# GPT-4o (2024-08-06)High

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-4o-2024-08-06-high. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-4o-2024-08-06-high.

OpenAI

Canonical URL: https://benchize.com/models/gpt-4o-2024-08-06-high
Last updated: Thu, 22 Oct 2026 08:20:15 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

OpenAI

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Latency | Source |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [MMLU Pro / economics](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aeconomics.md) | 79.86% | SE ±1.38 pp | 37 / 40 | $0.00609 | 6.95source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.858 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006085 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.954 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.38 pp sourcePopulation 138 stderr 1.381 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/economics/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MMLU Pro / physics](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aphysics.md) | 75.37% | SE ±1.2 pp | 35 / 40 | $0.00841 | 12.7source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.366 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.008408 \| USD \| per_test \| Lower is better \| \| `latency` \| 12.704 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.2 pp sourcePopulation 138 stderr 1.196 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/physics/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MMLU Pro / math](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Amath.md) | 78.91% | SE ±1.11 pp | 35 / 40 | $0.00915 | 11.46source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 78.905 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.009151 \| USD \| per_test \| Lower is better \| \| `latency` \| 11.455 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.11 pp sourcePopulation 138 stderr 1.11 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/math/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MortgageTax / numerical extraction](https://benchize.com/benchmarks/vals-ai%3Amortgage_tax%3Anumerical_extraction.md) | 71.15% | SE ±2.5 pp | 23 / 31 | $0.00678 | 7.27source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 71.145 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006779 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.274 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.5 pp sourcePopulation 98 stderr 2.501 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:13.924Z Evidence SHA-256 `e5c844561f97d119d66d70269e726ecfb68be79eae39acf14ead3e95422e648c` Source locator `/tasks/numerical_extraction/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MGSM / mgsm th](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_th.md) | 92.4% | SE ±1.68 pp | 3 / 8 | $0.00314 | 7.9source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.4 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.003138 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.901 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.68 pp sourcePopulation 75 stderr 1.676 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_th/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MortgageTax / overall](https://benchize.com/benchmarks/vals-ai%3Amortgage_tax%3Aoverall.md) | 60.97% | SE ±1.86 pp | 25 / 31 | $0.00696 | 7.36source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 60.97 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006956 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.356 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.86 pp sourcePopulation 98 stderr 1.862 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:13.924Z Evidence SHA-256 `e5c844561f97d119d66d70269e726ecfb68be79eae39acf14ead3e95422e648c` Source locator `/tasks/overall/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MedQA / indigenous](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Aindigenous.md) | 87.65% | SE ±1.44 pp | 6 / 12 | $0.00281 | 3.21source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.65 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002805 \| USD \| per_test \| Lower is better \| \| `latency` \| 3.208 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.44 pp sourcePopulation 95 stderr 1.442 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:15.908Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/indigenous/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MGSM / mgsm es](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_es.md) | 89.6% | SE ±1.93 pp | 8 / 8 | $0.00297 | 6.72source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.6 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002973 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.717 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.93 pp sourcePopulation 75 stderr 1.931 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_es/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [AIME 2025](https://benchize.com/benchmarks/aime-2025.md) | 15% | SE ±1.26 pp | 11 / 14 | $0.01 | 35.23source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_aime.C3_jItdR.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 15 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.010184 \| USD \| per_test \| Lower is better \| \| `latency` \| 35.226 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.26 pp sourcePopulation 96 stderr 1.26 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_aime.C3_jItdR.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:17.157Z Evidence SHA-256 `7d016210b39d24351bbb5d12be09a973decac461bb2486eb1f23724fed2b7e6c` Source locator `/tasks/aime_2025/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MMLU Pro / philosophy](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aphilosophy.md) | 67.54% | SE ±2.1 pp | 36 / 40 | $0.00538 | 5.94source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 67.535 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005383 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.941 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.1 pp sourcePopulation 138 stderr 2.096 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/philosophy/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MMLU Pro / chemistry](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Achemistry.md) | 73.32% | SE ±1.32 pp | 35 / 40 | $0.00988 | 14.51source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 73.322 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.009883 \| USD \| per_test \| Lower is better \| \| `latency` \| 14.513 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.32 pp sourcePopulation 138 stderr 1.315 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/chemistry/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MMMU Pro / overall](https://benchize.com/benchmarks/vals-ai%3Ammmu%3Aoverall.md) | 64.01% | SE ±1.15 pp | 26 / 28 | $0.00625 | 47.52source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmmu.BBln8x5x.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 64.009 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006251 \| USD \| per_test \| Lower is better \| \| `latency` \| 47.52 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.15 pp sourcePopulation 93 stderr 1.154 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmmu.BBln8x5x.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:21.664Z Evidence SHA-256 `29395186eddd2c70601228c584a14b3c1d8f9dba4b68256561b46b0dd03c635a` Source locator `/tasks/overall/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MMLU Pro / business](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Abusiness.md) | 79.09% | SE ±1.45 pp | 35 / 40 | $0.00644 | 7.89source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.087 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006438 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.893 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.45 pp sourcePopulation 138 stderr 1.448 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/business/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [TaxEval v2 / overall](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Aoverall.md) | 71.14% | SE ±0.89 pp | 30 / 40 | $0.00442 | 9.54source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 71.136 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004417 \| USD \| per_test \| Lower is better \| \| `latency` \| 9.543 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.89 pp sourcePopulation 145 stderr 0.892 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 2 Observed 2026-10-22T02:10:14.414Z Evidence SHA-256 `8b354a6ae848f5bb25a2e8b061b5f576d5b9e0c11b941dc1e6bed078e6529cd6` Source locator `/tasks/overall/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MMLU Pro / biology](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Abiology.md) | 88.15% | SE ±1.21 pp | 34 / 40 | $0.00657 | 7.18source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.145 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006568 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.182 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.21 pp sourcePopulation 138 stderr 1.207 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/biology/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [TaxEval v2 / correctness](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Acorrectness.md) | 60.83% | SE ±1.4 pp | 25 / 40 | $0.00442 | 9.54source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 60.834 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004417 \| USD \| per_test \| Lower is better \| \| `latency` \| 9.543 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.4 pp sourcePopulation 145 stderr 1.396 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 2 Observed 2026-10-22T02:10:14.414Z Evidence SHA-256 `8b354a6ae848f5bb25a2e8b061b5f576d5b9e0c11b941dc1e6bed078e6529cd6` Source locator `/tasks/correctness/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [LegalBench / conclusion tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Aconclusion_tasks.md) | 86.44% | SE ±0.77 pp | 32 / 44 | — | 0.34source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.442 \| percent \| reported \| Higher is better \| \| `latency` \| 0.343 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.77 pp sourcePopulation 151 stderr 0.773 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:08.909Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/conclusion_tasks/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MMLU Pro / history](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Ahistory.md) | 71.92% | SE ±2.3 pp | 29 / 40 | $0.00787 | 6.49source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 71.916 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.007865 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.494 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.3 pp sourcePopulation 138 stderr 2.302 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/history/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MGSM / mgsm ru](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_ru.md) | 95.6% | SE ±1.3 pp | 2 / 8 | $0.00283 | 6.15source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.6 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002825 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.146 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.3 pp sourcePopulation 75 stderr 1.297 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_ru/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [TaxEval v2 / stepwise reasoning](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Astepwise_reasoning.md) | 81.44% | SE ±1.11 pp | 30 / 40 | $0.00442 | 9.54source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 81.439 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004417 \| USD \| per_test \| Lower is better \| \| `latency` \| 9.543 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.11 pp sourcePopulation 145 stderr 1.112 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 2 Observed 2026-10-22T02:10:14.414Z Evidence SHA-256 `8b354a6ae848f5bb25a2e8b061b5f576d5b9e0c11b941dc1e6bed078e6529cd6` Source locator `/tasks/stepwise_reasoning/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MedQA / overall](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Aoverall.md) | 88.16% | SE ±0.58 pp | 6 / 12 | $0.00279 | 3.39source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.161 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002787 \| USD \| per_test \| Lower is better \| \| `latency` \| 3.392 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.58 pp sourcePopulation 95 stderr 0.578 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:15.908Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/overall/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MGSM / mgsm de](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_de.md) | 92% | SE ±1.72 pp | 4 / 8 | $0.00296 | 6.5source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002959 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.504 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.72 pp sourcePopulation 75 stderr 1.716 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_de/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MedQA / unbiased](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Aunbiased.md) | 89% | SE ±1.37 pp | 6 / 12 | $0.00273 | 3.28source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002733 \| USD \| per_test \| Lower is better \| \| `latency` \| 3.282 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.37 pp sourcePopulation 95 stderr 1.372 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:15.908Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/unbiased/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MedQA / asian](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Aasian.md) | 88.1% | SE ±1.42 pp | 6 / 12 | $0.00278 | 4.12source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.1 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002784 \| USD \| per_test \| Lower is better \| \| `latency` \| 4.116 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.42 pp sourcePopulation 95 stderr 1.42 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:15.908Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/asian/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MGSM / mgsm te](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_te.md) | 86.8% | SE ±2.14 pp | 4 / 8 | $0.00328 | 7.96source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.8 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.003276 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.961 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.14 pp sourcePopulation 75 stderr 2.141 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_te/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MMLU-Pro](https://benchize.com/benchmarks/mmlu-pro.md) | 74.13% | SE ±0.42 pp | 35 / 40 | $0.00722 | 9source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 74.13 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.007217 \| USD \| per_test \| Lower is better \| \| `latency` \| 8.998 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.42 pp sourcePopulation 138 stderr 0.42 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/overall/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MGSM / mgsm zh](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_zh.md) | 91.6% | SE ±1.75 pp | 2 / 8 | $0.00264 | 6.18source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.6 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002637 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.182 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.75 pp sourcePopulation 75 stderr 1.754 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_zh/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MMLU Pro / other](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aother.md) | 77.17% | SE ±1.38 pp | 35 / 40 | $0.00494 | 5.93source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 77.165 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004937 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.932 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.38 pp sourcePopulation 138 stderr 1.381 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/other/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MGSM / mgsm fr](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_fr.md) | 84% | SE ±2.32 pp | 6 / 8 | $0.00281 | 6.78source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002807 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.776 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.32 pp sourcePopulation 75 stderr 2.319 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_fr/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MGSM / mgsm sw](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_sw.md) | 91.6% | SE ±1.75 pp | 2 / 8 | $0.00229 | 3.29source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.6 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002293 \| USD \| per_test \| Lower is better \| \| `latency` \| 3.291 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.75 pp sourcePopulation 75 stderr 1.754 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_sw/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MMLU Pro / computer science](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Acomputer_science.md) | 78.05% | SE ±2.04 pp | 35 / 40 | $0.00792 | 10.06source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 78.049 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.007916 \| USD \| per_test \| Lower is better \| \| `latency` \| 10.061 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.04 pp sourcePopulation 138 stderr 2.044 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/computer_science/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MMLU Pro / psychology](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Apsychology.md) | 80.7% | SE ±1.4 pp | 32 / 40 | $0.00549 | 6.96source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.702 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005488 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.961 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.4 pp sourcePopulation 138 stderr 1.4 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/psychology/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MortgageTax / semantic extraction](https://benchize.com/benchmarks/vals-ai%3Amortgage_tax%3Asemantic_extraction.md) | 50.8% | SE ±2.76 pp | 28 / 31 | $0.00713 | 7.44source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50.795 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.007133 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.437 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.76 pp sourcePopulation 98 stderr 2.758 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:13.924Z Evidence SHA-256 `e5c844561f97d119d66d70269e726ecfb68be79eae39acf14ead3e95422e648c` Source locator `/tasks/semantic_extraction/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MGSM / mgsm bn](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_bn.md) | 89.6% | SE ±1.93 pp | 2 / 8 | $0.0032 | 6.82source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.6 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.003198 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.816 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.93 pp sourcePopulation 75 stderr 1.931 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_bn/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MGSM / mgsm ja](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_ja.md) | 87.2% | SE ±2.11 pp | 5 / 8 | $0.00345 | 8.87source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.2 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.003449 \| USD \| per_test \| Lower is better \| \| `latency` \| 8.874 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.11 pp sourcePopulation 75 stderr 2.113 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_ja/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MATH-500](https://benchize.com/benchmarks/math-500.md) | 75.2% | SE ±3.78 pp | 3 / 5 | $0.00564 | 12.29source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_math500.BvFbu92X.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.2 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005641 \| USD \| per_test \| Lower is better \| \| `latency` \| 12.291 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 8192 provider OpenAI reasoning Not reported Reasoning effort high Temperature 0 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.78 pp sourcePopulation 60 stderr 3.776 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_math500.BvFbu92X.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:17.658Z Evidence SHA-256 `435ec4da1112362c0a6bb4afeab53bf7b0faf2000e1ddbe1a878735dca1fe35b` Source locator `/tasks/overall/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [LegalBench / interpretation tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Ainterpretation_tasks.md) | 77.97% | SE ±0.2 pp | 30 / 44 | — | 0.37source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 77.968 \| percent \| reported \| Higher is better \| \| `latency` \| 0.367 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.2 pp sourcePopulation 151 stderr 0.199 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:08.909Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/interpretation_tasks/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MMLU Pro / law](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Alaw.md) | 56.13% | SE ±1.5 pp | 35 / 40 | $0.00696 | 8.06source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 56.131 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.00696 \| USD \| per_test \| Lower is better \| \| `latency` \| 8.064 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.5 pp sourcePopulation 138 stderr 1.496 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/law/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [LegalBench / rule tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Arule_tasks.md) | 74.72% | SE ±2.36 pp | 33 / 44 | — | 1.18source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 74.718 \| percent \| reported \| Higher is better \| \| `latency` \| 1.178 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.36 pp sourcePopulation 151 stderr 2.358 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:08.909Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/rule_tasks/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [CorpFin v2 / overall](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Aoverall.md) | 39.43% | SE ±0.95 pp | 39 / 39 | $0.15 | 0.05source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.433 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.147391 \| USD \| per_test \| Lower is better \| \| `latency` \| 0.046 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.95 pp sourcePopulation 134 stderr 0.951 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 2 Observed 2026-10-22T02:10:13.429Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/overall/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MedQA / white](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Awhite.md) | 88.5% | SE ±1.4 pp | 6 / 12 | $0.00279 | 3.23source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002794 \| USD \| per_test \| Lower is better \| \| `latency` \| 3.231 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.4 pp sourcePopulation 95 stderr 1.399 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:15.908Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/white/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MMLU Pro / health](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Ahealth.md) | 76.53% | SE ±1.48 pp | 33 / 40 | $0.00558 | 5.64source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 76.528 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005575 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.636 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.48 pp sourcePopulation 138 stderr 1.482 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/health/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MedQA / hispanic](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Ahispanic.md) | 87.9% | SE ±1.43 pp | 6 / 12 | $0.0028 | 3.37source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.9 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002799 \| USD \| per_test \| Lower is better \| \| `latency` \| 3.374 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.43 pp sourcePopulation 95 stderr 1.43 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:15.908Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/hispanic/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MGSM / mgsm en](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_en.md) | 97.2% | SE ±1.04 pp | 5 / 8 | $0.0028 | 6.88source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 97.2 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.0028 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.877 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.04 pp sourcePopulation 75 stderr 1.043 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_en/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [AIME / overall](https://benchize.com/benchmarks/vals-ai%3Aaime%3Aoverall.md) | 13.96% | SE ±0.97 pp | 11 / 14 | $0.01 | 68.37source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_aime.C3_jItdR.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 13.958 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.012158 \| USD \| per_test \| Lower is better \| \| `latency` \| 68.368 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.97 pp sourcePopulation 96 stderr 0.968 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_aime.C3_jItdR.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:17.157Z Evidence SHA-256 `7d016210b39d24351bbb5d12be09a973decac461bb2486eb1f23724fed2b7e6c` Source locator `/tasks/overall/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [LegalBench / overall](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Aoverall.md) | 80.12% | SE ±0.54 pp | 32 / 44 | — | 0.53source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.12 \| percent \| reported \| Higher is better \| \| `latency` \| 0.532 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.54 pp sourcePopulation 151 stderr 0.538 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:08.909Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/overall/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [CorpFin v2 / max fitting context](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Amax_fitting_context.md) | 36.36% | SE ±1.64 pp | 39 / 39 | $0.28 | 0.06source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 36.364 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.283471 \| USD \| per_test \| Lower is better \| \| `latency` \| 0.057 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.64 pp sourcePopulation 134 stderr 1.642 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 2 Observed 2026-10-22T02:10:13.429Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/max_fitting_context/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [LegalBench / rhetoric tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Arhetoric_tasks.md) | 80.88% | SE ±0.78 pp | 19 / 44 | — | 0.35source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.878 \| percent \| reported \| Higher is better \| \| `latency` \| 0.353 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.78 pp sourcePopulation 151 stderr 0.777 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:08.909Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/rhetoric_tasks/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [LegalBench / issue tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Aissue_tasks.md) | 80.6% | SE ±0.65 pp | 37 / 44 | — | 0.42source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.596 \| percent \| reported \| Higher is better \| \| `latency` \| 0.42 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.65 pp sourcePopulation 151 stderr 0.653 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:08.909Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/issue_tasks/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [CorpFin v2 / exact pages](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Aexact_pages.md) | 50.23% | SE ±1.71 pp | 39 / 39 | $0.00476 | 0.07source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50.233 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004761 \| USD \| per_test \| Lower is better \| \| `latency` \| 0.073 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.71 pp sourcePopulation 134 stderr 1.707 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 2 Observed 2026-10-22T02:10:13.429Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/exact_pages/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MedQA / black](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Ablack.md) | 87.81% | SE ±1.44 pp | 6 / 12 | $0.00281 | 3.14source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.813 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002807 \| USD \| per_test \| Lower is better \| \| `latency` \| 3.14 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.44 pp sourcePopulation 95 stderr 1.436 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medqa.Cco1kvog.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:15.908Z Evidence SHA-256 `d67905978d932f64698ebe9e230d9519e5bae1c9d7176dda8379dc3874b6f90f` Source locator `/tasks/black/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [AIME / aime 2024](https://benchize.com/benchmarks/vals-ai%3Aaime%3Aaime_2024.md) | 12.92% | SE ±1.47 pp | 13 / 14 | $0.01 | 101.51source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_aime.C3_jItdR.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 12.917 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.014132 \| USD \| per_test \| Lower is better \| \| `latency` \| 101.51 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.47 pp sourcePopulation 96 stderr 1.469 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_aime.C3_jItdR.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:17.157Z Evidence SHA-256 `7d016210b39d24351bbb5d12be09a973decac461bb2486eb1f23724fed2b7e6c` Source locator `/tasks/aime_2024/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MGSM / overall](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Aoverall.md) | 90.69% | SE ±1.79 pp | 2 / 8 | $0.00294 | 6.73source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.691 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002941 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.731 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.79 pp sourcePopulation 75 stderr 1.789 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/overall/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [MMLU Pro / engineering](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aengineering.md) | 55.11% | SE ±1.6 pp | 36 / 40 | $0.01 | 16.18source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 55.108 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.010385 \| USD \| per_test \| Lower is better \| \| `latency` \| 16.182 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.6 pp sourcePopulation 138 stderr 1.598 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/engineering/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |
| [CorpFin v2 / shared max context](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Ashared_max_context.md) | 31.7% | SE ±1.59 pp | 39 / 39 | $0.15 | 0.009source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 31.702 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.15394 \| USD \| per_test \| Lower is better \| \| `latency` \| 0.009 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 16384 provider OpenAI reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.59 pp sourcePopulation 134 stderr 1.589 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) Source Vals AI Original model label openai/gpt-4o-2024-08-06 Source version 2 Observed 2026-10-22T02:10:13.429Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/shared_max_context/openai~1gpt-4o-2024-08-06` |  |  |  |  |  |  |  |

---
Cite as: GPT-4o (2024-08-06)High — Benchize, https://benchize.com/models/gpt-4o-2024-08-06-high (retrieved 2026-10-22)