# GPT-5.5Extra high > Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-5-5-xhigh. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-5-5-xhigh. OpenAI Canonical URL: https://benchize.com/models/gpt-5-5-xhigh Last updated: Wed, 21 Oct 2026 18:52:20 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 | | | --- | --- | --- | --- | --- | --- | --- | --- | | [SWE Marathon](https://benchize.com/benchmarks/swe-marathon.md) | 14% | — | 5 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 14.0 \| percent \| reported \| Higher is better \| ### Configuration Reasoning effort xhigh thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GPT 5.5 (xhigh) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/4/scores/4` | | | | | | | | | [ProgramBench / strict](https://benchize.com/benchmarks/vals-ai%3Aprogrambench%3Astrict.md) | 0.5% | SE ±0.5 pp | 14 / 40 | $6.95 | 1,322.96source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0.5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.95454 \| USD \| per_test \| Lower is better \| \| `latency` \| 1322.959 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.5 pp sourcePopulation 64 stderr 0.5 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:10.137Z Evidence SHA-256 `e9bbb4378c7a058441a21d456baf9316b96c2cf5b58d371a3c7c803f5000bd8c` Source locator `/tasks/strict/openai~1gpt-5.5` | | | | | | | | | [SWE-bench / >4 hours](https://benchize.com/benchmarks/vals-ai%3Aswebench%3A%3E4%20hours.md) | 66.67% | SE ±33.33 pp | 6 / 39 | $1.51 | 479.33source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.667 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.509878 \| USD \| per_test \| Lower is better \| \| `latency` \| 479.329 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±33.33 pp sourcePopulation 88 stderr 33.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/openai~1gpt-5.5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate employment labor](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__employment_labor.md) | 76.4% | SE ±2.6 pp | 33 / 49 | $2.28 | 554.4source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 76.404 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.284177 \| USD \| per_test \| Lower is better \| \| `latency` \| 554.404 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.6 pp sourcePopulation 81 stderr 2.603 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__employment_labor/openai~1gpt-5.5` | | | | | | | | | [MMLU-Pro](https://benchize.com/benchmarks/mmlu-pro.md) | 88.14% | SE ±0.32 pp | 15 / 40 | $0.03 | 42.11source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.144 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.027891 \| USD \| per_test \| Lower is better \| \| `latency` \| 42.114 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.32 pp sourcePopulation 138 stderr 0.318 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-5.5 Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/overall/openai~1gpt-5.5` | | | | | | | | | [MMLU Pro / math](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Amath.md) | 94.75% | SE ±0.61 pp | 20 / 40 | $0.02 | 33.03source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 94.745 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.017893 \| USD \| per_test \| Lower is better \| \| `latency` \| 33.027 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.61 pp sourcePopulation 138 stderr 0.607 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-5.5 Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/math/openai~1gpt-5.5` | | | | | | | | | [BrokenArXiv 02/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--february.md) | 68.15% | 95% CI 59.95–76.35% | 1 / 15 | 0.77usd per problem | — | [matharena · arxiv_false--february](https://matharena.ai/competition_tables/arxiv_false--february) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.15 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.77 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--february predicted false Reasoning effort xhigh sourceModelName GPT-5.5 (xhigh) sourceModelVersion openai/gpt-55 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 59.95–76.35% confidenceInterval95 8.20 problems 31 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--february) Source matharena Original model label GPT-5.5 (xhigh) Source version arxiv_false--february Observed 2026-10-21T16:52:23.532Z Evidence SHA-256 `a6bc6fc18da7dd181ed727da924f9569d3e323c31c1aba9a4d9fa3bff492bee3` Source locator `/table/rows/0` | | | | | | | | | [Public Benefits Bench v1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Apublic-benefits-bench%3Aoverall.md) | 60.89% | SE ±1.27 pp | 23 / 34 | $3.97 | 2,377.31source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_snap.CUcEPb0v.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 60.893 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.971165 \| USD \| per_test \| Lower is better \| \| `latency` \| 2377.308 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.27 pp sourcePopulation 50 stderr 1.269 tokenTotals {"cache_read_tokens":790680064,"cache_write_tokens":null,"input_tokens":859486603,"output_tokens":5799841,"reasoning_tokens":3539368} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_snap.CUcEPb0v.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1.1 Observed 2026-10-21T16:46:17.865Z Evidence SHA-256 `6f091831ab607a26d65d2ade18cba7ce345ea3a67297b8c378e8a06ce398360d` Source locator `/tasks/overall/openai~1gpt-5.5` | | | | | | | | | [MMMU Pro / overall](https://benchize.com/benchmarks/vals-ai%3Ammmu%3Aoverall.md) | 88.27% | SE ±0.77 pp | 8 / 28 | $0.04 | 54.15source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmmu.BBln8x5x.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.266 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.043319 \| USD \| per_test \| Lower is better \| \| `latency` \| 54.147 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.77 pp sourcePopulation 93 stderr 0.774 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmmu.BBln8x5x.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:07.000Z Evidence SHA-256 `29395186eddd2c70601228c584a14b3c1d8f9dba4b68256561b46b0dd03c635a` Source locator `/tasks/overall/openai~1gpt-5.5` | | | | | | | | | [WorldVQA ForceAnswer](https://benchize.com/benchmarks/worldvqa-force-answer.md) | 38.5% | — | 5 / 5 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 38.5 \| percent \| reported \| Higher is better \| ### Configuration forceAnswer true Reasoning effort xhigh runs 3 thinkingEnabled true ### Reported statistics runCount 3 ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GPT 5.5 (xhigh) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/32/scores/4` | | | | | | | | | [EMB / ma](https://benchize.com/benchmarks/vals-ai%3Aemb%3Ama.md) | 66.81% | SE ±8.09 pp | 24 / 47 | $2.6 | 866.36source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.813 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.601886 \| USD \| per_test \| Lower is better \| \| `latency` \| 866.362 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.09 pp sourcePopulation 76 stderr 8.09 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/ma/openai~1gpt-5.5` | | | | | | | | | [HLE-Full](https://benchize.com/benchmarks/hle-full.md) | 41.4% | — | 5 / 5 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 41.4 \| percent \| reported \| Higher is better \| ### Configuration Reasoning effort xhigh sourceScoreFootnote * thinkingEnabled true toolsEnabled false ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GPT 5.5 (xhigh) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/21/scores/4` | | | | | | | | | [SAGE / linear algebra](https://benchize.com/benchmarks/vals-ai%3Asage%3Alinear_algebra.md) | 74.44% | SE ±4.92 pp | 4 / 41 | $0.11 | 44.7source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 74.436 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.114649 \| USD \| per_test \| Lower is better \| \| `latency` \| 44.698 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.92 pp sourcePopulation 91 stderr 4.923 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/linear_algebra/openai~1gpt-5.5` | | | | | | | | | [Tax Agent Bench / weighted pass fact pattern analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__fact_pattern_analysis.md) | 59.23% | SE ±7.08 pp | 24 / 46 | $3.88 | 956.48source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.225 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.881333 \| USD \| per_test \| Lower is better \| \| `latency` \| 956.476 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.08 pp sourcePopulation 73 stderr 7.076 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/weighted_pass__fact_pattern_analysis/openai~1gpt-5.5` | | | | | | | | | [Tax Agent Bench / weighted pass numbers calculations](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__numbers_calculations.md) | 76.76% | SE ±6.51 pp | 22 / 46 | $1.54 | 333.48source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 76.764 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.539682 \| USD \| per_test \| Lower is better \| \| `latency` \| 333.476 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.51 pp sourcePopulation 73 stderr 6.509 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/weighted_pass__numbers_calculations/openai~1gpt-5.5` | | | | | | | | | [ZeroBench main w/ python (pass@5)](https://benchize.com/benchmarks/zero-bench-main-python.md) | 41% | — | 2 / 5 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_at_5` \| 41.0 \| percent \| main_pass_at_5 \| Higher is better \| ### Configuration Reasoning effort xhigh runs 5 subset main thinkingEnabled true tools ["python"] toolsEnabled true trials 5 ### Reported statistics runCount 5 ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GPT 5.5 (xhigh) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/31/scores/4` | | | | | | | | | [Finance Agent (v2) / market analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Amarket_analysis.md) | 60.29% | SE ±1.61 pp | 29 / 50 | $2.72 | 498.93source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 60.288 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.721406 \| USD \| per_test \| Lower is better \| \| `latency` \| 498.931 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.61 pp sourcePopulation 80 stderr 1.614 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label openai/gpt-5.5 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/market_analysis/openai~1gpt-5.5` | | | | | | | | | [MMLU Pro / computer science](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Acomputer_science.md) | 89.76% | SE ±1.5 pp | 19 / 40 | $0.03 | 38.43source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.756 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.027059 \| USD \| per_test \| Lower is better \| \| `latency` \| 38.434 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.5 pp sourcePopulation 138 stderr 1.498 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-5.5 Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/computer_science/openai~1gpt-5.5` | | | | | | | | | [τ-bench banking knowledge](https://benchize.com/benchmarks/sierra%3Abanking_knowledge.md) | 44.59% | — | 3 / 19 | — | — | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5-5_sierra_2026-05-05/submission.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 44.58762886597938 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_2` \| 37.62886597938145 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_3` \| 33.24742268041237 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_4` \| 29.896907216494846 \| percent \| consistent_success_across_k_trials \| Higher is better \| ### Configuration benchmarkVersion 1.0.1 harness tau-bench methodology {"evaluation_date":"2026-07-22","notes":"Banking_knowledge evaluation with AllTools retrieval, GPT-5.2 low-reasoning user simulation, four trials, and seed 300.","tau2_bench_version":"1.0.1","user_simulator":"gpt-5.2","verification":{"modified_prompts":false,"omitted_questions":false}} modality text Reasoning effort xhigh retrieval alltools sourceSubmission gpt-5-5_sierra_2026-05-05 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5-5_sierra_2026-05-05/submission.json) Source sierra Original model label GPT-5.5 Evaluated 2026-05-05 Observed 2026-10-21T16:54:49.703Z Evidence SHA-256 `24247d74b2a942da4c8f85503d0f8b95ba6e2d5df7158c2adf15049056d8b7f4` Source locator `/results/banking_knowledge` | | | | | | | | | [SimpleQA Verified](https://benchize.com/benchmarks/epoch-ai%3Asimpleqa_verified.md) | 63% | SE ±1.53 pp | 14 / 39 | — | — | [epoch ai · SimpleQA Verified](https://epoch.ai/data/benchmark_data.zip#file=simpleqa_verified.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.63 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.63 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion SimpleQA Verified reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion gpt-5.5_xhigh ### Reported statistics Uncertainty Standard error: ±1.53 pp standardError 0.015275252316519465 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=simpleqa_verified.csv) Source epoch ai Original model label gpt-5.5 Source version SimpleQA Verified Evaluated 2026-08-27T19:28:25.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `d4ef3a7d6ccc9c611a30e98d0561021e903c0f4a224851311a7c420862154dd8` Source locator `/rows/65` | | | | | | | | | [SkillsBench / overall](https://benchize.com/benchmarks/vals-ai%3Askillsbench%3Aoverall.md) | 62.21% | SE ±4.52 pp | 3 / 20 | $2.54 | 414.62source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_skillsbench.BE2TXB-M.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 62.209 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.54346 \| USD \| per_test \| Lower is better \| \| `latency` \| 414.615 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness OpenHands maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.52 pp sourcePopulation 35 stderr 4.523 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_skillsbench.BE2TXB-M.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:11.147Z Evidence SHA-256 `aaad242949d81b7c7c61c36d4895d4460e9146760c1e6b4b38d235a16043bc61` Source locator `/tasks/overall/openai~1gpt-5.5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate international trade sanctions](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__international_trade_sanctions.md) | 80.95% | SE ±2.48 pp | 35 / 49 | $2.36 | 636.4source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.952 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.359423 \| USD \| per_test \| Lower is better \| \| `latency` \| 636.396 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.48 pp sourcePopulation 81 stderr 2.479 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/openai~1gpt-5.5` | | | | | | | | | [Finance Agent (v2) / comparables](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Acomparables.md) | 43.65% | SE ±0.5 pp | 30 / 50 | $5.68 | 798.36source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 43.653 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.684233 \| USD \| per_test \| Lower is better \| \| `latency` \| 798.364 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.5 pp sourcePopulation 80 stderr 0.5 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label openai/gpt-5.5 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/comparables/openai~1gpt-5.5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate corporate governance](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__corporate_governance.md) | 78.43% | SE ±2.41 pp | 35 / 49 | $6.43 | 757.95source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 78.425 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.425704 \| USD \| per_test \| Lower is better \| \| `latency` \| 757.952 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.41 pp sourcePopulation 81 stderr 2.411 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__corporate_governance/openai~1gpt-5.5` | | | | | | | | | [Tax Agent Bench / weighted pass controversy precedence analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__controversy_precedence_analysis.md) | 54.91% | SE ±8.42 pp | 22 / 46 | $4.71 | 1,096.63source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 54.91 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.706236 \| USD \| per_test \| Lower is better \| \| `latency` \| 1096.628 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.42 pp sourcePopulation 73 stderr 8.417 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/weighted_pass__controversy_precedence_analysis/openai~1gpt-5.5` | | | | | | | | | [SAGE / overall](https://benchize.com/benchmarks/vals-ai%3Asage%3Aoverall.md) | 51.53% | SE ±3.95 pp | 9 / 41 | $0.14 | 76.05source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 51.532 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.136289 \| USD \| per_test \| Lower is better \| \| `latency` \| 76.05 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.95 pp sourcePopulation 91 stderr 3.954 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/overall/openai~1gpt-5.5` | | | | | | | | | [SAGE / PDEs](https://benchize.com/benchmarks/vals-ai%3Asage%3APDEs.md) | 39.68% | SE ±6.15 pp | 21 / 41 | $0.14 | 91.9source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.683 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.142524 \| USD \| per_test \| Lower is better \| \| `latency` \| 91.895 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.15 pp sourcePopulation 91 stderr 6.148 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/PDEs/openai~1gpt-5.5` | | | | | | | | | [Short Story Writing — Pairwise Comparison](https://benchize.com/benchmarks/lechmazur-short-story%3Apairwise.md) | 2.43 | 95% CI 2.37–2.5 | 9 / 50 | — | — | [lechmazur short story · 8ba548d1cffefa5c472d3832e05f64e119a88fa4](https://api.github.com/repos/lechmazur/writing/contents/data/writing_gemini_argon_20261013/ratings.csv?ref=8ba548d1cffefa5c472d3832e05f64e119a88fa4) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `thurstone_rating` \| 2.432634818748467 \| index \| pooled_observed_panel \| Higher is better \| \| `win_probability` \| 0.8240518700529466 \| score_fraction \| comparison_pool \| Higher is better \| ### Configuration benchmarkScope data/writing_gemini_argon_20261013 Reasoning effort xhigh thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 2.37–2.5 bootstrapSamples 300 confidenceInterval95 ["2.3656110696462105","2.496184424290147"] sourceRank 9 ### Source [Original source](https://api.github.com/repos/lechmazur/writing/contents/data/writing_gemini_argon_20261013/ratings.csv?ref=8ba548d1cffefa5c472d3832e05f64e119a88fa4) Source lechmazur short story Original model label GPT-5.5 (xhigh) Source version 8ba548d1cffefa5c472d3832e05f64e119a88fa4 Observed 2026-10-21T16:34:21.130Z Evidence SHA-256 `c36baebed9f302ff7ad8fe97907d72e1757a015a39b6a3b23437597cf8e3bff6` Source locator `/rows/8` | | | | | | | | | [FrontierCode 1 main](https://benchize.com/benchmarks/frontiercode%3Av1%3Amain.md) | 25.48% | — | 10 / 39 | $5.59 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.2548 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.2825 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 5.5911 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort xhigh sourceVersion v1 subset main ### Reported statistics flaggedRate Not reported sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GPT-5.5 Observed 2026-10-21T16:31:00.878Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1/data/GPT-5.5/xhigh/main` | | | | | | | | | [EMB / dcf](https://benchize.com/benchmarks/vals-ai%3Aemb%3Adcf.md) | 56.74% | SE ±7.84 pp | 21 / 47 | $2.84 | 883.69source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 56.736 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.839702 \| USD \| per_test \| Lower is better \| \| `latency` \| 883.688 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.84 pp sourcePopulation 76 stderr 7.836 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/dcf/openai~1gpt-5.5` | | | | | | | | | [Public Benefits Bench v1 / both](https://benchize.com/benchmarks/vals-ai%3Apublic-benefits-bench-v1%3Aboth.md) | 57.24% | SE ±1.29 pp | 7 / 8 | $2.02 | 1,580.53source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_snap_v1.BPa0Hrre.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 57.24 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.018596 \| USD \| per_test \| Lower is better \| \| `latency` \| 1580.527 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.29 pp sourcePopulation 13 stderr 1.287 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_snap_v1.BPa0Hrre.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:18.363Z Evidence SHA-256 `b85e2b3cbdf03e13e2ffdb27ce4f108003a548d705a24ae26a0a115e2027475d` Source locator `/tasks/both/openai~1gpt-5.5` | | | | | | | | | [BrokenArXiv 06/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--june.md) | 69.44% | 95% CI 62.35–76.53% | 8 / 21 | 1.47usd per problem | — | [matharena · arxiv_false--june](https://matharena.ai/competition_tables/arxiv_false--june) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.44 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 1.47 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--june predicted false Reasoning effort xhigh sourceModelName GPT-5.5 (xhigh) sourceModelVersion openai/gpt-55 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 62.35–76.53% confidenceInterval95 7.09 problems 54 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--june) Source matharena Original model label GPT-5.5 (xhigh) Source version arxiv_false--june Observed 2026-10-21T16:52:25.323Z Evidence SHA-256 `f6d7e2280d05706643d46ae7786bd3fad6d912e4893781c3f62c73deebf38459` Source locator `/table/rows/7` | | | | | | | | | [SAGE / automata](https://benchize.com/benchmarks/vals-ai%3Asage%3Aautomata.md) | 40.48% | SE ±8.87 pp | 10 / 41 | $0.15 | 91.56source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 40.476 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.151694 \| USD \| per_test \| Lower is better \| \| `latency` \| 91.557 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.87 pp sourcePopulation 91 stderr 8.871 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/openai~1gpt-5.5` | | | | | | | | | [Time Horizon Index: KSP / overall](https://benchize.com/benchmarks/vals-ai%3Atime_horizon_index%3Aoverall.md) | 8.33% | SE ±0 pp | 9 / 10 | $516.36 | 0source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_ksp_bench.CDDTSam7.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 8.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 516.360641 \| USD \| per_test \| Lower is better \| \| `latency` \| 0 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 13 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ksp_bench.CDDTSam7.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:16.730Z Evidence SHA-256 `be251b72ecceae7912b9577f9b3a3512740c308a34f81ac823952e919adae50f` Source locator `/tasks/overall/openai~1gpt-5.5` | | | | | | | | | [MMLU Pro / engineering](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aengineering.md) | 84.83% | SE ±1.15 pp | 18 / 40 | $0.06 | 79.6source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.83 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.062984 \| USD \| per_test \| Lower is better \| \| `latency` \| 79.599 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.15 pp sourcePopulation 138 stderr 1.152 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-5.5 Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/engineering/openai~1gpt-5.5` | | | | | | | | | [ProgramBench / partial](https://benchize.com/benchmarks/vals-ai%3Aprogrambench%3Apartial.md) | 70.78% | SE ±1.82 pp | 19 / 40 | $6.95 | 1,322.96source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.775 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.95454 \| USD \| per_test \| Lower is better \| \| `latency` \| 1322.959 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.82 pp sourcePopulation 64 stderr 1.822 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:10.137Z Evidence SHA-256 `e9bbb4378c7a058441a21d456baf9316b96c2cf5b58d371a3c7c803f5000bd8c` Source locator `/tasks/partial/openai~1gpt-5.5` | | | | | | | | | [FrontierMath Tier 4 v2 (private)](https://benchize.com/benchmarks/epoch-ai%3Afrontiermath_tier_4_v2.md) | 72.5% | SE ±7.15 pp | 18 / 38 | — | — | [epoch ai · FrontierMath-Tier-4-v2-Private](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.725 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.725 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion gpt-5.5_xhigh ### Reported statistics Uncertainty Standard error: ±7.15 pp standardError 0.07149950690165274 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gpt-5.5 Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-06-11T17:47:36.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/64` | | | | | | | | | [ArXivMath 06/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--june.md) | 83.63% | 95% CI 79.67–87.59% | 8 / 22 | 1.82usd per problem | — | [matharena · arxiv--june](https://matharena.ai/competition_tables/arxiv--june) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.63 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 1.82 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--june predicted false Reasoning effort xhigh sourceModelName GPT-5.5 (xhigh) sourceModelVersion openai/gpt-55 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 79.67–87.59% confidenceInterval95 3.96 problems 48 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--june) Source matharena Original model label GPT-5.5 (xhigh) Source version arxiv--june Observed 2026-10-21T16:52:29.905Z Evidence SHA-256 `6832faff9be7e16a6c646c59017e30a2caedebe8cf02caf617a5ed9d8fb03bab` Source locator `/table/rows/7` | | | | | | | | | [Finance Agent (v2) / general qualitative analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Ageneral_qualitative_analysis.md) | 65.56% | SE ±1.39 pp | 23 / 50 | $4.53 | 717.08source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 65.559 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.530392 \| USD \| per_test \| Lower is better \| \| `latency` \| 717.08 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.39 pp sourcePopulation 80 stderr 1.39 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label openai/gpt-5.5 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/general_qualitative_analysis/openai~1gpt-5.5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate white collar defense investigations](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__white_collar_defense_investigations.md) | 65.32% | SE ±2.77 pp | 38 / 49 | $3.62 | 571.98source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 65.32 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.615019 \| USD \| per_test \| Lower is better \| \| `latency` \| 571.98 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.77 pp sourcePopulation 81 stderr 2.766 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__white_collar_defense_investigations/openai~1gpt-5.5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate corporate ma](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__corporate_ma.md) | 87.5% | SE ±1.88 pp | 31 / 49 | $3.4 | 803.61source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.395472 \| USD \| per_test \| Lower is better \| \| `latency` \| 803.612 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.88 pp sourcePopulation 81 stderr 1.875 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__corporate_ma/openai~1gpt-5.5` | | | | | | | | | [Tax Agent Bench / current temporal analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Acurrent_temporal_analysis.md) | 26.67% | SE ±8.21 pp | 33 / 46 | $5.23 | 1,352.02source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 26.667 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.233081 \| USD \| per_test \| Lower is better \| \| `latency` \| 1352.021 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.21 pp sourcePopulation 73 stderr 8.212 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/current_temporal_analysis/openai~1gpt-5.5` | | | | | | | | | [LiveCodeBench / easy](https://benchize.com/benchmarks/vals-ai%3Alcb%3Aeasy.md) | 98.45% | SE ±0.69 pp | 26 / 43 | $0.01 | 48.39source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 98.447 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.012472 \| USD \| per_test \| Lower is better \| \| `latency` \| 48.393 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.69 pp sourcePopulation 143 stderr 0.689 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:14.220Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/easy/openai~1gpt-5.5` | | | | | | | | | [TaxEval v2 / stepwise reasoning](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Astepwise_reasoning.md) | 84.46% | SE ±1.04 pp | 22 / 40 | $0.06 | 95.83source 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` \| 84.464 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.06042 \| USD \| per_test \| Lower is better \| \| `latency` \| 95.83 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.04 pp sourcePopulation 145 stderr 1.036 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-5.5 Source version 2 Observed 2026-10-21T16:45:59.000Z Evidence SHA-256 `8b354a6ae848f5bb25a2e8b061b5f576d5b9e0c11b941dc1e6bed078e6529cd6` Source locator `/tasks/stepwise_reasoning/openai~1gpt-5.5` | | | | | | | | | [GPQA Diamond](https://benchize.com/benchmarks/gpqa-diamond.md) | 93.18% | SE ±1.29 pp | 8 / 40 | $0.08 | 112.33source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 93.182 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.082767 \| USD \| per_test \| Lower is better \| \| `latency` \| 112.326 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.29 pp sourcePopulation 138 stderr 1.288 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:06.040Z Evidence SHA-256 `951eb5224097733a9d09d06c14908ae2980e2e640e539f2c284877c5092d7077` Source locator `/tasks/overall/openai~1gpt-5.5` | | | | | | | | | [Legal Research Bench / weighted pass business commercial](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__business_commercial.md) | 86.76% | SE ±2.95 pp | 20 / 50 | $6.68 | 2,266.22source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.764 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.684872 \| USD \| per_test \| Lower is better \| \| `latency` \| 2266.219 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.95 pp sourcePopulation 82 stderr 2.947 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__business_commercial/openai~1gpt-5.5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate banking finance](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__banking_finance.md) | 86.25% | SE ±2.1 pp | 29 / 49 | $3.45 | 632.11source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.245 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.453057 \| USD \| per_test \| Lower is better \| \| `latency` \| 632.108 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.1 pp sourcePopulation 81 stderr 2.104 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__banking_finance/openai~1gpt-5.5` | | | | | | | | | [Kimi Code Bench 2.0 (Internal)](https://benchize.com/benchmarks/kimi-code-bench-2.md) | 69% | — | 4 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 69.0 \| percent \| reported \| Higher is better \| ### Configuration benchmarkVisibility internal harness Codex Reasoning effort xhigh thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GPT 5.5 (xhigh) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/7/scores/4` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate tax](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__tax.md) | 72.58% | SE ±2.58 pp | 33 / 49 | $4.83 | 671.38source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 72.575 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.83132 \| USD \| per_test \| Lower is better \| \| `latency` \| 671.384 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.58 pp sourcePopulation 81 stderr 2.584 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__tax/openai~1gpt-5.5` | | | | | | | | | [LegalBench / conclusion tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Aconclusion_tasks.md) | 89.64% | SE ±0.7 pp | 12 / 44 | $0.00784 | 11.17source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.644 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.00784 \| USD \| per_test \| Lower is better \| \| `latency` \| 11.168 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.7 pp sourcePopulation 151 stderr 0.697 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-5.5 Source version 1 Observed 2026-10-21T16:45:53.390Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/conclusion_tasks/openai~1gpt-5.5` | | | | | | | | | [Tax Agent Bench / rule source lookup](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Arule_source_lookup.md) | 23.33% | SE ±7.85 pp | 31 / 46 | $3.52 | 799.36source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 23.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.524307 \| USD \| per_test \| Lower is better \| \| `latency` \| 799.357 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.85 pp sourcePopulation 73 stderr 7.854 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/rule_source_lookup/openai~1gpt-5.5` | | | | | | | | | [Furniture Assembly Benchmark](https://benchize.com/benchmarks/epoch-ai%3Afurniture_assembly.md) | 44.17% | SE ±6.41 pp | 12 / 21 | — | — | [epoch ai · Furniture Assembly](https://epoch.ai/data/benchmark_data.zip#file=furniture_assembly.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.44166666666666665 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.44166666666666665 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion Furniture Assembly reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion gpt-5.5_xhigh ### Reported statistics Uncertainty Standard error: ±6.41 pp standardError 0.06410142328406845 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=furniture_assembly.csv) Source epoch ai Original model label gpt-5.5 Source version Furniture Assembly Evaluated 2026-09-10T20:22:27.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `d62ab28005a1b7ab0e57b227d04b0cf86c70a5d8a1981addb26d2ac41c116865` Source locator `/rows/31` | | | | | | | | | [SAGE / calculus](https://benchize.com/benchmarks/vals-ai%3Asage%3Acalculus.md) | 72.22% | SE ±5.57 pp | 16 / 36 | $0.11 | 54.88source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 72.222 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.112212 \| USD \| per_test \| Lower is better \| \| `latency` \| 54.876 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.57 pp sourcePopulation 91 stderr 5.571 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/calculus/openai~1gpt-5.5` | | | | | | | | | [FrontierMath Tiers 1–3 v2 (private)](https://benchize.com/benchmarks/epoch-ai%3Afrontiermath_tiers_1_3_v2.md) | 85.26% | SE ±2.1 pp | 13 / 49 | — | — | [epoch ai · FrontierMath-Tiers-1-3-v2-Private](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tiers_1_3_v2.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.8526315789473684 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.8526315789473684 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tiers-1-3-v2-Private reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion gpt-5.5_xhigh ### Reported statistics Uncertainty Standard error: ±2.1 pp standardError 0.021034091168852485 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tiers_1_3_v2.csv) Source epoch ai Original model label gpt-5.5 Source version FrontierMath-Tiers-1-3-v2-Private Evaluated 2026-06-11T17:47:36.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `6e31ece7503f8f89dffe8af33010ed7d1d6f0aa3a80cff14fa79f9b34a7b258f` Source locator `/rows/108` | | | | | | | | | [MMLU Pro / biology](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Abiology.md) | 94% | SE ±0.89 pp | 12 / 40 | $0.02 | 24.48source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 94.003 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.018287 \| USD \| per_test \| Lower is better \| \| `latency` \| 24.475 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.89 pp sourcePopulation 138 stderr 0.887 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-5.5 Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/biology/openai~1gpt-5.5` | | | | | | | | | [MMLU Pro / economics](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aeconomics.md) | 89.93% | SE ±1.04 pp | 17 / 40 | $0.02 | 28.85source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.929 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.01703 \| USD \| per_test \| Lower is better \| \| `latency` \| 28.846 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.04 pp sourcePopulation 138 stderr 1.036 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-5.5 Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/economics/openai~1gpt-5.5` | | | | | | | | | [Legal Research Bench / business commercial](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Abusiness_commercial.md) | 37.21% | SE ±7.46 pp | 20 / 50 | $6.68 | 2,266.22source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 37.209 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.684872 \| USD \| per_test \| Lower is better \| \| `latency` \| 2266.219 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.46 pp sourcePopulation 82 stderr 7.458 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/business_commercial/openai~1gpt-5.5` | | | | | | | | | [ProgramBench / almost](https://benchize.com/benchmarks/vals-ai%3Aprogrambench%3Aalmost.md) | 9.5% | SE ±2.08 pp | 21 / 40 | $6.95 | 1,322.96source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 9.5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.95454 \| USD \| per_test \| Lower is better \| \| `latency` \| 1322.959 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.08 pp sourcePopulation 64 stderr 2.079 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:10.137Z Evidence SHA-256 `e9bbb4378c7a058441a21d456baf9316b96c2cf5b58d371a3c7c803f5000bd8c` Source locator `/tasks/almost/openai~1gpt-5.5` | | | | | | | | | [Kangaroo 2025 1-2](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_1-2.md) | 95.83% | 95% CI 91.83–99.83% | 1 / 16 | 0.11usd per problem | — | [matharena · kangaroo--kangaroo_2025_1-2](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_1-2) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.83 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.11 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_1-2 predicted false Reasoning effort xhigh sourceModelName GPT-5.5 (xhigh) sourceModelVersion openai/gpt-55 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 91.83–99.83% confidenceInterval95 4.00 problems 24 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_1-2) Source matharena Original model label GPT-5.5 (xhigh) Source version kangaroo--kangaroo_2025_1-2 Observed 2026-10-21T16:52:31.513Z Evidence SHA-256 `a59a4c362e2d87350330706a01dd330e9a1ac7cc64a4de0bacbf1a439d8fcf90` Source locator `/table/rows/0` | | | | | | | | | [MMLU Pro / chemistry](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Achemistry.md) | 91.25% | SE ±0.84 pp | 20 / 40 | $0.03 | 54.56source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.254 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.028489 \| USD \| per_test \| Lower is better \| \| `latency` \| 54.56 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.84 pp sourcePopulation 138 stderr 0.84 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-5.5 Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/chemistry/openai~1gpt-5.5` | | | | | | | | | [AIME 2026](https://benchize.com/benchmarks/aime-2026.md) | 100% | 95% CI 100–100% | 1 / 21 | 0.16usd per problem | — | [matharena · aime--aime_2026](https://matharena.ai/competition_tables/aime--aime_2026) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100.00 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.16 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition aime--aime_2026 predicted false Reasoning effort xhigh sourceModelName GPT-5.5 (xhigh) sourceModelVersion openai/gpt-55 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 100–100% confidenceInterval95 0.00 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/aime--aime_2026) Source matharena Original model label GPT-5.5 (xhigh) Source version aime--aime_2026 Observed 2026-10-21T16:52:37.816Z Evidence SHA-256 `58b3ac1e0805975eba566c493b8e0165d41eb7ca517218106e112529fb6342de` Source locator `/table/rows/0` | | | | | | | | | [BabyVision w/ python](https://benchize.com/benchmarks/babyvision-python.md) | 83.6% | — | 4 / 5 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 83.6 \| percent \| reported \| Higher is better \| ### Configuration Reasoning effort xhigh runs 3 thinkingEnabled true tools ["python"] toolsEnabled true ### Reported statistics runCount 3 ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GPT 5.5 (xhigh) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/29/scores/4` | | | | | | | | | [CharXiv (RQ) w/ python](https://benchize.com/benchmarks/charxiv-rq-python.md) | 89% | — | 5 / 5 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 89.0 \| percent \| reported \| Higher is better \| ### Configuration Reasoning effort xhigh runs 3 subset RQ thinkingEnabled true tools ["python"] toolsEnabled true ### Reported statistics runCount 3 ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GPT 5.5 (xhigh) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/26/scores/4` | | | | | | | | | [MedScribe / overall](https://benchize.com/benchmarks/vals-ai%3Amedscribe%3Aoverall.md) | 86.87% | SE ±1.93 pp | 13 / 49 | $0.14 | 132.76source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.868 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.142988 \| USD \| per_test \| Lower is better \| \| `latency` \| 132.761 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.93 pp sourcePopulation 109 stderr 1.932 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/openai~1gpt-5.5` | | | | | | | | | [ProgramBench / overall](https://benchize.com/benchmarks/vals-ai%3Aprogrambench%3Aoverall.md) | 0.5% | SE ±0.5 pp | 14 / 40 | $6.95 | 1,322.96source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0.5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.95454 \| USD \| per_test \| Lower is better \| \| `latency` \| 1322.959 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.5 pp sourcePopulation 64 stderr 0.5 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:10.137Z Evidence SHA-256 `e9bbb4378c7a058441a21d456baf9316b96c2cf5b58d371a3c7c803f5000bd8c` Source locator `/tasks/overall/openai~1gpt-5.5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / environmental esg](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aenvironmental_esg.md) | 0% | SE ±0 pp | 1 / 49 | $3.08 | 762.87source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.081603 \| USD \| per_test \| Lower is better \| \| `latency` \| 762.87 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/environmental_esg/openai~1gpt-5.5` | | | | | | | | | [OfficeQA Pro — Agent Harness](https://benchize.com/benchmarks/officeqa-pro%3Aagent.md) | 60.9% | — | 5 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 60.9 \| percent \| reported \| Higher is better \| ### Configuration corpusFormat rendered_pdf_images harness Codex machineReadablePdfText false Reasoning effort xhigh sourceScoreFootnote * thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GPT 5.5 (xhigh) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/17/scores/4` | | | | | | | | | [MCP Atlas](https://benchize.com/benchmarks/scale%3Amcp_atlas.md) | 75.3source score | CI 72.6–78 | 11 / 22 | — | — | [scale](https://labs.scale.com/leaderboard/mcp_atlas) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 75.3 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort xhigh Model configuration gpt-5.5 (xhigh) sourceModelVersion Not reported thinkingEnabled true ### Reported statistics Uncertainty Confidence interval: 72.6–78 contaminationWarning Not reported rank 19 reportedConfidenceHalfWidth 2.7 ### Source [Original source](https://labs.scale.com/leaderboard/mcp_atlas) Source scale Original model label gpt-5.5 (xhigh) Observed 2026-10-21T16:35:30.627Z Evidence SHA-256 `1467b1d078bf39a76fb663f006002e7c7d08224ca7c3de883ab628a2efccebb8` Source locator `/rows/18` | | | | | | | | | [SRE Bench / overall](https://benchize.com/benchmarks/vals-ai%3Asrebench%3Aoverall.md) | 3.82% | SE ±1.19 pp | 15 / 24 | $17.77 | 2,788source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sre_bench.Bd0uBJxH.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 3.817 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 17.773692 \| USD \| per_test \| Lower is better \| \| `latency` \| 2787.997 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.19 pp sourcePopulation 35 stderr 1.186 tokenTotals {"cache_read_tokens":5009534976,"cache_write_tokens":null,"input_tokens":5148417224,"output_tokens":16855383,"reasoning_tokens":8349676} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sre_bench.Bd0uBJxH.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:15.724Z Evidence SHA-256 `a10b2c964f5878b0fc21c888703f311a5ef7d7a74fc3c529cab3ddd9fa474e2b` Source locator `/tasks/overall/openai~1gpt-5.5` | | | | | | | | | [Vals Multimodal Index / mortgage tax](https://benchize.com/benchmarks/vals-ai%3Avals_multimodal_index%3Amortgage_tax.md) | 68.76% | SE ±0.91 pp | 7 / 20 | $0.07 | 28.24source duration | [Vals AI · 1.2](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.76 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.071407 \| USD \| per_test \| Lower is better \| \| `latency` \| 28.243 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.91 pp sourcePopulation 33 stderr 0.912 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1.2 Observed 2026-10-21T16:45:51.881Z Evidence SHA-256 `077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d` Source locator `/tasks/mortgage_tax/openai~1gpt-5.5` | | | | | | | | | [LegalBench / interpretation tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Ainterpretation_tasks.md) | 83.84% | SE ±0.19 pp | 11 / 44 | $0.01 | 15.56source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.836 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.014325 \| USD \| per_test \| Lower is better \| \| `latency` \| 15.562 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.19 pp sourcePopulation 151 stderr 0.194 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-5.5 Source version 1 Observed 2026-10-21T16:45:53.390Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/interpretation_tasks/openai~1gpt-5.5` | | | | | | | | | [Public Benefits Bench v1 / overall](https://benchize.com/benchmarks/vals-ai%3Apublic-benefits-bench-v1%3Aoverall.md) | 57.24% | SE ±1.29 pp | 7 / 8 | $2.02 | 1,580.53source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_snap_v1.BPa0Hrre.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 57.24 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.018596 \| USD \| per_test \| Lower is better \| \| `latency` \| 1580.527 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.29 pp sourcePopulation 13 stderr 1.287 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_snap_v1.BPa0Hrre.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:18.363Z Evidence SHA-256 `b85e2b3cbdf03e13e2ffdb27ce4f108003a548d705a24ae26a0a115e2027475d` Source locator `/tasks/overall/openai~1gpt-5.5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate environmental esg](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__environmental_esg.md) | 82.08% | SE ±2.3 pp | 28 / 49 | $3.08 | 762.87source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.079 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.081603 \| USD \| per_test \| Lower is better \| \| `latency` \| 762.87 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.3 pp sourcePopulation 81 stderr 2.3 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__environmental_esg/openai~1gpt-5.5` | | | | | | | | | [EMB / misc](https://benchize.com/benchmarks/vals-ai%3Aemb%3Amisc.md) | 64.65% | SE ±6.9 pp | 14 / 47 | $2.91 | 985.39source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 64.647 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.912134 \| USD \| per_test \| Lower is better \| \| `latency` \| 985.394 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.9 pp sourcePopulation 76 stderr 6.895 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/misc/openai~1gpt-5.5` | | | | | | | | | [Vals Multimodal Index / sage](https://benchize.com/benchmarks/vals-ai%3Avals_multimodal_index%3Asage.md) | 51.53% | SE ±3.95 pp | 6 / 20 | $0.13 | 76.05source duration | [Vals AI · 1.2](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 51.532 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.130637 \| USD \| per_test \| Lower is better \| \| `latency` \| 76.05 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.95 pp sourcePopulation 33 stderr 3.954 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1.2 Observed 2026-10-21T16:45:51.881Z Evidence SHA-256 `077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d` Source locator `/tasks/sage/openai~1gpt-5.5` | | | | | | | | | [CorpFin v2 / max fitting context](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Amax_fitting_context.md) | 70.05% | SE ±1.56 pp | 5 / 39 | $0.9 | 25.33source 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` \| 70.047 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.902658 \| USD \| per_test \| Lower is better \| \| `latency` \| 25.327 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.56 pp sourcePopulation 134 stderr 1.564 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-5.5 Source version 2 Observed 2026-10-21T16:45:57.998Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/max_fitting_context/openai~1gpt-5.5` | | | | | | | | | [Legal Research Bench / constitutional civil rights](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aconstitutional_civil_rights.md) | 28.95% | SE ±7.46 pp | 31 / 50 | $5.73 | 2,156.64source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 28.947 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.731692 \| USD \| per_test \| Lower is better \| \| `latency` \| 2156.642 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.46 pp sourcePopulation 82 stderr 7.456 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/constitutional_civil_rights/openai~1gpt-5.5` | | | | | | | | | [USAMO 2026](https://benchize.com/benchmarks/matharena%3Ausamo--usamo_2026.md) | 98.21% | 95% CI 92.91–103.51% | 1 / 8 | 0.79usd per problem | — | [matharena · usamo--usamo_2026](https://matharena.ai/competition_tables/usamo--usamo_2026) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 98.21 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.79 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition usamo--usamo_2026 predicted false Reasoning effort xhigh sourceModelName GPT-5.5 (xhigh) sourceModelVersion openai/gpt-55 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 92.91–103.51% confidenceInterval95 5.30 problems 6 ### Source [Original source](https://matharena.ai/competition_tables/usamo--usamo_2026) Source matharena Original model label GPT-5.5 (xhigh) Source version usamo--usamo_2026 Observed 2026-10-21T16:52:41.374Z Evidence SHA-256 `2c6f85fa189ac482d54d597e1cbbe64803cda65cd85e78add44087d94799756b` Source locator `/table/rows/0` | | | | | | | | | [SkillsBench / with skills](https://benchize.com/benchmarks/vals-ai%3Askillsbench%3Awith_skills.md) | 62.21% | SE ±4.52 pp | 3 / 20 | $2.54 | 414.62source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_skillsbench.BE2TXB-M.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 62.209 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.54346 \| USD \| per_test \| Lower is better \| \| `latency` \| 414.615 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness OpenHands maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.52 pp sourcePopulation 35 stderr 4.523 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_skillsbench.BE2TXB-M.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:11.147Z Evidence SHA-256 `aaad242949d81b7c7c61c36d4895d4460e9146760c1e6b4b38d235a16043bc61` Source locator `/tasks/with_skills/openai~1gpt-5.5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / immigration](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aimmigration.md) | 0% | SE ±0 pp | 6 / 49 | $2.99 | 682.57source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.985935 \| USD \| per_test \| Lower is better \| \| `latency` \| 682.574 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/immigration/openai~1gpt-5.5` | | | | | | | | | [PostTrain Bench](https://benchize.com/benchmarks/posttrainbench.md) | 28.4% | — | 6 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 28.4 \| percent \| reported \| Higher is better \| ### Configuration Reasoning effort xhigh thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GPT 5.5 (xhigh) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/5/scores/4` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / insurance](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Ainsurance.md) | 0% | SE ±0 pp | 2 / 49 | $2.42 | 631.63source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.417604 \| USD \| per_test \| Lower is better \| \| `latency` \| 631.634 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/insurance/openai~1gpt-5.5` | | | | | | | | | [FrontierCode 1 extended](https://benchize.com/benchmarks/frontiercode%3Av1%3Aextended.md) | 44.67% | — | 11 / 39 | $4.62 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4467 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.4903 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 4.6186 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort xhigh sourceVersion v1 subset extended ### Reported statistics flaggedRate Not reported sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GPT-5.5 Observed 2026-10-21T16:31:00.878Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1/data/GPT-5.5/xhigh/extended` | | | | | | | | | [Finance Agent (v2) / precedents](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Aprecedents.md) | 21.89% | SE ±1.9 pp | 33 / 50 | $7.46 | 1,110.44source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 21.894 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.463278 \| USD \| per_test \| Lower is better \| \| `latency` \| 1110.441 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.9 pp sourcePopulation 80 stderr 1.895 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label openai/gpt-5.5 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/precedents/openai~1gpt-5.5` | | | | | | | | | [Legal Research Bench / administrative regulatory](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aadministrative_regulatory.md) | 53.03% | SE ±6.19 pp | 13 / 50 | $7.95 | 2,093.38source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 53.03 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.953883 \| USD \| per_test \| Lower is better \| \| `latency` \| 2093.383 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.19 pp sourcePopulation 82 stderr 6.19 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/administrative_regulatory/openai~1gpt-5.5` | | | | | | | | | [SWE-bench / 1-4 hours](https://benchize.com/benchmarks/vals-ai%3Aswebench%3A1-4%20hours.md) | 50% | SE ±7.81 pp | 17 / 39 | $1.5 | 650.11source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.502703 \| USD \| per_test \| Lower is better \| \| `latency` \| 650.107 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.81 pp sourcePopulation 88 stderr 7.809 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/1-4 hours/openai~1gpt-5.5` | | | | | | | | | [Terminal-Bench 2.1](https://benchize.com/benchmarks/artificial-analysis%3Aterminalbench_v2_1.md) | 83.4% | — | 5 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 83.4 \| percent \| reported \| Higher is better \| ### Configuration harness Codex Reasoning effort xhigh thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GPT 5.5 (xhigh) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/2/scores/4` | | | | | | | | | [LiveCodeBench / overall](https://benchize.com/benchmarks/vals-ai%3Alcb%3Aoverall.md) | 85.3% | SE ±1.02 pp | 20 / 43 | $0.07 | 166.85source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.296 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.0666 \| USD \| per_test \| Lower is better \| \| `latency` \| 166.845 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.02 pp sourcePopulation 143 stderr 1.018 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:14.220Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/overall/openai~1gpt-5.5` | | | | | | | | | [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 95% | — | 34 / 213 | 0.73usd per task | — | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.95 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.73 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup gpt-5-5-2026-04-22-thinking modelType CoT Reasoning effort xhigh sourceModelVersion gpt-5-5-2026-04-22-thinking-xhigh thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label GPT-5.5 (XHigh) Source version v1 Observed 2026-10-21T16:34:20.378Z Evidence SHA-256 `302d8267c0522bf450ec1deeac4d060e2cf2fb444ba0a4269014d9535de0bd1f` Source locator `/evaluations/149` | | | | | | | | | [Code Migration / cobol](https://benchize.com/benchmarks/vals-ai%3Acode-migration%3Acobol.md) | 70% | SE ±15.28 pp | 1 / 47 | $3.15 | 2,340.7source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_code_migration.Dttzoqk3.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.151116 \| USD \| per_test \| Lower is better \| \| `latency` \| 2340.697 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±15.28 pp sourcePopulation 79 stderr 15.275 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_code_migration.Dttzoqk3.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:12.712Z Evidence SHA-256 `99194597f2c76c402195be47839409046e18bd30454616da6dd40b736a088fa4` Source locator `/tasks/cobol/openai~1gpt-5.5` | | | | | | | | | [Finance Agent (v2) / overall](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Aoverall.md) | 51.76% | SE ±0.55 pp | 28 / 50 | $4.15 | 662.27source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 51.76 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.149702 \| USD \| per_test \| Lower is better \| \| `latency` \| 662.269 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.55 pp sourcePopulation 80 stderr 0.55 tokenTotals {"cache_read_tokens":217525163,"cache_write_tokens":null,"input_tokens":423716492,"output_tokens":17794792,"reasoning_tokens":13531292} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label openai/gpt-5.5 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/overall/openai~1gpt-5.5` | | | | | | | | | [Finance Agent (v2) / general quantitative analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Ageneral_quantitative_analysis.md) | 73.71% | SE ±1.75 pp | 24 / 50 | $3.75 | 485.35source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 73.714 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.745478 \| USD \| per_test \| Lower is better \| \| `latency` \| 485.345 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.75 pp sourcePopulation 80 stderr 1.754 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label openai/gpt-5.5 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/general_quantitative_analysis/openai~1gpt-5.5` | | | | | | | | | [CaseLaw v2 / overall](https://benchize.com/benchmarks/vals-ai%3Acase_law_v2%3Aoverall.md) | 66.24% | SE ±0.32 pp | 2 / 17 | $0.16 | 25.2source 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` \| 66.238 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.155011 \| USD \| per_test \| Lower is better \| \| `latency` \| 25.2 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.32 pp sourcePopulation 54 stderr 0.322 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-5.5 Source version 2 Observed 2026-10-21T16:45:54.497Z Evidence SHA-256 `293f388f7e0fe563287d4cd19beaa7ef9821b32795dace34bd0197ed47a592d4` Source locator `/tasks/overall/openai~1gpt-5.5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate structured finance securitization](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__structured_finance_securitization.md) | 76.51% | SE ±2.39 pp | 36 / 49 | $7.61 | 794.39source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 76.508 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.609913 \| USD \| per_test \| Lower is better \| \| `latency` \| 794.386 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.39 pp sourcePopulation 81 stderr 2.392 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__structured_finance_securitization/openai~1gpt-5.5` | | | | | | | | | [Kangaroo 2025 7-8](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_7-8.md) | 95.83% | 95% CI 92.25–99.41% | 2 / 15 | 0.12usd per problem | — | [matharena · kangaroo--kangaroo_2025_7-8](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_7-8) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.83 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.12 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_7-8 predicted false Reasoning effort xhigh sourceModelName GPT-5.5 (xhigh) sourceModelVersion openai/gpt-55 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 92.25–99.41% confidenceInterval95 3.58 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_7-8) Source matharena Original model label GPT-5.5 (xhigh) Source version kangaroo--kangaroo_2025_7-8 Observed 2026-10-21T16:52:33.033Z Evidence SHA-256 `197887eb5244aa6bce3570bd9eb25bbb0bb6ec95568339536d94e2859f0ee8c1` Source locator `/table/rows/3` | | | | | | | | | [Finance Agent (v2) / financial modeling](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Afinancial_modeling.md) | 22.93% | SE ±2.11 pp | 22 / 50 | $3.18 | 592.86source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 22.93 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.178322 \| USD \| per_test \| Lower is better \| \| `latency` \| 592.855 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.11 pp sourcePopulation 80 stderr 2.11 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label openai/gpt-5.5 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/financial_modeling/openai~1gpt-5.5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / funds asset management](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Afunds_asset_management.md) | 0% | SE ±0 pp | 11 / 49 | $5.02 | 1,206.37source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.020577 \| USD \| per_test \| Lower is better \| \| `latency` \| 1206.37 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/funds_asset_management/openai~1gpt-5.5` | | | | | | | | | [Code Migration / code quality](https://benchize.com/benchmarks/vals-ai%3Acode-migration%3Acode_quality.md) | 3.5% | SE ±0.05 pp | 30 / 47 | $6.44 | 1,894.95source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_code_migration.Dttzoqk3.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 3.498 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.442253 \| USD \| per_test \| Lower is better \| \| `latency` \| 1894.953 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.05 pp sourcePopulation 79 stderr 0.048 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_code_migration.Dttzoqk3.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:12.712Z Evidence SHA-256 `99194597f2c76c402195be47839409046e18bd30454616da6dd40b736a088fa4` Source locator `/tasks/code_quality/openai~1gpt-5.5` | | | | | | | | | [Earthborne Rangers (EBR-bench)](https://benchize.com/benchmarks/epoch-ai%3Aebr_bench.md) | 34.29% | SE ±1.98 pp | 11 / 13 | — | — | [epoch ai · EBR-bench](https://epoch.ai/data/benchmark_data.zip#file=ebr_bench.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.3428571428571428 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.3428571428571428 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion EBR-bench reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion gpt-5.5_xhigh ### Reported statistics Uncertainty Standard error: ±1.98 pp standardError 0.01982539047110602 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=ebr_bench.csv) Source epoch ai Original model label gpt-5.5 Source version EBR-bench Evaluated 2026-07-27T13:22:32.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `15ec96ff8e424623e6a7452956d849312f595f2b5cb4ebe70ec47831f9087b44` Source locator `/rows/12` | | | | | | | | | [Mystery Game Puzzles](https://benchize.com/benchmarks/epoch-ai%3Amystery_game_puzzles.md) | 56% | SE ±4.99 pp | 9 / 71 | — | — | [epoch ai · Mystery Game Puzzles](https://epoch.ai/data/benchmark_data.zip#file=mystery_game_puzzles.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.56 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.56 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion Mystery Game Puzzles reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion gpt-5.5_xhigh ### Reported statistics Uncertainty Standard error: ±4.99 pp standardError 0.049888765156985884 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=mystery_game_puzzles.csv) Source epoch ai Original model label gpt-5.5 Source version Mystery Game Puzzles Evaluated 2026-07-24T18:19:51.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `795b977bc82c460a5e2c1d6dd7b2569ddb21853f3829c4f6fdd16edfaf47bfcf` Source locator `/rows/138` | | | | | | | | [Next page](https://benchize.com/models/gpt-5-5-xhigh.md?cursor=6576cf05dda1f01f023bc5f2fe329b68ae27550dc877d6614445d17556ebabfe) --- Cite as: GPT-5.5Extra high — Benchize, https://benchize.com/models/gpt-5-5-xhigh (retrieved 2026-10-21)