# GPT-6 AstraMax

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-6-astra-max. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-6-astra-max.

OpenAI

Canonical URL: https://benchize.com/models/gpt-6-astra-max
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 |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [Finance Agent (v2) / disclosure analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Adisclosure_analysis.md) | 61.68% | SE ±6.66 pp | 27 / 50 | $8.14 | 799.92source 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` \| 61.684 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.137573 \| USD \| per_test \| Lower is better \| \| `latency` \| 799.918 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.66 pp sourcePopulation 80 stderr 6.657 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-6-astra Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/disclosure_analysis/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,475.5 | — | 30 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1475.5015810971474 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1469.3515955729 rank 34 upper 1481.651566621395 variance 9.84582256738082 votes 13293 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/33/row` |  |  |  |  |  |  |  |
| [Vibe Code Bench v1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Avibe-code%3Aoverall.md) | 89.59% | SE ±2.17 pp | 7 / 59 | $38.51 | 2,344.13source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_vibe_code_bench.DcEBMbCA.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.594 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 38.512323 \| USD \| per_test \| Lower is better \| \| `latency` \| 2344.127 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness OpenHands maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.17 pp sourcePopulation 116 stderr 2.174 tokenTotals {"cache_read_tokens":762745769,"cache_write_tokens":null,"input_tokens":813962842,"output_tokens":7672087,"reasoning_tokens":3013580} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vibe_code_bench.DcEBMbCA.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.1 Observed 2026-10-21T16:46:08.625Z Evidence SHA-256 `0e8c23f521a0f751c5592952620e197b376cade41c78578461b7aa5740a173e7` Source locator `/tasks/overall/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [SWE-bench Multimodal / prism](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Aprism.md) | 47.37% | SE ±8.21 pp | 8 / 14 | — | — | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.368 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.21 pp sourcePopulation 20 stderr 8.209 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/prism/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / corporate governance](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acorporate_governance.md) | 0% | SE ±0 pp | 11 / 49 | $33.1 | 1,583.51source 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` \| 33.095665 \| USD \| per_test \| Lower is better \| \| `latency` \| 1583.514 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max 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-6-astra Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/corporate_governance/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [EMB v1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Aoverall.md) | 72.68% | SE ±2.3 pp | 6 / 19 | $5.83 | 804.28source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 72.683 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.827063 \| USD \| per_test \| Lower is better \| \| `latency` \| 804.28 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.3 pp sourcePopulation 30 stderr 2.297 tokenTotals {"cache_read_tokens":104449111,"cache_write_tokens":null,"input_tokens":123989946,"output_tokens":5542631,"reasoning_tokens":3051513} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/overall/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Legal Research Bench / weighted pass business commercial](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__business_commercial.md) | 83.82% | SE ±3 pp | 31 / 50 | $10.62 | 1,735.65source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.821 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.624987 \| USD \| per_test \| Lower is better \| \| `latency` \| 1735.645 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3 pp sourcePopulation 82 stderr 3.003 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-6-astra Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__business_commercial/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Finance Agent v2.1 / market analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Amarket_analysis.md) | 64.22% | SE ±6.74 pp | 8 / 18 | $5.05 | 836.6source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 64.22 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.051776 \| USD \| per_test \| Lower is better \| \| `latency` \| 836.603 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.74 pp sourcePopulation 28 stderr 6.743 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) Source Vals AI Original model label openai/gpt-6-astra Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/market_analysis/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Terminal-Bench 4.0 / operations](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Aoperations.md) | 48.15% | SE ±9.8 pp | 3 / 36 | — | — | [Vals AI · 4.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.148 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±9.8 pp sourcePopulation 52 stderr 9.799 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) Source Vals AI Original model label openai/gpt-6-astra Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/operations/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) | 1,485.65 | — | 26 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1485.6487996676049 \| rating \| reported \| Higher is better \| ### Configuration category english config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1477.0292023270213 rank 29 upper 1494.2683970081885 variance 19.340948785797703 votes 5372 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1665/row` |  |  |  |  |  |  |  |
| [Finance Agent (v2) / precedents](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Aprecedents.md) | 30.29% | SE ±6.4 pp | 15 / 50 | $11.36 | 1,034.65source 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` \| 30.289 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 11.362177 \| USD \| per_test \| Lower is better \| \| `latency` \| 1034.651 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.4 pp sourcePopulation 80 stderr 6.403 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-6-astra Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/precedents/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [HLAB-Vals-1.1 / antitrust competition](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aantitrust_competition.md) | 10% | SE ±10 pp | 4 / 14 | $28.28 | 1,978.79source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 10 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 28.281218 \| USD \| per_test \| Lower is better \| \| `latency` \| 1978.794 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±10 pp sourcePopulation 24 stderr 10 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/antitrust_competition/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Tax Agent Bench / weighted pass forms filings](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__forms_filings.md) | 60.76% | SE ±8.09 pp | 18 / 46 | $8.33 | 1,243.96source 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` \| 60.759 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.333408 \| USD \| per_test \| Lower is better \| \| `latency` \| 1243.963 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.09 pp sourcePopulation 73 stderr 8.09 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-6-astra Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/weighted_pass__forms_filings/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Vibe Code Bench 1-100 / overall](https://benchize.com/benchmarks/vals-ai%3Avcb-1-100%3Aoverall.md) | 27.64% | SE ±4.08 pp | 4 / 16 | $84.72 | 12,339.63source duration | [Vals AI · 1.0](https://www.vals.ai/_astro/benchmark_view_vcb_1_100.ZqWqHxGl.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 27.644 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 84.720155 \| USD \| per_test \| Lower is better \| \| `latency` \| 12339.625 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness OpenHands maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.08 pp sourcePopulation 25 stderr 4.082 tokenTotals {"cache_read_tokens":1709079929,"cache_write_tokens":222772860,"input_tokens":1931929247,"output_tokens":47592637,"reasoning_tokens":27157780} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vcb_1_100.ZqWqHxGl.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.0 Observed 2026-10-21T16:46:09.131Z Evidence SHA-256 `4a3ebdcd9364ec3a21193d00de0bf723384d85187244abff859527fd3cc51891` Source locator `/tasks/overall/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [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) | 90.71% | SE ±1.65 pp | 24 / 49 | $28.64 | 1,816.78source 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` \| 90.705 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 28.643676 \| USD \| per_test \| Lower is better \| \| `latency` \| 1816.776 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.65 pp sourcePopulation 81 stderr 1.646 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-6-astra Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__corporate_ma/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / antitrust competition](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aantitrust_competition.md) | 0% | SE ±0 pp | 7 / 49 | $24.98 | 1,474.89source 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` \| 24.979276 \| USD \| per_test \| Lower is better \| \| `latency` \| 1474.888 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max 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-6-astra Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/antitrust_competition/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [MedCode / overall](https://benchize.com/benchmarks/vals-ai%3Amedcode%3Aoverall.md) | 48.49% | SE ±2.13 pp | 19 / 49 | $0.45 | 102.87source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medcode.DehpEDgG.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.486 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.451358 \| USD \| per_test \| Lower is better \| \| `latency` \| 102.865 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.13 pp sourcePopulation 107 stderr 2.131 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medcode.DehpEDgG.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1 Observed 2026-10-21T16:45:59.516Z Evidence SHA-256 `988a6ae1e07e33ce031572ed4a804be11c36ee97a1dd75cbe4740fff3b534f8c` Source locator `/tasks/overall/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Arena text / polish](https://benchize.com/benchmarks/lmarena%3Atext%3Apolish.md) | 1,422.27 | — | 55 / 117 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1422.2719053266462 \| rating \| reported \| Higher is better \| ### Configuration category polish config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1380.1889479688477 rank 97 upper 1464.3548626844447 variance 461.01634369681494 votes 184 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10244/row` |  |  |  |  |  |  |  |
| [Finance Agent v2.1 / financial modeling](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Afinancial_modeling.md) | 45.02% | SE ±6.8 pp | 7 / 18 | $5.91 | 998.95source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 45.024 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.911616 \| USD \| per_test \| Lower is better \| \| `latency` \| 998.948 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.8 pp sourcePopulation 28 stderr 6.798 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) Source Vals AI Original model label openai/gpt-6-astra Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/financial_modeling/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,464.18 | — | 39 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1464.1761679158026 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1453.3765287597898 rank 53 upper 1474.9758070718153 variance 30.361435939852623 votes 3256 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3920/row` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / criteria pass rate energy natural resources](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__energy_natural_resources.md) | 92.41% | SE ±1.52 pp | 27 / 49 | $50.66 | 1,943.2source 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` \| 92.409 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 50.660049 \| USD \| per_test \| Lower is better \| \| `latency` \| 1943.202 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.52 pp sourcePopulation 81 stderr 1.524 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-6-astra Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__energy_natural_resources/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Arena vision / ocr (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aocr--config-vision.md) | 1,291.92 | — | 29 / 74 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1291.9232352489832 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision Reasoning effort max thinkingEnabled true ### Reported statistics lower 1280.140837233899 rank 32 upper 1303.7056332640677 variance 36.13858939161558 votes 2740 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/1050/row` |  |  |  |  |  |  |  |
| [Arena text style control / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexclude_ties.md) | 1,487.59 | — | 26 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1487.5872796935753 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1479.5218870237404 rank 29 upper 1495.6526723634101 variance 16.933816540787618 votes 9806 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2082/row` |  |  |  |  |  |  |  |
| [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 64.48% | — | 4 / 125 | $3.93 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.6448 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.7063 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 3.9329 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort max sourceVersion v1_1 subset extended ### Reported statistics flaggedRate 0 sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GPT-6 Astra Observed 2026-10-21T16:31:00.878Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/GPT-6%20Astra/max/extended` |  |  |  |  |  |  |  |
| [HLAB-Vals-1.1 / criteria pass rate trusts estates private client](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__trusts_estates_private_client.md) | 93.89% | SE ±1.48 pp | 7 / 14 | $23.7 | 1,899.11source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 93.893 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 23.695343 \| USD \| per_test \| Lower is better \| \| `latency` \| 1899.114 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.48 pp sourcePopulation 24 stderr 1.482 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__trusts_estates_private_client/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [CUA-bench / minecraft nether](https://benchize.com/benchmarks/vals-ai%3Acua_bench%3Aminecraft_nether.md) | 30% | SE ±0 pp | 1 / 8 | $162.3 | 42.02source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_cua_bench.DpgrKYWA.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 30 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 162.301085 \| USD \| per_test \| Lower is better \| \| `latency` \| 42.02 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness codex maxOutputTokens 128000 provider openai reasoning true Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 9 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_cua_bench.DpgrKYWA.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1 Observed 2026-10-21T16:46:16.228Z Evidence SHA-256 `8c415c63f28cd80496a4ccca27d1062ec98bb55268e58cba105b8cf2d7ee53d3` Source locator `/tasks/minecraft_nether/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [EMB / scratch](https://benchize.com/benchmarks/vals-ai%3Aemb%3Ascratch.md) | 69.09% | SE ±2.83 pp | 8 / 47 | $5.89 | 887.07source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.085 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.886751 \| USD \| per_test \| Lower is better \| \| `latency` \| 887.067 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.83 pp sourcePopulation 76 stderr 2.834 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/scratch/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [CUA-bench / held out sandbox](https://benchize.com/benchmarks/vals-ai%3Acua_bench%3Aheld_out_sandbox.md) | 15% | SE ±0 pp | 2 / 8 | $454.59 | 30.86source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_cua_bench.DpgrKYWA.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 15 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 454.590025 \| USD \| per_test \| Lower is better \| \| `latency` \| 30.86 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness codex maxOutputTokens 128000 provider openai reasoning true Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 9 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_cua_bench.DpgrKYWA.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1 Observed 2026-10-21T16:46:16.228Z Evidence SHA-256 `8c415c63f28cd80496a4ccca27d1062ec98bb55268e58cba105b8cf2d7ee53d3` Source locator `/tasks/held_out_sandbox/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Terminal-Bench Science 0.1](https://benchize.com/benchmarks/terminal-science%3Av0-1-eval%3Aoverall.md) | 68.1% | SE ±3.22 pp | 1 / 9 | $4,997.46 | — | [terminal science](https://www.terminal-bench-science.ai/api/leaderboard?package=terminal-bench-science%2Fterminal-bench-science&name=v0-1-eval) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.0952380952381 \| percent \| reported \| Higher is better \| \| `total_cost` \| 4997.461181 \| USD \| all_trials \| Lower is better \| \| `total_tokens` \| 2288326796 \| tokens \| all_trials \| Lower is better \| ### Configuration agent Codex benchmarkVersion v0-1-eval domain overall Reasoning effort max ### Reported statistics Uncertainty Standard error: ±3.22 pp accuracyStandardError 3.2164475807033743 passes 143 rank 1 tasks 210 ### Source [Original source](https://www.terminal-bench-science.ai/api/leaderboard?package=terminal-bench-science%2Fterminal-bench-science&name=v0-1-eval) Source terminal science Original model label GPT-6 Astra Evaluated 2026-09-22T11:46:04.426644+00:00 Observed 2026-10-21T16:32:46.684Z Evidence SHA-256 `86e6278ca64da88b69c1efd6059a33248bd300f27673098f60184286b470c4a7` Source locator `/rows/0/metrics` |  |  |  |  |  |  |  |
| [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md) | 1,439.46 | — | 42 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1439.4635440534255 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1426.884811430719 rank 56 upper 1452.0422766761317 variance 41.18865300369081 votes 2328 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4338/row` |  |  |  |  |  |  |  |
| [Code Migration / code quality](https://benchize.com/benchmarks/vals-ai%3Acode-migration%3Acode_quality.md) | 4.47% | SE ±0.03 pp | 10 / 47 | $44.36 | 3,510source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_code_migration.Dttzoqk3.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 4.469 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 44.364548 \| USD \| per_test \| Lower is better \| \| `latency` \| 3510.003 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.03 pp sourcePopulation 79 stderr 0.033 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-6-astra Source version 1 Observed 2026-10-21T16:46:12.712Z Evidence SHA-256 `99194597f2c76c402195be47839409046e18bd30454616da6dd40b736a088fa4` Source locator `/tasks/code_quality/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [HLAB-Vals-1.1 / criteria pass rate data privacy cybersecurity](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__data_privacy_cybersecurity.md) | 95.76% | SE ±1.2 pp | 11 / 14 | $32.1 | 2,134.04source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.76 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 32.097478 \| USD \| per_test \| Lower is better \| \| `latency` \| 2134.04 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.2 pp sourcePopulation 24 stderr 1.2 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__data_privacy_cybersecurity/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [EMB / lbo](https://benchize.com/benchmarks/vals-ai%3Aemb%3Albo.md) | 61.83% | SE ±6.09 pp | 9 / 47 | $5.72 | 818.98source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 61.825 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.720048 \| USD \| per_test \| Lower is better \| \| `latency` \| 818.984 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.09 pp sourcePopulation 76 stderr 6.088 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,500elo | — | 1 / 110 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1500 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported Reasoning effort max sourceModelVersion gpt-6-astra-max thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 1155455 battles 256 losses 65 standardError Not reported winRate 74.6 wins 191 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label GPT-6 Astra (max) Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/0` |  |  |  |  |  |  |  |
| [Arena text / creative writing](https://benchize.com/benchmarks/lmarena%3Atext%3Acreative_writing.md) | 1,419.8 | — | 44 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1419.8031388305878 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1408.0089627337527 rank 69 upper 1431.5973149274228 variance 36.210876205102586 votes 2966 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1290/row` |  |  |  |  |  |  |  |
| [IOI / ioi2025](https://benchize.com/benchmarks/vals-ai%3Aioi%3Aioi2025.md) | 100% | SE ±0 pp | 1 / 29 | $5.11 | 1,562.49source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.113398 \| USD \| per_test \| Lower is better \| \| `latency` \| 1562.492 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 44 stderr 0 tokenTotals {"cache_read_tokens":1910090,"cache_write_tokens":180790,"input_tokens":2091102,"output_tokens":70089,"reasoning_tokens":38414} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label openai/gpt-6-astra Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / energy natural resources](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aenergy_natural_resources.md) | 0% | SE ±0 pp | 28 / 49 | $50.66 | 1,943.2source 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` \| 50.660049 \| USD \| per_test \| Lower is better \| \| `latency` \| 1943.202 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max 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-6-astra Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/energy_natural_resources/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Arena vision style control / creative writing vision](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Acreative_writing_vision.md) | 1,294.27 | — | 10 / 70 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1294.2668980734213 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing_vision config vision_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1263.235998527231 rank 11 upper 1325.2977976196114 variance 250.66433654279044 votes 408 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/373/row` |  |  |  |  |  |  |  |
| [Finance Agent v2.1 / general qualitative analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Ageneral_qualitative_analysis.md) | 61.91% | SE ±5.97 pp | 17 / 18 | $10.02 | 1,895.77source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 61.906 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.016985 \| USD \| per_test \| Lower is better \| \| `latency` \| 1895.772 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.97 pp sourcePopulation 28 stderr 5.968 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) Source Vals AI Original model label openai/gpt-6-astra Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/general_qualitative_analysis/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Terminal-Bench 4.0 / software](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Asoftware.md) | 61.11% | SE ±3.21 pp | 1 / 36 | — | — | [Vals AI · 4.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 61.111 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.21 pp sourcePopulation 52 stderr 3.208 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) Source Vals AI Original model label openai/gpt-6-astra Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/software/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) | 1,446.72 | — | 51 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1446.721417918345 \| rating \| reported \| Higher is better \| ### Configuration category english config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1438.1167971532054 rank 81 upper 1455.3260386834845 variance 19.27379726499119 votes 5372 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1717/row` |  |  |  |  |  |  |  |
| [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 2,169.2 | Range 2,131.2–2,210.3 | 21 / 126 | — | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 2169.2 \| rating \| reported \| Higher is better \| \| `overall` \| 82.32 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 80.37 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 79.9 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 83.43 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 82.14 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 98.29 \| source_score \| rubric \| Higher is better \| \| `slop` \| 88.59 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 96.8 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 87.54 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 77.78 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 78.36 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 76.63 \| source_score \| rubric \| Higher is better \| ### Configuration provider codex Reasoning effort max scoreScope 10_task_current sourceConfiguration gpt-6-astra-max thinkingEnabled true ### Reported statistics Uncertainty Reported interval: 2,131.2–2,210.3 interval [2131.2,2210.3] rank 21 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label GPT-6 Astra (max) Evaluated 2026-10-11 Observed 2026-10-21T16:32:48.862Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/20` |  |  |  |  |  |  |  |
| [Finance Agent (v2) / comparables](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Acomparables.md) | 37.76% | SE ±6.31 pp | 40 / 50 | $9.44 | 1,015.4source 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` \| 37.758 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 9.441278 \| USD \| per_test \| Lower is better \| \| `latency` \| 1015.396 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.31 pp sourcePopulation 80 stderr 6.312 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-6-astra Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/comparables/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / criteria pass rate funds asset management](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__funds_asset_management.md) | 83.67% | SE ±2 pp | 17 / 49 | $35.06 | 1,928.17source 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` \| 83.673 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 35.059835 \| USD \| per_test \| Lower is better \| \| `latency` \| 1928.168 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2 pp sourcePopulation 81 stderr 1.999 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-6-astra Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__funds_asset_management/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [SWE-bench Multimodal / bpmn js](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Abpmn_js.md) | 62.26% | SE ±6.72 pp | 8 / 14 | — | — | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 62.264 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.72 pp sourcePopulation 20 stderr 6.722 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/bpmn_js/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Legal Research Bench / weighted pass civil litigation](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__civil_litigation.md) | 88.67% | SE ±2.51 pp | 16 / 50 | $13.74 | 1,743.79source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.669 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 13.735474 \| USD \| per_test \| Lower is better \| \| `latency` \| 1743.79 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.51 pp sourcePopulation 82 stderr 2.508 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-6-astra Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__civil_litigation/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Earthborne Rangers (EBR-bench)](https://benchize.com/benchmarks/epoch-ai%3Aebr_bench.md) | 76.19% | SE ±8.38 pp | 1 / 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` \| 0.7619047619047619 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.7619047619047619 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion EBR-bench reasoningBudget Not reported Reasoning effort max sourceModelVersion gpt-6-astra_max ### Reported statistics Uncertainty Standard error: ±8.38 pp standardError 0.08384198505551908 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=ebr_bench.csv) Source epoch ai Original model label gpt-6-astra Source version EBR-bench Evaluated 2026-08-30T15:38:49.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `15ec96ff8e424623e6a7452956d849312f595f2b5cb4ebe70ec47831f9087b44` Source locator `/rows/9` |  |  |  |  |  |  |  |
| [Legal Research Bench / weighted pass family](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__family.md) | 77.31% | SE ±4 pp | 12 / 50 | $15 | 1,896.18source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 77.307 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 15.003346 \| USD \| per_test \| Lower is better \| \| `latency` \| 1896.183 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4 pp sourcePopulation 82 stderr 3.995 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-6-astra Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__family/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [ProofBench v1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Aproof_bench%3Aoverall.md) | 99% | SE ±1 pp | 4 / 34 | $1.71 | 307.87source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_proof_bench.i3Hwh8rW.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 99 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.71238 \| USD \| per_test \| Lower is better \| \| `latency` \| 307.867 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1 pp sourcePopulation 52 stderr 1 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_proof_bench.i3Hwh8rW.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.1 Observed 2026-10-21T16:46:01.401Z Evidence SHA-256 `22be2aca25de5c4a9eb6448a95713e09a7c97126dfc6f4f75c4afd0e563209cb` Source locator `/tasks/overall/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Finance Agent (v2) / general qualitative analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Ageneral_qualitative_analysis.md) | 68.43% | SE ±5.69 pp | 13 / 50 | $9.77 | 1,070.1source 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` \| 68.425 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 9.77377 \| USD \| per_test \| Lower is better \| \| `latency` \| 1070.103 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.69 pp sourcePopulation 80 stderr 5.687 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-6-astra Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/general_qualitative_analysis/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) | 1,404.56 | — | 44 / 120 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1404.5615216441001 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1364.5080081232513 rank 73 upper 1444.6150351649492 variance 417.62362171435365 votes 248 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8023/row` |  |  |  |  |  |  |  |
| [EMB / overall](https://benchize.com/benchmarks/vals-ai%3Aemb%3Aoverall.md) | 71.7% | SE ±2.48 pp | 9 / 47 | $5.83 | 804.28source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 71.7 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.827063 \| USD \| per_test \| Lower is better \| \| `latency` \| 804.28 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.48 pp sourcePopulation 76 stderr 2.475 tokenTotals {"cache_read_tokens":104449111,"cache_write_tokens":null,"input_tokens":123989946,"output_tokens":5542631,"reasoning_tokens":3051513} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/overall/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [DeepSWE](https://benchize.com/benchmarks/deepswe%3Av1.1.md) | 73.23% | Range 72.4–74.06% | 4 / 70 | $7.5 | 1,982.97s | [deepswe](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_at_1` \| 0.7323008849557522 \| score_fraction \| scored_rollout_attempts \| Higher is better \| \| `pass_at_4` \| 0.7964601769911505 \| score_fraction \| tasks_with_one_passing_rollout \| Higher is better \| \| `cost_per_attempt` \| 7.497827996681416 \| USD \| scored_attempt \| Lower is better \| \| `duration` \| 1982.966814159292 \| seconds \| scored_attempt \| Lower is better \| ### Configuration harness mini-swe-agent Reasoning effort max sourceConfiguration mini_swe_agent_gpt_6_astra_max ### Reported statistics Uncertainty Reported interval: 72.4–74.06% interval [0.7239976873936956,0.7406040825178087] intervalMethod 95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R)) runCount 4 sampleSize 452 taskCount 113 ### Source [Original source](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) Source deepswe Original model label gpt-6-astra Observed 2026-10-21T16:30:23.371Z Evidence SHA-256 `a7c15d66288fd249c020b9931c017b92d1a3b90e480b3ff34974b752bd030019` Source locator `/rows/4` |  |  |  |  |  |  |  |
| [Arena vision / diagram (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Adiagram--config-vision.md) | 1,297.25 | — | 32 / 74 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1297.2542545036872 \| rating \| reported \| Higher is better \| ### Configuration category diagram config vision Reasoning effort max thinkingEnabled true ### Reported statistics lower 1277.7934024184044 rank 36 upper 1316.7151065889702 variance 98.58878659457396 votes 966 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/502/row` |  |  |  |  |  |  |  |
| [Terminal-Bench 4.0 / overall](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Aoverall.md) | 59.6% | SE ±4.4 pp | 3 / 36 | $9.58 | 2,142.08source duration | [Vals AI · 4.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.596 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 9.584259 \| USD \| per_test \| Lower is better \| \| `latency` \| 2142.082 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.4 pp sourcePopulation 52 stderr 4.403 tokenTotals {"cache_read_tokens":184898940,"cache_write_tokens":8367663,"input_tokens":193308076,"output_tokens":5366501,"reasoning_tokens":3845988} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) Source Vals AI Original model label openai/gpt-6-astra Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/overall/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Vals Index / code migration](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Acode_migration.md) | 78.03% | SE ±3.13 pp | 3 / 14 | $66.64 | 5,286.5source duration | [Vals AI · 2.2](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 78.031 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 66.641779 \| USD \| per_test \| Lower is better \| \| `latency` \| 5286.504 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.13 pp sourcePopulation 23 stderr 3.128 tokenTotals {"cache_read_tokens":1791878139,"cache_write_tokens":36294376,"input_tokens":1828192015,"output_tokens":12132196,"reasoning_tokens":4524551} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label openai/gpt-6-astra Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/code_migration/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [CUA-bench / held out sports](https://benchize.com/benchmarks/vals-ai%3Acua_bench%3Aheld_out_sports.md) | 0% | SE ±0 pp | 1 / 8 | $54.02 | 32.74source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_cua_bench.DpgrKYWA.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 54.021346 \| USD \| per_test \| Lower is better \| \| `latency` \| 32.74 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness codex maxOutputTokens 128000 provider openai reasoning true Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 9 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_cua_bench.DpgrKYWA.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1 Observed 2026-10-21T16:46:16.228Z Evidence SHA-256 `8c415c63f28cd80496a4ccca27d1062ec98bb55268e58cba105b8cf2d7ee53d3` Source locator `/tasks/held_out_sports/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Arena text / expert](https://benchize.com/benchmarks/lmarena%3Atext%3Aexpert.md) | 1,489.45 | — | 31 / 148 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1489.4450070463686 \| rating \| reported \| Higher is better \| ### Configuration category expert config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1472.9238682269513 rank 37 upper 1505.9661458657858 variance 71.05322239042904 votes 1279 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2507/row` |  |  |  |  |  |  |  |
| [EMB v1.1 / operating](https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Aoperating.md) | 75.51% | SE ±4.35 pp | 2 / 19 | $3.62 | 590.97source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.505 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.61903 \| USD \| per_test \| Lower is better \| \| `latency` \| 590.973 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.35 pp sourcePopulation 30 stderr 4.345 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/operating/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) | 1,450.59 | — | 17 / 124 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1450.586677568088 \| rating \| reported \| Higher is better \| ### Configuration category korean config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1411.2484322354208 rank 21 upper 1489.9249229007555 variance 402.84111273474446 votes 230 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8254/row` |  |  |  |  |  |  |  |
| [Terminal-Bench-Science / mathematical sciences](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-science%3Amathematical_sciences.md) | 88.24% | SE ±8.06 pp | 1 / 30 | — | — | [Vals AI · 0.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_science.o-HR8Nyt.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.235 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Mini-SWE-agent maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.06 pp sourcePopulation 41 stderr 8.055 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_science.o-HR8Nyt.json) Source Vals AI Original model label openai/gpt-6-astra Source version 0.1 Observed 2026-10-21T16:46:03.529Z Evidence SHA-256 `a30a8618deaecf018ea1c8c9f675576cdd9ab79742d05788067db49afcc5f91b` Source locator `/tasks/mathematical_sciences/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [HLAB-Vals-1.1 / international trade sanctions](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Ainternational_trade_sanctions.md) | 0% | SE ±0 pp | 5 / 14 | $12.01 | 1,668.72source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 12.013329 \| USD \| per_test \| Lower is better \| \| `latency` \| 1668.724 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 24 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/international_trade_sanctions/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [HLAB-Vals-1.1 / criteria pass rate intellectual property](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__intellectual_property.md) | 94.48% | SE ±1.36 pp | 9 / 14 | $19.56 | 1,837.1source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 94.484 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 19.556639 \| USD \| per_test \| Lower is better \| \| `latency` \| 1837.104 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.36 pp sourcePopulation 24 stderr 1.364 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__intellectual_property/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Arena webdev / webdev](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev.md) | 1,773.78 | — | 2 / 90 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1773.7830236243688 \| rating \| reported \| Higher is better \| ### Configuration category webdev config webdev Reasoning effort max thinkingEnabled true ### Reported statistics lower 1763.6123562538887 rank 2 upper 1783.9536909948486 variance 26.927914521351674 votes 6169 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/213/row` |  |  |  |  |  |  |  |
| [HLAB-Vals-1.1 / capital markets](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acapital_markets.md) | 20% | SE ±20 pp | 5 / 14 | $20.14 | 1,505.51source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 20.140295 \| USD \| per_test \| Lower is better \| \| `latency` \| 1505.512 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 24 stderr 20 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/capital_markets/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Time Horizon Index: KSP / overall](https://benchize.com/benchmarks/vals-ai%3Atime_horizon_index%3Aoverall.md) | 90.5% | SE ±0 pp | 2 / 10 | $4,206.59 | 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` \| 90.5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4206.58511 \| 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 max 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-6-astra Source version 1 Observed 2026-10-21T16:46:16.730Z Evidence SHA-256 `be251b72ecceae7912b9577f9b3a3512740c308a34f81ac823952e919adae50f` Source locator `/tasks/overall/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [HLAB-Vals-1.1 / criteria pass rate environmental esg](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__environmental_esg.md) | 89.61% | SE ±1.83 pp | 7 / 14 | $17.92 | 1,976.58source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.606 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 17.922383 \| USD \| per_test \| Lower is better \| \| `latency` \| 1976.582 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.83 pp sourcePopulation 24 stderr 1.83 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__environmental_esg/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [SAGE / overall](https://benchize.com/benchmarks/vals-ai%3Asage%3Aoverall.md) | 46.37% | SE ±3.44 pp | 26 / 41 | $0.28 | 41.63source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 46.367 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.282823 \| USD \| per_test \| Lower is better \| \| `latency` \| 41.629 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.44 pp sourcePopulation 91 stderr 3.444 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/overall/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / bankruptcy restructuring](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Abankruptcy_restructuring.md) | 0% | SE ±0 pp | 3 / 49 | $37.67 | 1,593.86source 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` \| 37.668899 \| USD \| per_test \| Lower is better \| \| `latency` \| 1593.86 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max 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-6-astra Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/bankruptcy_restructuring/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [BrokenArXiv 05/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--may.md) | 91% | 95% CI 85.39–96.61% | 2 / 20 | 0.7usd per problem | — | [matharena · arxiv_false--may](https://matharena.ai/competition_tables/arxiv_false--may) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.00 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.70 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--may predicted false Reasoning effort max sourceModelName GPT-6 Astra (max) sourceModelVersion openai/gpt-6-astra thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 85.39–96.61% confidenceInterval95 5.61 problems 50 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--may) Source matharena Original model label GPT-6 Astra (max) Source version arxiv_false--may Observed 2026-10-21T16:52:24.785Z Evidence SHA-256 `b317fca30109e8c78ed5d2b835fe227b8cfbee3b6f9cb6d7aaeadca866660969` Source locator `/table/rows/1` |  |  |  |  |  |  |  |
| [SAGE / linear algebra](https://benchize.com/benchmarks/vals-ai%3Asage%3Alinear_algebra.md) | 62.12% | SE ±5.5 pp | 30 / 41 | $0.35 | 29.31source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 62.117 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.3535 \| USD \| per_test \| Lower is better \| \| `latency` \| 29.309 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.5 pp sourcePopulation 91 stderr 5.495 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/linear_algebra/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / intellectual property](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aintellectual_property.md) | 0% | SE ±0 pp | 6 / 49 | $20.1 | 1,399.04source 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` \| 20.104733 \| USD \| per_test \| Lower is better \| \| `latency` \| 1399.04 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max 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-6-astra Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/intellectual_property/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [SWE-bench Multimodal / scratch gui](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Ascratch_gui.md) | 16.67% | SE ±16.67 pp | 6 / 14 | — | — | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 16.667 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±16.67 pp sourcePopulation 20 stderr 16.667 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/scratch_gui/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [FrontierMath Tiers 1–3 v2 (private)](https://benchize.com/benchmarks/epoch-ai%3Afrontiermath_tiers_1_3_v2.md) | 93.68% | SE ±1.44 pp | 1 / 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` \| 0.9368421052631579 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.9368421052631579 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tiers-1-3-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion gpt-6-astra_max ### Reported statistics Uncertainty Standard error: ±1.44 pp standardError 0.014434038295343787 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tiers_1_3_v2.csv) Source epoch ai Original model label gpt-6-astra Source version FrontierMath-Tiers-1-3-v2-Private Evaluated 2026-08-30T14:57:43.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `6e31ece7503f8f89dffe8af33010ed7d1d6f0aa3a80cff14fa79f9b34a7b258f` Source locator `/rows/23` |  |  |  |  |  |  |  |
| [Legal Research Bench / weighted pass immigration](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__immigration.md) | 84.35% | SE ±5.89 pp | 5 / 50 | $14.72 | 2,079.5source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.347 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 14.716249 \| USD \| per_test \| Lower is better \| \| `latency` \| 2079.496 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.89 pp sourcePopulation 82 stderr 5.891 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-6-astra Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__immigration/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Finance Agent (v2) / all pass](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Aall_pass.md) | 40.25% | SE ±2.12 pp | 26 / 50 | $6.82 | 692.67source 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` \| 40.252 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.81746 \| USD \| per_test \| Lower is better \| \| `latency` \| 692.672 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.12 pp sourcePopulation 80 stderr 2.115 tokenTotals {"cache_read_tokens":70591920,"cache_write_tokens":null,"input_tokens":240568066,"output_tokens":22397666,"reasoning_tokens":16813955} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label openai/gpt-6-astra Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/all_pass/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [HLAB-Vals-1.1 / white collar defense investigations](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Awhite_collar_defense_investigations.md) | 0% | SE ±0 pp | 2 / 14 | $17.86 | 1,732.53source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 17.857837 \| USD \| per_test \| Lower is better \| \| `latency` \| 1732.526 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 24 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/white_collar_defense_investigations/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Arena text / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_software_and_it_services.md) | 1,474.17 | — | 39 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1474.1675899746165 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1465.1640419546757 rank 53 upper 1483.1711379945577 variance 21.102367806388102 votes 4750 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6753/row` |  |  |  |  |  |  |  |
| [Arena vision style control / diagram](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Adiagram.md) | 1,309.63 | — | 25 / 74 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1309.6282707464331 \| rating \| reported \| Higher is better \| ### Configuration category diagram config vision_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1290.011741769919 rank 27 upper 1329.2447997229474 variance 100.1724154931563 votes 966 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/493/row` |  |  |  |  |  |  |  |
| [Finance Agent v2.1 / precedents](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Aprecedents.md) | 40.19% | SE ±6.96 pp | 8 / 18 | $12.45 | 1,695.73source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 40.185 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 12.448809 \| USD \| per_test \| Lower is better \| \| `latency` \| 1695.727 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.96 pp sourcePopulation 28 stderr 6.96 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) Source Vals AI Original model label openai/gpt-6-astra Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/precedents/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Finance Agent v2.1 / overall](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Aoverall.md) | 60.43% | SE ±2.12 pp | 13 / 18 | $7.82 | 1,228.75source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 60.428 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.823464 \| USD \| per_test \| Lower is better \| \| `latency` \| 1228.75 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.12 pp sourcePopulation 28 stderr 2.12 tokenTotals {"cache_read_tokens":77618056,"cache_write_tokens":170564517,"input_tokens":248231715,"output_tokens":22170755,"reasoning_tokens":16637610} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) Source Vals AI Original model label openai/gpt-6-astra Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/overall/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [ArXivMath 08/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--august.md) | 88.6% | 95% CI 82.77–94.43% | 3 / 11 | 3.63usd per problem | — | [matharena · arxiv--august](https://matharena.ai/competition_tables/arxiv--august) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.60 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 3.63 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--august predicted false Reasoning effort max sourceModelName GPT-6 Astra (max) sourceModelVersion openai/gpt-6-astra thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 82.77–94.43% confidenceInterval95 5.83 problems 57 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--august) Source matharena Original model label GPT-6 Astra (max) Source version arxiv--august Observed 2026-10-21T16:52:30.283Z Evidence SHA-256 `5924e5ecc15ff087ec1504b1e4ac44408b005c4f70e81e0d2184f930383a963c` Source locator `/table/rows/2` |  |  |  |  |  |  |  |
| [Arena text style control / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_business_and_management_and_financial_operations.md) | 1,474.64 | — | 29 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1474.6384188430359 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1461.9708133590632 rank 34 upper 1487.3060243270088 variance 41.77273171148646 votes 2328 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4316/row` |  |  |  |  |  |  |  |
| [Finance Agent v2.1 / general quantitative analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Ageneral_quantitative_analysis.md) | 79.51% | SE ±5.14 pp | 8 / 18 | $6.74 | 861.2source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.509 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.73805 \| USD \| per_test \| Lower is better \| \| `latency` \| 861.201 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.14 pp sourcePopulation 28 stderr 5.139 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) Source Vals AI Original model label openai/gpt-6-astra Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/general_quantitative_analysis/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / emerging companies venture capital](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aemerging_companies_venture_capital.md) | 0% | SE ±0 pp | 18 / 49 | $20.55 | 1,318.76source 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` \| 20.549812 \| USD \| per_test \| Lower is better \| \| `latency` \| 1318.76 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max 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-6-astra Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/emerging_companies_venture_capital/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Arena text / russian](https://benchize.com/benchmarks/lmarena%3Atext%3Arussian.md) | 1,437.59 | — | 46 / 150 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1437.586097510248 \| rating \| reported \| Higher is better \| ### Configuration category russian config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1423.1024518933734 rank 66 upper 1452.0697431271226 variance 54.60841835011622 votes 1723 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10449/row` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / trusts estates private client](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Atrusts_estates_private_client.md) | 20% | SE ±20 pp | 2 / 49 | $23.65 | 1,477.19source 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` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 23.645844 \| USD \| per_test \| Lower is better \| \| `latency` \| 1477.192 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 81 stderr 20 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-6-astra Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/trusts_estates_private_client/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Terminal-Bench-Science / engineering sciences](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-science%3Aengineering_sciences.md) | 33.33% | SE ±16.67 pp | 3 / 30 | — | — | [Vals AI · 0.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_science.o-HR8Nyt.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Mini-SWE-agent maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±16.67 pp sourcePopulation 41 stderr 16.667 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_science.o-HR8Nyt.json) Source Vals AI Original model label openai/gpt-6-astra Source version 0.1 Observed 2026-10-21T16:46:03.529Z Evidence SHA-256 `a30a8618deaecf018ea1c8c9f675576cdd9ab79742d05788067db49afcc5f91b` Source locator `/tasks/engineering_sciences/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Tax Agent Bench / forms filings](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aforms_filings.md) | 6.67% | SE ±4.63 pp | 32 / 46 | $8.33 | 1,243.96source 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` \| 6.667 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.333408 \| USD \| per_test \| Lower is better \| \| `latency` \| 1243.963 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.63 pp sourcePopulation 73 stderr 4.632 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-6-astra Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/forms_filings/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [HLAB-Vals-1.1 / criteria pass rate banking finance](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__banking_finance.md) | 93.1% | SE ±1.55 pp | 8 / 14 | $26.7 | 1,845.73source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 93.097 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 26.702694 \| USD \| per_test \| Lower is better \| \| `latency` \| 1845.728 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.55 pp sourcePopulation 24 stderr 1.551 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__banking_finance/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [SpireClimb](https://benchize.com/benchmarks/epoch-ai%3Aspireclimb.md) | 25.67% | SE ±3.68 pp | 1 / 7 | — | — | [epoch ai · SpireClimb](https://epoch.ai/data/benchmark_data.zip#file=spireclimb.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.25666666666666665 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.25666666666666665 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion SpireClimb reasoningBudget Not reported Reasoning effort max sourceModelVersion gpt-6-astra_max ### Reported statistics Uncertainty Standard error: ±3.68 pp standardError 0.03679235526872096 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=spireclimb.csv) Source epoch ai Original model label gpt-6-astra Source version SpireClimb Evaluated 2026-09-23T02:12:45.776Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `8bb2bda1fd232b776c132133a46df08f18ceabdc5552e9d61eb5802dc85f4a5e` Source locator `/rows/6` |  |  |  |  |  |  |  |
| [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,491.25 | — | 23 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1491.2500300344818 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1473.4889145569568 rank 25 upper 1509.0111455120066 variance 82.11912133655915 votes 1142 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5132/row` |  |  |  |  |  |  |  |
| [CyberBench v1.1 / poc](https://benchize.com/benchmarks/benchmark%3Acyber%3Apoc.md) | 0% | SE ±0 pp | 25 / 28 | — | 0source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher 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 max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 47 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.1 Observed 2026-10-21T16:46:15.238Z Evidence SHA-256 `943f593f929f8971a6b746269a2851b5febc2aad4e2f1066895f715033cdc7f1` Source locator `/tasks/poc/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Code Migration v1.1 / code quality](https://benchize.com/benchmarks/vals-ai%3Acode-migration-v1-1%3Acode_quality.md) | 3.4% | SE ±0.03 pp | 10 / 17 | $62.07 | 5,221.42source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_code_migration_v1_1.bJHk6HEY.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 3.395 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 62.066613 \| USD \| per_test \| Lower is better \| \| `latency` \| 5221.422 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.03 pp sourcePopulation 26 stderr 0.032 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_code_migration_v1_1.bJHk6HEY.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.1 Observed 2026-10-21T16:46:09.631Z Evidence SHA-256 `352faac603c73f05cc01e89214fb4adcafa05ea7432ea71ea9903a6b5fe36b08` Source locator `/tasks/code_quality/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Arena text style control / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_mathematical.md) | 1,504.67 | — | 17 / 148 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1504.6673883595417 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1483.3002438249214 rank 18 upper 1526.034532894162 variance 118.84934522891903 votes 775 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5930/row` |  |  |  |  |  |  |  |
| [Tax Agent Bench / current temporal analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Acurrent_temporal_analysis.md) | 29.94% | SE ±8.49 pp | 30 / 46 | $9.28 | 1,384.95source 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` \| 29.944 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 9.278145 \| USD \| per_test \| Lower is better \| \| `latency` \| 1384.946 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.49 pp sourcePopulation 73 stderr 8.494 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-6-astra Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/current_temporal_analysis/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / criteria pass rate healthcare life sciences](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__healthcare_life_sciences.md) | 86.47% | SE ±1.97 pp | 26 / 49 | $20.84 | 1,509.92source 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` \| 86.469 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 20.8409 \| USD \| per_test \| Lower is better \| \| `latency` \| 1509.924 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.97 pp sourcePopulation 81 stderr 1.968 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-6-astra Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__healthcare_life_sciences/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [DesignArena Agentic web applications](https://benchize.com/benchmarks/designarena%3Awebapps.md) | 1,373elo | SE ±14.21 | 1 / 39 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=webapps) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1373 \| elo \| webapps \| Higher is better \| ### Configuration arenaType agents category agon_webapps inputModality text Reasoning effort max sourceModelVersion gpt-6-astra-max thinkingEnabled true variationName public ### Reported statistics Uncertainty Standard error: ±14.21 averageGenerationTimeMs Not reported battles 720 losses 220 standardError 14.2104 winRate 69.4 wins 500 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=webapps) Source designarena Original model label GPT-6 Astra (max) Source version public Observed 2026-10-21T16:38:00.309Z Evidence SHA-256 `f955787274cf4ac627ada7cd33eaae2e08ef7297db92d3391340fcaa0b44a35f` Source locator `/data/0` |  |  |  |  |  |  |  |
| [EMB v1.1 / misc](https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Amisc.md) | 60.64% | SE ±6.2 pp | 15 / 19 | $3.82 | 594.87source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 60.636 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.821522 \| USD \| per_test \| Lower is better \| \| `latency` \| 594.866 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.2 pp sourcePopulation 30 stderr 6.196 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/misc/openai~1gpt-6-astra` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / criteria pass rate immigration](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__immigration.md) | 84.73% | SE ±2.17 pp | 24 / 49 | $11.16 | 1,172.74source 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` \| 84.727 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 11.161235 \| USD \| per_test \| Lower is better \| \| `latency` \| 1172.736 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.17 pp sourcePopulation 81 stderr 2.173 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-6-astra Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__immigration/openai~1gpt-6-astra` |  |  |  |  |  |  |  |

[Next page](https://benchize.com/models/gpt-6-astra-max.md?cursor=4b671ef27c74f9ea2c9b1615738464bec8b62e5747b9509dbc1514846b40d02e)

---
Cite as: GPT-6 AstraMax — Benchize, https://benchize.com/models/gpt-6-astra-max (retrieved 2026-10-21)