "monster + junkshop + classroom",
  "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
  "version": "4.5.0"
}
No comparable data

Blender complete benchmark

8,376.478252675453 samples/min

Median and quartilesn = 33

4.5.0 · monster + junkshop + classroom · OPTIX · Windows · 1P · 8 cores · 16 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
8,029.24
P50 · Median
8,376.48
P75
8,713.1

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
6,888.44 / 9,011.01
Measurement dates
2025-07-21 – 2026-02-22
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 33

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 8376.478252675453,
    "observed_max": 9011.007612961344,
    "observed_min": 6888.435981917581,
    "percentiles": {
      "p25": 8029.240981691414,
      "p50": 8376.478252675453,
      "p75": 8713.100514970576
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 33,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 8,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 16,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster + junkshop + classroom",
    "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
    "version": "4.5.0"
  },
  "condition_id": "fcbfaa5ebb2e05530517",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "efd82d09-8cd6-41c6-82e2-cfe3c5009169",
    "cffa79ca-6c63-4fc5-8a32-d2f4d5f4cfec",
    "72a78e1c-aed4-46be-9fdd-f9c06799c911"
  ],
  "measured_from": "2025-07-21T00:33:42.197110+00:00",
  "measured_to": "2026-02-22T23:33:34.662036+00:00",
  "median": 8376.478252675453,
  "parameter_id": "benchmark.blender.total_samples_per_minute",
  "percentiles": {
    "p25": 8029.240981691414,
    "p50": 8376.478252675453,
    "p75": 8713.100514970576
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 33,
  "sample_status": "quartiles"
}
One-sided evidenceBlender · 4.5.0 · junkshop · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 8,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 16,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "junkshop",
  "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
  "version": "4.5.0"
}
No comparable data

Blender scene rendering

2,110.2099222988895 samples/min

Median and quartilesn = 33

4.5.0 · junkshop · OPTIX · Windows · 1P · 8 cores · 16 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
2,028.56
P50 · Median
2,110.21
P75
2,194.32

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
1,732.98 / 2,288.97
Measurement dates
2025-07-21 – 2026-02-22
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 33

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2110.2099222988895,
    "observed_max": 2288.9657458162105,
    "observed_min": 1732.9793854224924,
    "percentiles": {
      "p25": 2028.5588764805223,
      "p50": 2110.2099222988895,
      "p75": 2194.319564942234
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 33,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 8,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 16,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "junkshop",
    "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
    "version": "4.5.0"
  },
  "condition_id": "182053b0dff1224bbe47",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "efd82d09-8cd6-41c6-82e2-cfe3c5009169",
    "cffa79ca-6c63-4fc5-8a32-d2f4d5f4cfec",
    "72a78e1c-aed4-46be-9fdd-f9c06799c911"
  ],
  "measured_from": "2025-07-21T00:33:04.642841+00:00",
  "measured_to": "2026-02-22T23:32:56.382697+00:00",
  "median": 2110.2099222988895,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 2028.5588764805223,
    "p50": 2110.2099222988895,
    "p75": 2194.319564942234
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 33,
  "sample_status": "quartiles"
}
One-sided evidenceBlender · 4.5.0 · monster · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 8,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 16,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "monster",
  "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
  "version": "4.5.0"
}
No comparable data

Blender scene rendering

4,148.695823941922 samples/min

Median and quartilesn = 33

4.5.0 · monster · OPTIX · Windows · 1P · 8 cores · 16 threads

Box: middle 50% (P25–P75)Vertical line: median (P50)

P25
3,981.94
P50 · Median
4,148.7
P75
4,329.84

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
3,406.92 / 4,482.41
Measurement dates
2025-07-21 – 2026-02-22
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 33

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 4148.695823941922,
    "observed_max": 4482.413043374688,
    "observed_min": 3406.916199646887,
    "percentiles": {
      "p25": 3981.942954310816,
      "p50": 4148.695823941922,
      "p75": 4329.83877797908
    },
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 33,
    "sample_status": "quartiles",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 8,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 16,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster",
    "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
    "version": "4.5.0"
  },
  "condition_id": "feb2e8228abdccfa7fde",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "efd82d09-8cd6-41c6-82e2-cfe3c5009169",
    "cffa79ca-6c63-4fc5-8a32-d2f4d5f4cfec",
    "72a78e1c-aed4-46be-9fdd-f9c06799c911"
  ],
  "measured_from": "2025-07-21T00:32:14.338142+00:00",
  "measured_to": "2026-02-22T23:32:09.908090+00:00",
  "median": 4148.695823941922,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "percentiles": {
    "p25": 3981.942954310816,
    "p50": 4148.695823941922,
    "p75": 4329.83877797908
  },
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 33,
  "sample_status": "quartiles"
}
One-sided evidenceBlender · 4.4.0 · classroom · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 24,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 32,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "classroom",
  "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
  "version": "4.4.0"
}
No comparable data

Blender scene rendering

2,127.4640764959763 samples/min

Provisional median · Limited submissionsn = 27

4.4.0 · classroom · OPTIX · Windows · 1P · 24 cores · 32 threads

2,127.46 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
1,796.13 / 2,327.9
Measurement dates
2025-03-21 – 2026-02-09
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 27

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2127.4640764959763,
    "observed_max": 2327.898417101844,
    "observed_min": 1796.1316406199348,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 27,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 24,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "classroom",
    "scene_checksum": "936f0a528f03eba291c67ea87743a0ebde58938fb87471b262721b89b46b875d",
    "version": "4.4.0"
  },
  "condition_id": "a02e38b00424a06bcbc9",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "971cb196-1c29-47f5-84c2-d5caa2c82287",
    "f681dc38-76b7-4eca-a9bf-29ea1c107152",
    "7a0e6485-db3c-4116-92f9-549dc8804589"
  ],
  "measured_from": "2025-03-21T12:53:39.792608+00:00",
  "measured_to": "2026-02-09T19:19:27.496949+00:00",
  "median": 2127.4640764959763,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 27,
  "sample_status": "provisional"
}
One-sided evidenceBlender · 4.4.0 · monster + junkshop + classroom · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 24,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 32,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "monster + junkshop + classroom",
  "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
  "version": "4.4.0"
}
No comparable data

Blender complete benchmark

8,479.08050308784 samples/min

Provisional median · Limited submissionsn = 27

4.4.0 · monster + junkshop + classroom · OPTIX · Windows · 1P · 24 cores · 32 threads

8,479.08 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
7,717.91 / 9,274.56
Measurement dates
2025-03-21 – 2026-02-09
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 27

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 8479.08050308784,
    "observed_max": 9274.56030452713,
    "observed_min": 7717.906658562177,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 27,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 24,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster + junkshop + classroom",
    "scene_checksum": "c3453da9769193d968fb1cc675fd7f92a3424abe9ac730218f2e00b953389356",
    "version": "4.4.0"
  },
  "condition_id": "0f247eddb5bf79461a3e",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "971cb196-1c29-47f5-84c2-d5caa2c82287",
    "f681dc38-76b7-4eca-a9bf-29ea1c107152",
    "7a0e6485-db3c-4116-92f9-549dc8804589"
  ],
  "measured_from": "2025-03-21T12:53:39.792608+00:00",
  "measured_to": "2026-02-09T19:19:27.496949+00:00",
  "median": 8479.08050308784,
  "parameter_id": "benchmark.blender.total_samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 27,
  "sample_status": "provisional"
}
One-sided evidenceBlender · 4.4.0 · junkshop · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 24,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 32,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "junkshop",
  "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
  "version": "4.4.0"
}
No comparable data

Blender scene rendering

2,109.9822082740393 samples/min

Provisional median · Limited submissionsn = 27

4.4.0 · junkshop · OPTIX · Windows · 1P · 24 cores · 32 threads

2,109.98 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
1,899.03 / 2,336.48
Measurement dates
2025-03-21 – 2026-02-09
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 27

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 2109.9822082740393,
    "observed_max": 2336.4843393030187,
    "observed_min": 1899.031432212452,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 27,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 24,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "junkshop",
    "scene_checksum": "f5515a21a1337b908212d8d76733530df83014464a24c585ab7b96000da0cdce",
    "version": "4.4.0"
  },
  "condition_id": "1c1f63c002c4a6b0707e",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "971cb196-1c29-47f5-84c2-d5caa2c82287",
    "f681dc38-76b7-4eca-a9bf-29ea1c107152",
    "7a0e6485-db3c-4116-92f9-549dc8804589"
  ],
  "measured_from": "2025-03-21T12:53:01.569809+00:00",
  "measured_to": "2026-02-09T19:18:51.526717+00:00",
  "median": 2109.9822082740393,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 27,
  "sample_status": "provisional"
}
One-sided evidenceBlender · 4.4.0 · monster · OPTIX
Full test conditions
{
  "benchmark": "Blender",
  "environment": {
    "backend": "OPTIX",
    "benchmark_script": "3.1.1",
    "device_name": "NVIDIA GeForce RTX 4080 SUPER",
    "dist_name": "",
    "dist_version": "",
    "driver": null,
    "num_cpu_cores": 24,
    "num_cpu_sockets": 1,
    "num_cpu_threads": 32,
    "power_limit": null,
    "ram_bytes": null,
    "settings_status": "unknown",
    "system": "Windows"
  },
  "scene": "monster",
  "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
  "version": "4.4.0"
}
No comparable data

Blender scene rendering

4,234.2224035303825 samples/min

Provisional median · Limited submissionsn = 27

4.4.0 · monster · OPTIX · Windows · 1P · 24 cores · 32 threads

4,234.22 Provisional median

Counts represent submissions; the number of independent systems is unknown. Stock or overclocked status, RAM and power settings are also unknown.

Measurement scope and interpretation

Sample thresholds are an initial display policy, not a guarantee of statistical confidence. P95 is not a theoretical limit. OS submission shares do not represent user market share.

Observed minimum / maximum
3,894.78 / 4,610.18
Measurement dates
2025-03-21 – 2026-02-09
Duplicate submissions removed
0
Quantile calculation
linear interpolation · (n−1) × p

Run count: 27

View source ↗

Result and source conditions
{
  "analysis": {
    "duplicates_removed": 0,
    "independent_system_count": null,
    "median": 4234.2224035303825,
    "observed_max": 4610.177548122267,
    "observed_min": 3894.7762857482107,
    "policy": "submitted-runs-v1",
    "quantile_method": "linear interpolation at (n-1)*p",
    "sample_count": 27,
    "sample_status": "provisional",
    "settings_status": "unknown"
  },
  "comparison_readiness": "observational-only",
  "condition": {
    "benchmark": "Blender",
    "environment": {
      "backend": "OPTIX",
      "benchmark_script": "3.1.1",
      "device_name": "NVIDIA GeForce RTX 4080 SUPER",
      "dist_name": "",
      "dist_version": "",
      "driver": null,
      "num_cpu_cores": 24,
      "num_cpu_sockets": 1,
      "num_cpu_threads": 32,
      "power_limit": null,
      "ram_bytes": null,
      "settings_status": "unknown",
      "system": "Windows"
    },
    "scene": "monster",
    "scene_checksum": "8ff812a02f720433de1403dab447be9541eecca71cc919224a7790d017c1b2ce",
    "version": "4.4.0"
  },
  "condition_id": "d7266847959fe131a5c4",
  "document_id": "blender-open-data-3b13b06e2e84b715",
  "example_record_ids": [
    "971cb196-1c29-47f5-84c2-d5caa2c82287",
    "f681dc38-76b7-4eca-a9bf-29ea1c107152",
    "7a0e6485-db3c-4116-92f9-549dc8804589"
  ],
  "measured_from": "2025-03-21T12:52:18.918470+00:00",
  "measured_to": "2026-02-09T19:18:09.616594+00:00",
  "median": 4234.2224035303825,
  "parameter_id": "benchmark.blender.samples_per_minute",
  "population": "public submitted runs; not independent systems",
  "product_id": "geforce-rtx-4080-super",
  "run_count": 27,
  "sample_status": "provisional"
}

DIEFOLIO / PRICE CONTEXT

Price & shopping

A dollar reference. Your currency.

GeForce RTX 4090

Launch starting price

USD 1,599.00

US dollar reference
Price sourceNVIDIA ↗

Price reference date: 2022-09-20
Source checked: 2026-10-11

International shop · check delivery country

AmazonNewegg

GeForce RTX 4080 SUPER

Launch starting price

USD 999.00

US dollar reference
Price sourceNVIDIA ↗

Price reference date: 2024-01-08
Source checked: 2026-10-11

International shop · check delivery country

AmazonNewegg

Conversion applies to the US reference price. It excludes local retail prices, taxes, shipping and board-model differences.

Check current selling prices at the linked shops. Verify the exact model, stock and delivery terms.

Key specifications

Parameter and conditionsGeForce RTX 4090GeForce RTX 4080 SUPER
Dedicated VRAM
24 GB
Source and conditions

View source ↗

{
  "document_id": "nvidia-geforce-0d2a5639216392f8",
  "parameter_id": "gpu.vram",
  "product_id": "geforce-rtx-4090",
  "qualifiers": {},
  "raw_label": "VRAM",
  "raw_value": "24",
  "state": "known",
  "value": 24
}
16 GB
Source and conditions

View source ↗

{
  "document_id": "nvidia-geforce-0d2a5639216392f8",
  "parameter_id": "gpu.vram",
  "product_id": "geforce-rtx-4080-super",
  "qualifiers": {},
  "raw_label": "VRAM",
  "raw_value": "16",
  "state": "known",
  "value": 16
}
CUDA cores
16,384
Source and conditions

View source ↗

{
  "document_id": "nvidia-geforce-0d2a5639216392f8",
  "parameter_id": "gpu.cuda_cores",
  "product_id": "geforce-rtx-4090",
  "qualifiers": {},
  "raw_label": "NVIDIA CUDA Cores",
  "raw_value": "16384",
  "state": "known",
  "value": 16384
}
10,240
Source and conditions

View source ↗

{
  "document_id": "nvidia-geforce-0d2a5639216392f8",
  "parameter_id": "gpu.cuda_cores",
  "product_id": "geforce-rtx-4080-super",
  "qualifiers": {},
  "raw_label": "NVIDIA CUDA Cores",
  "raw_value": "10240",
  "state": "known",
  "value": 10240
}

Core counts and clock speeds are not workload performance rankings. TDP, base power and maximum turbo power are different metrics, not measured power consumption.

Product context and sources

GeForce RTX 4090

24GB of VRAM does not guarantee compatibility with every AI model. Check the model, quantization, context length and runtime; CUDA core counts across generations are not measured performance ratios.

Full specifications and sources →

GeForce RTX 4080 SUPER

RTX 4080 and RTX 4080 SUPER are separate products. Equal memory capacity does not imply equal gaming or rendering performance; check board, driver and test conditions.

Full specifications and sources →