# GPT-4o (2024-11-20)High > Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-4o-2024-11-20-high. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-4o-2024-11-20-high. OpenAI Canonical URL: https://benchize.com/models/gpt-4o-2024-11-20-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 | | | --- | --- | --- | --- | --- | --- | --- | --- | | [TaxEval v2 / correctness](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Acorrectness.md) | 64.84% | SE ±1.37 pp | 9 / 40 | $0.00581 | 5.86source 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` \| 64.841 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005806 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.855 \| 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 145 stderr 1.365 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-2024-11-20 Source version 2 Observed 2026-10-22T02:10:14.414Z Evidence SHA-256 `8b354a6ae848f5bb25a2e8b061b5f576d5b9e0c11b941dc1e6bed078e6529cd6` Source locator `/tasks/correctness/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MGSM / mgsm bn](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_bn.md) | 90.4% | SE ±1.86 pp | 1 / 8 | $0.0048 | 5.41source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.4 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004795 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.405 \| 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 75 stderr 1.863 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_bn/openai~1gpt-4o-2024-11-20` | | | | | | | | | [GPQA Diamond / diamond zero shot cot](https://benchize.com/benchmarks/vals-ai%3Agpqa%3Adiamond_zero_shot_cot.md) | 53.54% | SE ±3.55 pp | 34 / 40 | $0.0071 | 14.13source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 53.535 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.007103 \| USD \| per_test \| Lower is better \| \| `latency` \| 14.131 \| 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: ±3.55 pp sourcePopulation 138 stderr 3.55 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) Source Vals AI Original model label openai/gpt-4o-2024-11-20 Source version 1 Observed 2026-10-22T02:10:20.661Z Evidence SHA-256 `951eb5224097733a9d09d06c14908ae2980e2e640e539f2c284877c5092d7077` Source locator `/tasks/diamond_zero_shot_cot/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MGSM / mgsm te](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_te.md) | 87.2% | SE ±2.11 pp | 3 / 8 | $0.00538 | 4.12source 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` \| 0.005378 \| USD \| per_test \| Lower is better \| \| `latency` \| 4.12 \| 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_te/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MMLU Pro / biology](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Abiology.md) | 84.1% | SE ±1.47 pp | 36 / 40 | $0.00727 | 8.08source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.1 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.007273 \| USD \| per_test \| Lower is better \| \| `latency` \| 8.08 \| 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: ±1.47 pp sourcePopulation 138 stderr 1.468 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/biology/openai~1gpt-4o-2024-11-20` | | | | | | | | | [CorpFin v2 / exact pages](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Aexact_pages.md) | 55.25% | SE ±1.7 pp | 36 / 39 | — | 2.22source 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` \| 55.245 \| percent \| reported \| Higher is better \| \| `latency` \| 2.215 \| 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: ±1.7 pp sourcePopulation 134 stderr 1.698 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-2024-11-20 Source version 2 Observed 2026-10-22T02:10:13.429Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/exact_pages/openai~1gpt-4o-2024-11-20` | | | | | | | | | [LegalBench / interpretation tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Ainterpretation_tasks.md) | 77.91% | SE ±0.21 pp | 31 / 44 | — | 0.33source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 77.91 \| percent \| reported \| Higher is better \| \| `latency` \| 0.325 \| 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: ±0.21 pp sourcePopulation 151 stderr 0.209 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:08.909Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/interpretation_tasks/openai~1gpt-4o-2024-11-20` | | | | | | | | | [LegalBench / rhetoric tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Arhetoric_tasks.md) | 80.95% | SE ±0.82 pp | 18 / 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` \| 80.954 \| 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: ±0.82 pp sourcePopulation 151 stderr 0.817 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:08.909Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/rhetoric_tasks/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MMLU Pro / law](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Alaw.md) | 48.68% | SE ±1.48 pp | 39 / 40 | $0.0086 | 13.02source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.683 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.008599 \| USD \| per_test \| Lower is better \| \| `latency` \| 13.023 \| 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 1.481 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/law/openai~1gpt-4o-2024-11-20` | | | | | | | | | [LegalBench / conclusion tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Aconclusion_tasks.md) | 87.21% | SE ±0.82 pp | 31 / 44 | — | 0.33source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.208 \| percent \| reported \| Higher is better \| \| `latency` \| 0.328 \| 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: ±0.82 pp sourcePopulation 151 stderr 0.818 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:08.909Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/conclusion_tasks/openai~1gpt-4o-2024-11-20` | | | | | | | | | [TaxEval v2 / overall](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Aoverall.md) | 74.53% | SE ±0.86 pp | 16 / 40 | $0.00581 | 5.86source 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` \| 74.53 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005806 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.855 \| 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: ±0.86 pp sourcePopulation 145 stderr 0.859 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-2024-11-20 Source version 2 Observed 2026-10-22T02:10:14.414Z Evidence SHA-256 `8b354a6ae848f5bb25a2e8b061b5f576d5b9e0c11b941dc1e6bed078e6529cd6` Source locator `/tasks/overall/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MGSM / mgsm en](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_en.md) | 96% | SE ±1.24 pp | 6 / 8 | $0.00357 | 3.56source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.003573 \| USD \| per_test \| Lower is better \| \| `latency` \| 3.558 \| 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: ±1.24 pp sourcePopulation 75 stderr 1.239 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_en/openai~1gpt-4o-2024-11-20` | | | | | | | | | [AIME / overall](https://benchize.com/benchmarks/vals-ai%3Aaime%3Aoverall.md) | 11.88% | SE ±0.96 pp | 13 / 14 | $0.01 | 15.78source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_aime.C3_jItdR.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 11.875 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.011954 \| USD \| per_test \| Lower is better \| \| `latency` \| 15.776 \| 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: ±0.96 pp sourcePopulation 96 stderr 0.955 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:17.157Z Evidence SHA-256 `7d016210b39d24351bbb5d12be09a973decac461bb2486eb1f23724fed2b7e6c` Source locator `/tasks/overall/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MMMU Pro / overall](https://benchize.com/benchmarks/vals-ai%3Ammmu%3Aoverall.md) | 62.16% | SE ±1.17 pp | 27 / 28 | $0.00682 | 45.87source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmmu.BBln8x5x.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 62.161 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006822 \| USD \| per_test \| Lower is better \| \| `latency` \| 45.873 \| 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: ±1.17 pp sourcePopulation 93 stderr 1.166 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:21.664Z Evidence SHA-256 `29395186eddd2c70601228c584a14b3c1d8f9dba4b68256561b46b0dd03c635a` Source locator `/tasks/overall/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MMLU Pro / math](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Amath.md) | 73.87% | SE ±1.26 pp | 38 / 40 | $0.00955 | 10.95source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 73.871 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.009548 \| USD \| per_test \| Lower is better \| \| `latency` \| 10.95 \| 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: ±1.26 pp sourcePopulation 138 stderr 1.263 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/math/openai~1gpt-4o-2024-11-20` | | | | | | | | | [LegalBench / issue tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Aissue_tasks.md) | 87.57% | SE ±0.62 pp | 24 / 44 | — | 0.38source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.568 \| percent \| reported \| Higher is better \| \| `latency` \| 0.381 \| 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: ±0.62 pp sourcePopulation 151 stderr 0.615 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:08.909Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/issue_tasks/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MMLU Pro / chemistry](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Achemistry.md) | 75.27% | SE ±1.32 pp | 34 / 40 | $0.01 | 13.45source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.265 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.010192 \| USD \| per_test \| Lower is better \| \| `latency` \| 13.454 \| 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/chemistry/openai~1gpt-4o-2024-11-20` | | | | | | | | | [CorpFin v2 / shared max context](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Ashared_max_context.md) | 39.86% | SE ±1.67 pp | 37 / 39 | — | 6.25source 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` \| 39.86 \| percent \| reported \| Higher is better \| \| `latency` \| 6.248 \| 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: ±1.67 pp sourcePopulation 134 stderr 1.672 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-2024-11-20 Source version 2 Observed 2026-10-22T02:10:13.429Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/shared_max_context/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MGSM / mgsm de](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_de.md) | 92% | SE ±1.72 pp | 4 / 8 | $0.00461 | 4.52source 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` \| 0.004608 \| USD \| per_test \| Lower is better \| \| `latency` \| 4.516 \| 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_de/openai~1gpt-4o-2024-11-20` | | | | | | | | | [AIME / aime 2024](https://benchize.com/benchmarks/vals-ai%3Aaime%3Aaime_2024.md) | 14.17% | SE ±1.05 pp | 12 / 14 | $0.01 | 15.96source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_aime.C3_jItdR.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 14.167 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.011915 \| USD \| per_test \| Lower is better \| \| `latency` \| 15.959 \| 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: ±1.05 pp sourcePopulation 96 stderr 1.045 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:17.157Z Evidence SHA-256 `7d016210b39d24351bbb5d12be09a973decac461bb2486eb1f23724fed2b7e6c` Source locator `/tasks/aime_2024/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MMLU Pro / history](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Ahistory.md) | 65.62% | SE ±2.54 pp | 35 / 40 | $0.0082 | 5.58source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 65.617 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.008195 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.575 \| 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: ±2.54 pp sourcePopulation 138 stderr 2.54 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/history/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MGSM / overall](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Aoverall.md) | 90.36% | SE ±1.83 pp | 3 / 8 | $0.00432 | 3.98source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.364 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004323 \| USD \| per_test \| Lower is better \| \| `latency` \| 3.982 \| 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: ±1.83 pp sourcePopulation 75 stderr 1.826 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/overall/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MGSM / mgsm th](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_th.md) | 92.8% | SE ±1.64 pp | 2 / 8 | $0.00443 | 3.49source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.8 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004426 \| USD \| per_test \| Lower is better \| \| `latency` \| 3.485 \| 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 75 stderr 1.635 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_th/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MortgageTax / numerical extraction](https://benchize.com/benchmarks/vals-ai%3Amortgage_tax%3Anumerical_extraction.md) | 64.87% | SE ±2.63 pp | 26 / 31 | $0.00694 | 5.85source 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` \| 64.865 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006935 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.85 \| 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: ±2.63 pp sourcePopulation 98 stderr 2.634 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:13.924Z Evidence SHA-256 `e5c844561f97d119d66d70269e726ecfb68be79eae39acf14ead3e95422e648c` Source locator `/tasks/numerical_extraction/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MGSM / mgsm zh](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_zh.md) | 91.6% | SE ±1.75 pp | 2 / 8 | $0.0039 | 3.52source 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` \| 0.003896 \| USD \| per_test \| Lower is better \| \| `latency` \| 3.518 \| 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_zh/openai~1gpt-4o-2024-11-20` | | | | | | | | | [CorpFin v2 / max fitting context](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Amax_fitting_context.md) | 42.66% | SE ±1.69 pp | 36 / 39 | — | 10.92source 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` \| 42.657 \| percent \| reported \| Higher is better \| \| `latency` \| 10.92 \| 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: ±1.69 pp sourcePopulation 134 stderr 1.688 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-2024-11-20 Source version 2 Observed 2026-10-22T02:10:13.429Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/max_fitting_context/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MMLU Pro / health](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Ahealth.md) | 75.31% | SE ±1.53 pp | 34 / 40 | $0.00561 | 6.08source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.306 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005606 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.075 \| 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: ±1.53 pp sourcePopulation 138 stderr 1.525 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/health/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MMLU Pro / other](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aother.md) | 77.27% | SE ±1.4 pp | 34 / 40 | $0.00434 | 5.53source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 77.273 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004344 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.526 \| 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 1.397 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/other/openai~1gpt-4o-2024-11-20` | | | | | | | | | [TaxEval v2 / stepwise reasoning](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Astepwise_reasoning.md) | 84.22% | SE ±1.04 pp | 24 / 40 | $0.00581 | 5.86source 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` \| 84.219 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005806 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.855 \| 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 145 stderr 1.042 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-2024-11-20 Source version 2 Observed 2026-10-22T02:10:14.414Z Evidence SHA-256 `8b354a6ae848f5bb25a2e8b061b5f576d5b9e0c11b941dc1e6bed078e6529cd6` Source locator `/tasks/stepwise_reasoning/openai~1gpt-4o-2024-11-20` | | | | | | | | | [AIME 2025](https://benchize.com/benchmarks/aime-2025.md) | 9.58% | SE ±1.6 pp | 14 / 14 | $0.01 | 15.59source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_aime.C3_jItdR.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 9.583 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.011992 \| USD \| per_test \| Lower is better \| \| `latency` \| 15.593 \| 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: ±1.6 pp sourcePopulation 96 stderr 1.598 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:17.157Z Evidence SHA-256 `7d016210b39d24351bbb5d12be09a973decac461bb2486eb1f23724fed2b7e6c` Source locator `/tasks/aime_2025/openai~1gpt-4o-2024-11-20` | | | | | | | | | [LegalBench / overall](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Aoverall.md) | 82.21% | SE ±0.46 pp | 27 / 44 | — | 0.45source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.214 \| percent \| reported \| Higher is better \| \| `latency` \| 0.452 \| 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: ±0.46 pp sourcePopulation 151 stderr 0.463 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:08.909Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/overall/openai~1gpt-4o-2024-11-20` | | | | | | | | | [LiveCodeBench / hard](https://benchize.com/benchmarks/vals-ai%3Alcb%3Ahard.md) | 5.14% | SE ±1.18 pp | 41 / 43 | $0.00524 | 5.66source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 5.143 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005244 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.656 \| 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: ±1.18 pp sourcePopulation 143 stderr 1.181 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label openai/gpt-4o-2024-11-20 Source version 1 Observed 2026-10-22T02:10:28.824Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/hard/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MGSM / mgsm ru](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_ru.md) | 93.6% | SE ±1.55 pp | 5 / 8 | $0.00418 | 4.12source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 93.6 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004181 \| USD \| per_test \| Lower is better \| \| `latency` \| 4.115 \| 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: ±1.55 pp sourcePopulation 75 stderr 1.548 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_ru/openai~1gpt-4o-2024-11-20` | | | | | | | | | [GPQA Diamond / diamond few shot cot](https://benchize.com/benchmarks/vals-ai%3Agpqa%3Adiamond_few_shot_cot.md) | 54.04% | SE ±3.54 pp | 34 / 40 | $0.01 | 15.72source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 54.04 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.011827 \| USD \| per_test \| Lower is better \| \| `latency` \| 15.717 \| 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: ±3.54 pp sourcePopulation 138 stderr 3.542 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) Source Vals AI Original model label openai/gpt-4o-2024-11-20 Source version 1 Observed 2026-10-22T02:10:20.661Z Evidence SHA-256 `951eb5224097733a9d09d06c14908ae2980e2e640e539f2c284877c5092d7077` Source locator `/tasks/diamond_few_shot_cot/openai~1gpt-4o-2024-11-20` | | | | | | | | | [LegalBench / rule tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Arule_tasks.md) | 77.43% | SE ±1.9 pp | 29 / 44 | — | 0.88source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 77.429 \| percent \| reported \| Higher is better \| \| `latency` \| 0.882 \| 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: ±1.9 pp sourcePopulation 151 stderr 1.9 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:08.909Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/rule_tasks/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MMLU Pro / physics](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aphysics.md) | 74.21% | SE ±1.27 pp | 36 / 40 | $0.00821 | 12.1source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 74.211 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.008214 \| USD \| per_test \| Lower is better \| \| `latency` \| 12.097 \| 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: ±1.27 pp sourcePopulation 138 stderr 1.271 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/physics/openai~1gpt-4o-2024-11-20` | | | | | | | | | [CaseLaw v2 / overall](https://benchize.com/benchmarks/vals-ai%3Acase_law_v2%3Aoverall.md) | 59.7% | SE ±0.43 pp | 9 / 17 | $0.07 | 40.87source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_case_law_v2.DLKA06_7.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.7 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.066774 \| USD \| per_test \| Lower is better \| \| `latency` \| 40.867 \| 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: ±0.43 pp sourcePopulation 54 stderr 0.429 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_case_law_v2.DLKA06_7.json) Source Vals AI Original model label openai/gpt-4o-2024-11-20 Source version 2 Observed 2026-10-22T02:10:09.895Z Evidence SHA-256 `293f388f7e0fe563287d4cd19beaa7ef9821b32795dace34bd0197ed47a592d4` Source locator `/tasks/overall/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MMLU Pro / engineering](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aengineering.md) | 52.63% | SE ±1.61 pp | 38 / 40 | $0.01 | 15.56source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.632 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.010722 \| USD \| per_test \| Lower is better \| \| `latency` \| 15.557 \| 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: ±1.61 pp sourcePopulation 138 stderr 1.606 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/engineering/openai~1gpt-4o-2024-11-20` | | | | | | | | | [LiveCodeBench / easy](https://benchize.com/benchmarks/vals-ai%3Alcb%3Aeasy.md) | 86.03% | SE ±1.93 pp | 41 / 43 | $0.00269 | 2.74source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.025 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.00269 \| USD \| per_test \| Lower is better \| \| `latency` \| 2.741 \| 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 143 stderr 1.932 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label openai/gpt-4o-2024-11-20 Source version 1 Observed 2026-10-22T02:10:28.824Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/easy/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MMLU Pro / psychology](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Apsychology.md) | 82.96% | SE ±1.35 pp | 29 / 40 | $0.00545 | 6.71source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.957 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005454 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.706 \| 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: ±1.35 pp sourcePopulation 138 stderr 1.35 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/psychology/openai~1gpt-4o-2024-11-20` | | | | | | | | | [LiveCodeBench / overall](https://benchize.com/benchmarks/vals-ai%3Alcb%3Aoverall.md) | 43.44% | SE ±1.12 pp | 41 / 43 | $0.004 | 4.35source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 43.444 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.003999 \| USD \| per_test \| Lower is better \| \| `latency` \| 4.347 \| 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: ±1.12 pp sourcePopulation 143 stderr 1.123 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label openai/gpt-4o-2024-11-20 Source version 1 Observed 2026-10-22T02:10:28.824Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/overall/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MMLU-Pro](https://benchize.com/benchmarks/mmlu-pro.md) | 72.56% | SE ±0.44 pp | 36 / 40 | $0.00747 | 9.14source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 72.563 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.007465 \| USD \| per_test \| Lower is better \| \| `latency` \| 9.143 \| 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: ±0.44 pp sourcePopulation 138 stderr 0.441 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/overall/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MMLU Pro / business](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Abusiness.md) | 77.69% | SE ±1.53 pp | 37 / 40 | $0.00609 | 7.52source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 77.693 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006093 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.518 \| 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: ±1.53 pp sourcePopulation 138 stderr 1.533 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/business/openai~1gpt-4o-2024-11-20` | | | | | | | | | [CorpFin v2 / overall](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Aoverall.md) | 45.92% | SE ±0.97 pp | 37 / 39 | — | 6.46source 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` \| 45.921 \| percent \| reported \| Higher is better \| \| `latency` \| 6.461 \| 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: ±0.97 pp sourcePopulation 134 stderr 0.973 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-2024-11-20 Source version 2 Observed 2026-10-22T02:10:13.429Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/overall/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MortgageTax / semantic extraction](https://benchize.com/benchmarks/vals-ai%3Amortgage_tax%3Asemantic_extraction.md) | 50% | SE ±2.76 pp | 29 / 31 | $0.00735 | 6.12source 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 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.007347 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.119 \| 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 2.759 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:13.924Z Evidence SHA-256 `e5c844561f97d119d66d70269e726ecfb68be79eae39acf14ead3e95422e648c` Source locator `/tasks/semantic_extraction/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MortgageTax / overall](https://benchize.com/benchmarks/vals-ai%3Amortgage_tax%3Aoverall.md) | 57.43% | SE ±1.91 pp | 27 / 31 | $0.00714 | 5.98source 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` \| 57.432 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.007141 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.984 \| 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: ±1.91 pp sourcePopulation 98 stderr 1.907 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:13.924Z Evidence SHA-256 `e5c844561f97d119d66d70269e726ecfb68be79eae39acf14ead3e95422e648c` Source locator `/tasks/overall/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MGSM / mgsm sw](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_sw.md) | 91.6% | SE ±1.75 pp | 2 / 8 | $0.00373 | 3.16source 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` \| 0.00373 \| USD \| per_test \| Lower is better \| \| `latency` \| 3.156 \| 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_sw/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MGSM / mgsm fr](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_fr.md) | 82.4% | SE ±2.41 pp | 8 / 8 | $0.00354 | 3.75source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.4 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.00354 \| USD \| per_test \| Lower is better \| \| `latency` \| 3.747 \| 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: ±2.41 pp sourcePopulation 75 stderr 2.408 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_fr/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MGSM / mgsm ja](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_ja.md) | 86% | SE ±2.19 pp | 7 / 8 | $0.00557 | 4.52source 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 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005571 \| USD \| per_test \| Lower is better \| \| `latency` \| 4.522 \| 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: ±2.19 pp sourcePopulation 75 stderr 2.194 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_ja/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MMLU Pro / economics](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aeconomics.md) | 81.28% | SE ±1.41 pp | 35 / 40 | $0.00664 | 7.48source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 81.28 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.00664 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.483 \| 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: ±1.41 pp sourcePopulation 138 stderr 1.407 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/economics/openai~1gpt-4o-2024-11-20` | | | | | | | | | [LiveCodeBench / medium](https://benchize.com/benchmarks/vals-ai%3Alcb%3Amedium.md) | 39.16% | SE ±2.49 pp | 41 / 43 | $0.00406 | 4.64source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.164 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004063 \| USD \| per_test \| Lower is better \| \| `latency` \| 4.643 \| 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: ±2.49 pp sourcePopulation 143 stderr 2.494 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label openai/gpt-4o-2024-11-20 Source version 1 Observed 2026-10-22T02:10:28.824Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/medium/openai~1gpt-4o-2024-11-20` | | | | | | | | | [GPQA Diamond](https://benchize.com/benchmarks/gpqa-diamond.md) | 53.79% | SE ±2.51 pp | 34 / 40 | $0.00947 | 14.92source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 53.788 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.009465 \| USD \| per_test \| Lower is better \| \| `latency` \| 14.924 \| 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: ±2.51 pp sourcePopulation 138 stderr 2.507 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) Source Vals AI Original model label openai/gpt-4o-2024-11-20 Source version 1 Observed 2026-10-22T02:10:20.661Z Evidence SHA-256 `951eb5224097733a9d09d06c14908ae2980e2e640e539f2c284877c5092d7077` Source locator `/tasks/overall/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MMLU Pro / philosophy](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aphilosophy.md) | 71.14% | SE ±2.06 pp | 34 / 40 | $0.0052 | 6.38source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 71.142 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005199 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.384 \| 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: ±2.06 pp sourcePopulation 138 stderr 2.056 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/philosophy/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MGSM / mgsm es](https://benchize.com/benchmarks/vals-ai%3Amgsm%3Amgsm_es.md) | 90.4% | SE ±1.86 pp | 7 / 8 | $0.00386 | 3.66source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mgsm.CneCP-rm.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.4 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.003856 \| USD \| per_test \| Lower is better \| \| `latency` \| 3.661 \| 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 75 stderr 1.863 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:18.177Z Evidence SHA-256 `1b87f953e52c00bf4bdd90c3add26165f644eeb7a74a8382d2a0324ff0cc1040` Source locator `/tasks/mgsm_es/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MMLU Pro / computer science](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Acomputer_science.md) | 75.85% | SE ±2.26 pp | 36 / 40 | $0.00843 | 9.57source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.854 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.008429 \| USD \| per_test \| Lower is better \| \| `latency` \| 9.572 \| 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: ±2.26 pp sourcePopulation 138 stderr 2.258 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:21.194Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/computer_science/openai~1gpt-4o-2024-11-20` | | | | | | | | | [MATH-500](https://benchize.com/benchmarks/math-500.md) | 74% | SE ±3.83 pp | 4 / 5 | $0.00885 | 12.8source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_math500.BvFbu92X.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 74 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.008846 \| USD \| per_test \| Lower is better \| \| `latency` \| 12.804 \| 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: ±3.83 pp sourcePopulation 60 stderr 3.834 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-2024-11-20 Source version 1 Observed 2026-10-22T02:10:17.658Z Evidence SHA-256 `435ec4da1112362c0a6bb4afeab53bf7b0faf2000e1ddbe1a878735dca1fe35b` Source locator `/tasks/overall/openai~1gpt-4o-2024-11-20` | | | | | | | | --- Cite as: GPT-4o (2024-11-20)High — Benchize, https://benchize.com/models/gpt-4o-2024-11-20-high (retrieved 2026-10-22)