# GPT-6 LunaMax > Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-6-luna-max. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-6-luna-max. OpenAI Canonical URL: https://benchize.com/models/gpt-6-luna-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 | | | --- | --- | --- | --- | --- | --- | --- | --- | | [SpireClimb](https://benchize.com/benchmarks/epoch-ai%3Aspireclimb.md) | 0% | SE ±0 pp | 7 / 7 | — | — | [epoch ai · SpireClimb](https://epoch.ai/data/benchmark_data.zip#file=spireclimb.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.0 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.0 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion SpireClimb reasoningBudget Not reported Reasoning effort max sourceModelVersion gpt-6-luna_max ### Reported statistics Uncertainty Standard error: ±0 pp standardError 0 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=spireclimb.csv) Source epoch ai Original model label gpt-6-luna Source version SpireClimb Evaluated 2026-09-28T21:23:58.598Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `8bb2bda1fd232b776c132133a46df08f18ceabdc5552e9d61eb5802dc85f4a5e` Source locator `/rows/2` | | | | | | | | | [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) | 1,479.78 | — | 57 / 146 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1479.7849429577716 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1470.449399118368 rank 92 upper 1489.120486797175 variance 22.68731303533161 votes 5366 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/508/row` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / immigration](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aimmigration.md) | 0% | SE ±0 pp | 6 / 49 | $0.11 | 630.91source 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` \| 0.110658 \| USD \| per_test \| Lower is better \| \| `latency` \| 630.912 \| 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-luna Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/immigration/openai~1gpt-6-luna` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate environmental esg](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__environmental_esg.md) | 87.63% | SE ±1.97 pp | 13 / 14 | $0.16 | 1,205.65source 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` \| 87.634 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.156612 \| USD \| per_test \| Lower is better \| \| `latency` \| 1205.648 \| 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 24 stderr 1.974 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-luna 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-luna` | | | | | | | | | [BioMysteryBench / human difficult](https://benchize.com/benchmarks/vals-ai%3Abiomysterybench%3Ahuman_difficult.md) | 17.65% | SE ±3.4 pp | 20 / 20 | $0.06 | 566.38source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_biomysterybench.Bley-WAP.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 17.647 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.058804 \| USD \| per_test \| Lower is better \| \| `latency` \| 566.382 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Terminus 2 maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.4 pp sourcePopulation 27 stderr 3.396 tokenTotals {"cache_read_tokens":33513499,"cache_write_tokens":1616184,"input_tokens":35146199,"output_tokens":933635,"reasoning_tokens":753491} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_biomysterybench.Bley-WAP.json) Source Vals AI Original model label openai/gpt-6-luna Source version 1 Observed 2026-10-21T16:46:04.029Z Evidence SHA-256 `59bf79d38ec415a34ffb1c2901a16ecbbe101b7fa864e86104d2571fc7cfc23d` Source locator `/tasks/human_difficult/openai~1gpt-6-luna` | | | | | | | | | [Terminal-Bench 2.1 / overall](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2-1%3Aoverall.md) | 73.03% | SE ±1.72 pp | 19 / 43 | $0.03 | 425.09source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 73.034 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.029222 \| USD \| per_test \| Lower is better \| \| `latency` \| 425.094 \| 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: ±1.72 pp sourcePopulation 76 stderr 1.716 tokenTotals {"cache_read_tokens":64567254,"cache_write_tokens":4144652,"input_tokens":68771981,"output_tokens":2862029,"reasoning_tokens":2313628} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) Source Vals AI Original model label openai/gpt-6-luna Source version 2.1 Observed 2026-10-21T16:46:13.216Z Evidence SHA-256 `a5306805cdf86495bdcceff6b2c8534a3768b9853f5077895dab975b809b054f` Source locator `/tasks/overall/openai~1gpt-6-luna` | | | | | | | | | [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-luna Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/scratch_gui/openai~1gpt-6-luna` | | | | | | | | | [SAGE / calculus](https://benchize.com/benchmarks/vals-ai%3Asage%3Acalculus.md) | 44.14% | SE ±6.45 pp | 29 / 36 | $0.01 | 96.29source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 44.136 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.013009 \| USD \| per_test \| Lower is better \| \| `latency` \| 96.286 \| 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: ±6.45 pp sourcePopulation 91 stderr 6.449 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-luna Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/calculus/openai~1gpt-6-luna` | | | | | | | | | [ProgramBench / strict](https://benchize.com/benchmarks/vals-ai%3Aprogrambench%3Astrict.md) | 0.5% | SE ±0.5 pp | 14 / 40 | $0.18 | 1,734.86source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0.5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.180944 \| USD \| per_test \| Lower is better \| \| `latency` \| 1734.863 \| 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: ±0.5 pp sourcePopulation 64 stderr 0.5 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) Source Vals AI Original model label openai/gpt-6-luna Source version 1 Observed 2026-10-21T16:46:10.137Z Evidence SHA-256 `e9bbb4378c7a058441a21d456baf9316b96c2cf5b58d371a3c7c803f5000bd8c` Source locator `/tasks/strict/openai~1gpt-6-luna` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate structured finance securitization](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__structured_finance_securitization.md) | 87.26% | SE ±1.9 pp | 13 / 14 | $0.33 | 1,362.74source 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` \| 87.258 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.326133 \| USD \| per_test \| Lower is better \| \| `latency` \| 1362.744 \| 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: ±1.9 pp sourcePopulation 24 stderr 1.897 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-luna Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__structured_finance_securitization/openai~1gpt-6-luna` | | | | | | | | | [Terminal-Bench 4.0 / ml](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Aml.md) | 9.09% | SE ±9.09 pp | 28 / 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` \| 9.091 \| 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: ±9.09 pp sourcePopulation 52 stderr 9.091 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-luna Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/ml/openai~1gpt-6-luna` | | | | | | | | | [Terminal-Bench 4.0 / security](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Asecurity.md) | 26.67% | SE ±6.67 pp | 20 / 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` \| 26.667 \| 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: ±6.67 pp sourcePopulation 52 stderr 6.667 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-luna Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/security/openai~1gpt-6-luna` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate capital markets](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__capital_markets.md) | 89.41% | SE ±1.93 pp | 20 / 49 | $0.2 | 788.5source 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` \| 89.412 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.197475 \| USD \| per_test \| Lower is better \| \| `latency` \| 788.504 \| 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: ±1.93 pp sourcePopulation 81 stderr 1.931 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-luna Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__capital_markets/openai~1gpt-6-luna` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / data privacy cybersecurity](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Adata_privacy_cybersecurity.md) | 0% | SE ±0 pp | 13 / 49 | $0.34 | 1,442.55source 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` \| 0.343032 \| USD \| per_test \| Lower is better \| \| `latency` \| 1442.554 \| 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-luna Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/data_privacy_cybersecurity/openai~1gpt-6-luna` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate employment labor](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__employment_labor.md) | 77.9% | SE ±2.54 pp | 27 / 49 | $0.21 | 1,138.11source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 77.903 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.205481 \| USD \| per_test \| Lower is better \| \| `latency` \| 1138.112 \| 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: ±2.54 pp sourcePopulation 81 stderr 2.544 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-luna Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__employment_labor/openai~1gpt-6-luna` | | | | | | | | | [Arena text style control / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_entertainment_and_sports_and_media.md) | 1,413.83 | — | 53 / 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` \| 1413.8289591039477 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1407.4402566124604 rank 87 upper 1420.2176615954352 variance 10.625005090478064 votes 16757 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4779/row` | | | | | | | | | [Arena vision / overall (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aoverall--config-vision.md) | 1,216.1 | — | 64 / 82 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1216.103808862197 \| rating \| reported \| Higher is better \| ### Configuration category overall config vision Reasoning effort max thinkingEnabled true ### Reported statistics lower 1205.300900513246 rank 85 upper 1226.9067172111481 variance 30.379820334700003 votes 3662 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/84/row` | | | | | | | | | [Arena text / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_entertainment_and_sports_and_media.md) | 1,363.62 | — | 86 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1363.6156141934719 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1357.2880186516581 rank 151 upper 1369.9432097352856 variance 10.422724076877191 votes 16757 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4843/row` | | | | | | | | | [SWE-bench Multimodal / overall](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Aoverall.md) | 37.5% | SE ±2.21 pp | 13 / 14 | $0.03 | 315.87source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 37.5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.03193 \| USD \| per_test \| Lower is better \| \| `latency` \| 315.874 \| 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: ±2.21 pp sourcePopulation 20 stderr 2.212 tokenTotals {"cache_read_tokens":493305377,"cache_write_tokens":30777074,"input_tokens":524114440,"output_tokens":13085746,"reasoning_tokens":9069944} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) Source Vals AI Original model label openai/gpt-6-luna Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/overall/openai~1gpt-6-luna` | | | | | | | | | [Terminal-Bench-Science / mathematical sciences](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-science%3Amathematical_sciences.md) | 0% | SE ±0 pp | 19 / 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` \| 0 \| 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: ±0 pp sourcePopulation 41 stderr 0 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-luna Source version 0.1 Observed 2026-10-21T16:46:03.529Z Evidence SHA-256 `a30a8618deaecf018ea1c8c9f675576cdd9ab79742d05788067db49afcc5f91b` Source locator `/tasks/mathematical_sciences/openai~1gpt-6-luna` | | | | | | | | | [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,408.1 | — | 67 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1408.0986818950428 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1402.3140023671488 rank 109 upper 1413.8833614229368 variance 8.710887921060491 votes 21675 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7642/row` | | | | | | | | | [EMB / misc](https://benchize.com/benchmarks/vals-ai%3Aemb%3Amisc.md) | 68.59% | SE ±4.35 pp | 11 / 47 | $0.1 | 834.6source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.586 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.095388 \| USD \| per_test \| Lower is better \| \| `latency` \| 834.6 \| 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 76 stderr 4.353 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-luna Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/misc/openai~1gpt-6-luna` | | | | | | | | | [SAGE / PDEs](https://benchize.com/benchmarks/vals-ai%3Asage%3APDEs.md) | 38.1% | SE ±6.1 pp | 30 / 41 | $0.00545 | 77.75source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 38.095 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005451 \| USD \| per_test \| Lower is better \| \| `latency` \| 77.748 \| 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: ±6.1 pp sourcePopulation 91 stderr 6.103 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-luna Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/PDEs/openai~1gpt-6-luna` | | | | | | | | | [Arena text style control / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts_english.md) | 1,469.16 | — | 57 / 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` \| 1469.1594503307228 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1462.9150077393724 rank 91 upper 1475.4038929220733 variance 10.150587341094052 votes 15274 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3958/row` | | | | | | | | | [IOI / overall](https://benchize.com/benchmarks/vals-ai%3Aioi%3Aoverall.md) | 55.56% | SE ±8.87 pp | 15 / 29 | $0.2 | 2,147.14source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 55.556 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.199412 \| USD \| per_test \| Lower is better \| \| `latency` \| 2147.141 \| 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: ±8.87 pp sourcePopulation 44 stderr 8.866 tokenTotals {"cache_read_tokens":22466950,"cache_write_tokens":1008870,"input_tokens":23476341,"output_tokens":697861,"reasoning_tokens":642789} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label openai/gpt-6-luna Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/overall/openai~1gpt-6-luna` | | | | | | | | | [HLAB-Vals-1.1 / data privacy cybersecurity](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Adata_privacy_cybersecurity.md) | 0% | SE ±0 pp | 12 / 14 | $0.29 | 1,319.85source 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` \| 0.292544 \| USD \| per_test \| Lower is better \| \| `latency` \| 1319.848 \| 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-luna Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/data_privacy_cybersecurity/openai~1gpt-6-luna` | | | | | | | | | [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) | 1,376.3 | — | 82 / 129 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1376.2987451222812 \| rating \| reported \| Higher is better \| ### Configuration category german config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1354.7861531755846 rank 147 upper 1397.8113370689775 variance 120.47288123251136 votes 888 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3283/row` | | | | | | | | | [Terminal-Bench 4](https://benchize.com/benchmarks/harbor%3Aterminal-bench-4.md) | 16.36% | 95% CI 13.64–19.08% | 15 / 17 | — | — | [harbor](https://www.tbench.ai/) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 16.36 \| percent \| reported \| Higher is better \| \| `pass_at_2` \| 0.2273 \| score_fraction \| reported \| Higher is better \| \| `pass_at_3` \| 0.2621 \| score_fraction \| reported \| Higher is better \| \| `pass_at_4` \| 0.2848 \| score_fraction \| reported \| Higher is better \| \| `pass_at_5` \| 0.303 \| score_fraction \| reported \| Higher is better \| ### Configuration agent Codex Reasoning effort max sourceSubmission 5bd8ac99-7353-4210-bdc5-153029e660d5 ### Reported statistics Uncertainty 95% confidence interval: 13.64–19.08% confidenceHalfWidth95 2.72 sampleSize 330 ### Source [Original source](https://www.tbench.ai/) Source harbor Original model label GPT-6 Luna Evaluated 2026-09-22 Observed 2026-10-21T16:33:12.399Z Evidence SHA-256 `0c2d7608e0711b34acae3e757dc2b8bf58bf1f5f04fec84de6cd02598168712c` Source locator `/rows/30` | | | | | | | | | [Terminal-Bench 4.0 / software](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Asoftware.md) | 14.82% | SE ±1.85 pp | 25 / 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` \| 14.815 \| 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: ±1.85 pp sourcePopulation 52 stderr 1.852 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-luna Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/software/openai~1gpt-6-luna` | | | | | | | | | [Terminal-Bench-Science / physical sciences](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-science%3Aphysical_sciences.md) | 0% | SE ±0 pp | 24 / 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` \| 0 \| 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: ±0 pp sourcePopulation 41 stderr 0 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-luna Source version 0.1 Observed 2026-10-21T16:46:03.529Z Evidence SHA-256 `a30a8618deaecf018ea1c8c9f675576cdd9ab79742d05788067db49afcc5f91b` Source locator `/tasks/physical_sciences/openai~1gpt-6-luna` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate intellectual property](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__intellectual_property.md) | 88.34% | SE ±1.91 pp | 31 / 49 | $0.24 | 939.26source 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` \| 88.339 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.235396 \| USD \| per_test \| Lower is better \| \| `latency` \| 939.262 \| 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: ±1.91 pp sourcePopulation 81 stderr 1.911 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-luna Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__intellectual_property/openai~1gpt-6-luna` | | | | | | | | | [Finance Agent v2.1 / all pass](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Aall_pass.md) | 43.78% | SE ±2.21 pp | 16 / 18 | $0.12 | 926.86source 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` \| 43.78 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.120919 \| USD \| per_test \| Lower is better \| \| `latency` \| 926.859 \| 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: ±2.21 pp sourcePopulation 28 stderr 2.214 tokenTotals {"cache_read_tokens":189468255,"cache_write_tokens":203907655,"input_tokens":393427873,"output_tokens":45914348,"reasoning_tokens":42042763} ### 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-luna Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/all_pass/openai~1gpt-6-luna` | | | | | | | | | [Arena vision / diagram (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Adiagram--config-vision.md) | 1,245.35 | — | 60 / 74 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1245.347416839249 \| rating \| reported \| Higher is better \| ### Configuration category diagram config vision Reasoning effort max thinkingEnabled true ### Reported statistics lower 1224.9209539434305 rank 80 upper 1265.7738797350676 variance 108.61508762935613 votes 905 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/546/row` | | | | | | | | | [Legal Research Bench / constitutional civil rights](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aconstitutional_civil_rights.md) | 31.58% | SE ±7.64 pp | 27 / 50 | $0.36 | 1,958.94source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 31.579 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.364867 \| USD \| per_test \| Lower is better \| \| `latency` \| 1958.935 \| 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: ±7.64 pp sourcePopulation 82 stderr 7.642 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-luna Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/constitutional_civil_rights/openai~1gpt-6-luna` | | | | | | | | | [HLAB-Vals-1.1 / emerging companies venture capital](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aemerging_companies_venture_capital.md) | 10% | SE ±10 pp | 8 / 14 | $0.27 | 1,360.81source 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` \| 0.274165 \| USD \| per_test \| Lower is better \| \| `latency` \| 1360.808 \| 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-luna Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/emerging_companies_venture_capital/openai~1gpt-6-luna` | | | | | | | | | [OTIS Mock AIME 2024–2025](https://benchize.com/benchmarks/epoch-ai%3Aotis_mock_aime_2024_2025.md) | 98.89% | SE ±0.67 pp | 14 / 123 | — | — | [epoch ai · OTIS Mock AIME 2024-2025](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.9888888888888889 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.9888888888888889 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion OTIS Mock AIME 2024-2025 reasoningBudget Not reported Reasoning effort max sourceModelVersion gpt-6-luna_max ### Reported statistics Uncertainty Standard error: ±0.67 pp standardError 0.006674027922425511 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) Source epoch ai Original model label gpt-6-luna Source version OTIS Mock AIME 2024-2025 Evaluated 2026-09-22T22:14:05.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `5b411612f91e155dff4b09d09b548b42f7936482ea8b3c00b510bd46e2f6bc2c` Source locator `/rows/9` | | | | | | | | | [Tax Agent Bench / controversy precedence analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Acontroversy_precedence_analysis.md) | 6.67% | SE ±4.63 pp | 23 / 46 | $0.24 | 2,538.97source 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` \| 0.235158 \| USD \| per_test \| Lower is better \| \| `latency` \| 2538.969 \| 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-luna Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/controversy_precedence_analysis/openai~1gpt-6-luna` | | | | | | | | | [BioMysteryBench / human solvable](https://benchize.com/benchmarks/vals-ai%3Abiomysterybench%3Ahuman_solvable.md) | 71.69% | SE ±2.42 pp | 16 / 20 | $0.05 | 513.89source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_biomysterybench.Bley-WAP.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 71.689 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.051939 \| USD \| per_test \| Lower is better \| \| `latency` \| 513.89 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Terminus 2 maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.42 pp sourcePopulation 27 stderr 2.416 tokenTotals {"cache_read_tokens":116053692,"cache_write_tokens":6170923,"input_tokens":122362295,"output_tokens":3549136,"reasoning_tokens":2504994} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_biomysterybench.Bley-WAP.json) Source Vals AI Original model label openai/gpt-6-luna Source version 1 Observed 2026-10-21T16:46:04.029Z Evidence SHA-256 `59bf79d38ec415a34ffb1c2901a16ecbbe101b7fa864e86104d2571fc7cfc23d` Source locator `/tasks/human_solvable/openai~1gpt-6-luna` | | | | | | | | | [HLAB-Vals-1.1 / funds asset management](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Afunds_asset_management.md) | 0% | SE ±0 pp | 10 / 14 | $0.29 | 1,405.04source 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` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.293666 \| USD \| per_test \| Lower is better \| \| `latency` \| 1405.04 \| 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 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-luna Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/funds_asset_management/openai~1gpt-6-luna` | | | | | | | | | [Arena vision / chinese (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Achinese--config-vision.md) | 1,266.18 | — | 54 / 74 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1266.1796511927982 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort max thinkingEnabled true ### Reported statistics lower 1222.2446098178932 rank 70 upper 1310.1146925677033 variance 502.4882344738569 votes 169 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/270/row` | | | | | | | | | [EMB / ma](https://benchize.com/benchmarks/vals-ai%3Aemb%3Ama.md) | 72.05% | SE ±6.69 pp | 19 / 47 | $0.09 | 754.2source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 72.051 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.085662 \| USD \| per_test \| Lower is better \| \| `latency` \| 754.204 \| 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: ±6.69 pp sourcePopulation 76 stderr 6.691 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-luna Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/ma/openai~1gpt-6-luna` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate white collar defense investigations](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__white_collar_defense_investigations.md) | 82.16% | SE ±2.23 pp | 26 / 49 | $0.47 | 1,489.37source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.155 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.473577 \| USD \| per_test \| Lower is better \| \| `latency` \| 1489.37 \| 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: ±2.23 pp sourcePopulation 81 stderr 2.226 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-luna Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__white_collar_defense_investigations/openai~1gpt-6-luna` | | | | | | | | | [EMB / comps](https://benchize.com/benchmarks/vals-ai%3Aemb%3Acomps.md) | 70.47% | SE ±6.16 pp | 15 / 47 | $0.37 | 1,820.73source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.474 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.373356 \| USD \| per_test \| Lower is better \| \| `latency` \| 1820.73 \| 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: ±6.16 pp sourcePopulation 76 stderr 6.155 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-luna Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/comps/openai~1gpt-6-luna` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate tax](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__tax.md) | 79.43% | SE ±2.34 pp | 13 / 14 | $0.33 | 1,376.27source 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` \| 79.431 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.329521 \| USD \| per_test \| Lower is better \| \| `latency` \| 1376.274 \| 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: ±2.34 pp sourcePopulation 24 stderr 2.341 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-luna Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__tax/openai~1gpt-6-luna` | | | | | | | | | [HLAB-Vals-1.1 / bankruptcy restructuring](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Abankruptcy_restructuring.md) | 0% | SE ±0 pp | 7 / 14 | $0.32 | 1,306.95source 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` \| 0.315042 \| USD \| per_test \| Lower is better \| \| `latency` \| 1306.948 \| 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: ±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-luna Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/bankruptcy_restructuring/openai~1gpt-6-luna` | | | | | | | | | [Finance Agent v2.1 / adjustments](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Aadjustments.md) | 56.28% | SE ±6.89 pp | 16 / 18 | $0.12 | 808.32source 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` \| 56.278 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.115355 \| USD \| per_test \| Lower is better \| \| `latency` \| 808.317 \| 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: ±6.89 pp sourcePopulation 28 stderr 6.889 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-luna Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/adjustments/openai~1gpt-6-luna` | | | | | | | | | [SWE-bench Multimodal / lighthouse](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Alighthouse.md) | 16.67% | SE ±5.12 pp | 14 / 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: ±5.12 pp sourcePopulation 20 stderr 5.119 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-luna Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/lighthouse/openai~1gpt-6-luna` | | | | | | | | | [SWE-bench Multimodal / eslint](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Aeslint.md) | 36.36% | SE ±15.21 pp | 12 / 14 | — | — | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 36.364 \| 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: ±15.21 pp sourcePopulation 20 stderr 15.212 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-luna Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/eslint/openai~1gpt-6-luna` | | | | | | | | | [Finance Agent (v2) / earnings analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Aearnings_analysis.md) | 74.19% | SE ±0.74 pp | 21 / 50 | $0.04 | 386.01source 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` \| 74.193 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.040595 \| USD \| per_test \| Lower is better \| \| `latency` \| 386.01 \| 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: ±0.74 pp sourcePopulation 80 stderr 0.742 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-luna Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/earnings_analysis/openai~1gpt-6-luna` | | | | | | | | | [ProofBench v1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Aproof_bench%3Aoverall.md) | 64% | SE ±4.82 pp | 16 / 34 | $0.04 | 451.48source 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` \| 64 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.041637 \| USD \| per_test \| Lower is better \| \| `latency` \| 451.481 \| 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: ±4.82 pp sourcePopulation 52 stderr 4.824 tokenTotals {"cache_read_tokens":117050095,"cache_write_tokens":8996692,"input_tokens":126053768,"output_tokens":2652752,"reasoning_tokens":1912396} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_proof_bench.i3Hwh8rW.json) Source Vals AI Original model label openai/gpt-6-luna Source version 1.1 Observed 2026-10-21T16:46:01.401Z Evidence SHA-256 `22be2aca25de5c4a9eb6448a95713e09a7c97126dfc6f4f75c4afd0e563209cb` Source locator `/tasks/overall/openai~1gpt-6-luna` | | | | | | | | | [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 | $0.24 | 939.26source 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` \| 0.235396 \| USD \| per_test \| Lower is better \| \| `latency` \| 939.262 \| 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-luna Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/intellectual_property/openai~1gpt-6-luna` | | | | | | | | | [EMB v1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Aoverall.md) | 69.95% | SE ±2.54 pp | 9 / 19 | $0.14 | 1,041.05source 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` \| 69.954 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.141708 \| USD \| per_test \| Lower is better \| \| `latency` \| 1041.052 \| 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: ±2.54 pp sourcePopulation 30 stderr 2.542 tokenTotals {"cache_read_tokens":332678280,"cache_write_tokens":29598418,"input_tokens":362285754,"output_tokens":11007243,"reasoning_tokens":8590626} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label openai/gpt-6-luna Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/overall/openai~1gpt-6-luna` | | | | | | | | | [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) | 1,442.86 | — | 61 / 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` \| 1442.8554285078167 \| 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 1435.9510025124034 rank 95 upper 1449.75985450323 variance 12.409634087272408 votes 10905 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4377/row` | | | | | | | | | [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) | 1,369.03 | — | 64 / 120 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1369.0250379892427 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1348.824325426946 rank 112 upper 1389.2257505515395 variance 106.22755756908005 votes 1242 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8062/row` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / employment labor](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aemployment_labor.md) | 0% | SE ±0 pp | 1 / 49 | $0.21 | 1,138.11source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.205481 \| USD \| per_test \| Lower is better \| \| `latency` \| 1138.112 \| 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-luna Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/employment_labor/openai~1gpt-6-luna` | | | | | | | | | [Legal Research Bench / business commercial](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Abusiness_commercial.md) | 23.26% | SE ±6.52 pp | 35 / 50 | $0.46 | 2,678.68source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 23.256 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.455548 \| USD \| per_test \| Lower is better \| \| `latency` \| 2678.679 \| 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: ±6.52 pp sourcePopulation 82 stderr 6.519 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-luna Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/business_commercial/openai~1gpt-6-luna` | | | | | | | | | [Arena text style control / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts.md) | 1,464.67 | — | 55 / 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` \| 1464.6736466257375 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1459.582492159408 rank 87 upper 1469.764801092067 variance 6.747398582120769 votes 39234 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3537/row` | | | | | | | | | [IOI / ioi2025](https://benchize.com/benchmarks/vals-ai%3Aioi%3Aioi2025.md) | 39% | SE ±17.41 pp | 24 / 29 | $0.16 | 1,692.64source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.155148 \| USD \| per_test \| Lower is better \| \| `latency` \| 1692.641 \| 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: ±17.41 pp sourcePopulation 44 stderr 17.408 tokenTotals {"cache_read_tokens":17298254,"cache_write_tokens":863717,"input_tokens":18162547,"output_tokens":604036,"reasoning_tokens":548590} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label openai/gpt-6-luna Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/openai~1gpt-6-luna` | | | | | | | | | [HLAB-Vals-1.1 / international trade sanctions](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Ainternational_trade_sanctions.md) | 0% | SE ±0 pp | 5 / 14 | $0.12 | 982.25source 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` \| 0.115275 \| USD \| per_test \| Lower is better \| \| `latency` \| 982.246 \| 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-luna Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/international_trade_sanctions/openai~1gpt-6-luna` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate.md) | 83.44% | SE ±0.45 pp | 28 / 49 | $0.3 | 1,051.83source 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` \| 83.442 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.303552 \| USD \| per_test \| Lower is better \| \| `latency` \| 1051.83 \| 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: ±0.45 pp sourcePopulation 81 stderr 0.447 tokenTotals {"cache_read_tokens":1422964599,"cache_write_tokens":37829190,"input_tokens":1460813994,"output_tokens":12095727,"reasoning_tokens":6619071} ### 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-luna Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate/openai~1gpt-6-luna` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate healthcare life sciences](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__healthcare_life_sciences.md) | 87.08% | SE ±1.95 pp | 14 / 14 | $0.27 | 1,362.43source 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` \| 87.081 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.267572 \| USD \| per_test \| Lower is better \| \| `latency` \| 1362.432 \| 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: ±1.95 pp sourcePopulation 24 stderr 1.946 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-luna Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__healthcare_life_sciences/openai~1gpt-6-luna` | | | | | | | | | [Arena text / coding](https://benchize.com/benchmarks/lmarena%3Atext%3Acoding.md) | 1,436.56 | — | 75 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1436.5554672582232 \| rating \| reported \| Higher is better \| ### Configuration category coding config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1430.3048227507304 rank 124 upper 1442.8061117657157 variance 10.170760271742015 votes 14401 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/933/row` | | | | | | | | | [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,366.64 | — | 96 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1366.6350122316228 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1360.9073188619593 rank 168 upper 1372.362705601286 variance 8.540107513363349 votes 46946 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2221/row` | | | | | | | | | [EMB / overall](https://benchize.com/benchmarks/vals-ai%3Aemb%3Aoverall.md) | 68.52% | SE ±2.81 pp | 14 / 47 | $0.14 | 1,041.05source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.515 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.141708 \| USD \| per_test \| Lower is better \| \| `latency` \| 1041.052 \| 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: ±2.81 pp sourcePopulation 76 stderr 2.809 tokenTotals {"cache_read_tokens":332678280,"cache_write_tokens":29598418,"input_tokens":362285754,"output_tokens":11007243,"reasoning_tokens":8590626} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-6-luna Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/overall/openai~1gpt-6-luna` | | | | | | | | | [Terminal-Bench 4.0 / science](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Ascience.md) | 21.43% | SE ±0 pp | 19 / 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` \| 21.429 \| 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: ±0 pp sourcePopulation 52 stderr 0 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-luna Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/science/openai~1gpt-6-luna` | | | | | | | | | [Terminal-Bench 4.0 / operations](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Aoperations.md) | 3.7% | SE ±3.7 pp | 31 / 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` \| 3.704 \| 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: ±3.7 pp sourcePopulation 52 stderr 3.704 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-luna Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/operations/openai~1gpt-6-luna` | | | | | | | | | [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) | 1,426.69 | — | 91 / 146 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1426.6852150962122 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1417.412541765013 rank 155 upper 1435.9578884274117 variance 22.382765173465728 votes 5366 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/571/row` | | | | | | | | | [APEX-Agents](https://benchize.com/benchmarks/mercor%3Aapex-agents%3A1.1.md) | 44.3% | — | 27 / 38 | — | — | [mercor · 1.1](https://www.mercor.com/apex/apex-agents-leaderboard/) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 44.3 \| percent \| task_completion_pass_at_1 \| Higher is better \| \| `mean_score` \| 59 \| percent \| rubric_mean \| Higher is better \| ### Configuration datasetUrl https://huggingface.co/datasets/mercor/apex-agents-v1.1 datasetVersion 1.1 harness loop_truncated_tools_agent Reasoning effort max ### Reported statistics reportedErrors {"mean_score":4.9,"pass_1":5.5} sampleSize 946 ### Source [Original source](https://www.mercor.com/apex/apex-agents-leaderboard/) Source mercor Original model label GPT-6 Luna Source version 1.1 Observed 2026-10-21T16:33:27.509Z Evidence SHA-256 `359c569c3b0b62ab375895eabf3c45846fa45551d419d5c9d6a4c9117db78184` Source locator `/__NEXT_DATA__/props/pageProps/leaderboardData/42` | | | | | | | | | [SRE Bench / solved](https://benchize.com/benchmarks/vals-ai%3Asrebench%3Asolved.md) | 2.67% | SE ±1 pp | 17 / 24 | $1.55 | 4,871.1source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sre_bench.Bd0uBJxH.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 2.672 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.550056 \| USD \| per_test \| Lower is better \| \| `latency` \| 4871.097 \| 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 35 stderr 0.998 tokenTotals {"cache_read_tokens":17550144252,"cache_write_tokens":154857879,"input_tokens":17705307873,"output_tokens":76403083,"reasoning_tokens":59461162} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sre_bench.Bd0uBJxH.json) Source Vals AI Original model label openai/gpt-6-luna Source version 1 Observed 2026-10-21T16:46:15.724Z Evidence SHA-256 `a10b2c964f5878b0fc21c888703f311a5ef7d7a74fc3c529cab3ddd9fa474e2b` Source locator `/tasks/solved/openai~1gpt-6-luna` | | | | | | | | | [Legal Research Bench / weighted pass immigration](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__immigration.md) | 78.59% | SE ±8.94 pp | 25 / 50 | $0.63 | 3,576.37source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 78.594 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.63176 \| USD \| per_test \| Lower is better \| \| `latency` \| 3576.368 \| 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: ±8.94 pp sourcePopulation 82 stderr 8.935 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-luna Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__immigration/openai~1gpt-6-luna` | | | | | | | | | [Legal Research Bench / administrative regulatory](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aadministrative_regulatory.md) | 37.88% | SE ±6.02 pp | 33 / 50 | $0.41 | 2,341.02source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 37.879 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.409481 \| USD \| per_test \| Lower is better \| \| `latency` \| 2341.023 \| 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: ±6.02 pp sourcePopulation 82 stderr 6.017 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-luna Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/administrative_regulatory/openai~1gpt-6-luna` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate intellectual property](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__intellectual_property.md) | 92.17% | SE ±1.61 pp | 13 / 14 | $0.26 | 1,253.69source 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` \| 92.171 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.259407 \| USD \| per_test \| Lower is better \| \| `latency` \| 1253.686 \| 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: ±1.61 pp sourcePopulation 24 stderr 1.605 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-luna 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-luna` | | | | | | | | | [SWE-bench Multimodal / prettier](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Aprettier.md) | 46.15% | SE ±14.39 pp | 12 / 14 | — | — | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 46.154 \| 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: ±14.39 pp sourcePopulation 20 stderr 14.391 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-luna Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/prettier/openai~1gpt-6-luna` | | | | | | | | | [HLAB-Vals-1.1 / tax](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Atax.md) | 0% | SE ±0 pp | 7 / 14 | $0.33 | 1,376.27source 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` \| 0.329521 \| USD \| per_test \| Lower is better \| \| `latency` \| 1376.274 \| 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-luna Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/tax/openai~1gpt-6-luna` | | | | | | | | | [Arena text style control / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_software_and_it_services.md) | 1,488.46 | — | 51 / 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` \| 1488.4626116726577 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1482.6912192910947 rank 78 upper 1494.2340040542206 variance 8.670916851307782 votes 22318 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6778/row` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / tax](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Atax.md) | 0% | SE ±0 pp | 3 / 49 | $0.36 | 964.33source 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` \| 0.358568 \| USD \| per_test \| Lower is better \| \| `latency` \| 964.33 \| 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-luna Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/tax/openai~1gpt-6-luna` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate antitrust competition](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__antitrust_competition.md) | 84.24% | SE ±2.2 pp | 14 / 14 | $0.23 | 1,062.15source 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` \| 84.239 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.226157 \| USD \| per_test \| Lower is better \| \| `latency` \| 1062.146 \| 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: ±2.2 pp sourcePopulation 24 stderr 2.197 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-luna Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__antitrust_competition/openai~1gpt-6-luna` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate litigation dispute resolution](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__litigation_dispute_resolution.md) | 88.53% | SE ±1.96 pp | 13 / 14 | $0.87 | 2,139.15source 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` \| 88.534 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.869002 \| USD \| per_test \| Lower is better \| \| `latency` \| 2139.15 \| 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: ±1.96 pp sourcePopulation 24 stderr 1.957 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-luna Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__litigation_dispute_resolution/openai~1gpt-6-luna` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / real estate](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Areal_estate.md) | 0% | SE ±0 pp | 6 / 49 | $0.52 | 1,155.78source 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` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.51747 \| USD \| per_test \| Lower is better \| \| `latency` \| 1155.776 \| 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: ±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-luna Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/real_estate/openai~1gpt-6-luna` | | | | | | | | | [Finance Agent (v2) / market analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Amarket_analysis.md) | 53.28% | SE ±2.89 pp | 38 / 50 | $0.1 | 714.61source 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` \| 53.283 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.104812 \| USD \| per_test \| Lower is better \| \| `latency` \| 714.613 \| 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: ±2.89 pp sourcePopulation 80 stderr 2.892 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-luna Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/market_analysis/openai~1gpt-6-luna` | | | | | | | | | [ProgramBench / overall](https://benchize.com/benchmarks/vals-ai%3Aprogrambench%3Aoverall.md) | 0.5% | SE ±0.5 pp | 14 / 40 | $0.18 | 1,734.86source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0.5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.180944 \| USD \| per_test \| Lower is better \| \| `latency` \| 1734.863 \| 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: ±0.5 pp sourcePopulation 64 stderr 0.5 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) Source Vals AI Original model label openai/gpt-6-luna Source version 1 Observed 2026-10-21T16:46:10.137Z Evidence SHA-256 `e9bbb4378c7a058441a21d456baf9316b96c2cf5b58d371a3c7c803f5000bd8c` Source locator `/tasks/overall/openai~1gpt-6-luna` | | | | | | | | | [Code Migration v1.1 / code quality](https://benchize.com/benchmarks/vals-ai%3Acode-migration-v1-1%3Acode_quality.md) | 2.89% | SE ±0.05 pp | 16 / 17 | $0.83 | 3,621.47source 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` \| 2.885 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.827763 \| USD \| per_test \| Lower is better \| \| `latency` \| 3621.471 \| 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: ±0.05 pp sourcePopulation 26 stderr 0.045 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-luna Source version 1.1 Observed 2026-10-21T16:46:09.631Z Evidence SHA-256 `352faac603c73f05cc01e89214fb4adcafa05ea7432ea71ea9903a6b5fe36b08` Source locator `/tasks/code_quality/openai~1gpt-6-luna` | | | | | | | | | [SimpleQA Verified](https://benchize.com/benchmarks/epoch-ai%3Asimpleqa_verified.md) | 41.4% | SE ±1.56 pp | 25 / 39 | — | — | [epoch ai · SimpleQA Verified](https://epoch.ai/data/benchmark_data.zip#file=simpleqa_verified.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.414 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.414 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion SimpleQA Verified reasoningBudget Not reported Reasoning effort max sourceModelVersion gpt-6-luna_max ### Reported statistics Uncertainty Standard error: ±1.56 pp standardError 0.015583544104177553 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=simpleqa_verified.csv) Source epoch ai Original model label gpt-6-luna Source version SimpleQA Verified Evaluated 2026-09-22T22:14:05.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `d4ef3a7d6ccc9c611a30e98d0561021e903c0f4a224851311a7c420862154dd8` Source locator `/rows/7` | | | | | | | | | [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,490.31 | — | 44 / 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` \| 1490.3053791955622 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1482.0769008599295 rank 60 upper 1498.5338575311946 variance 17.625558122666423 votes 6698 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2530/row` | | | | | | | | | [Terminal-Bench 4.0 / overall](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Aoverall.md) | 13.64% | SE ±1.52 pp | 24 / 36 | $0.35 | 1,965.57source 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` \| 13.636 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.354726 \| USD \| per_test \| Lower is better \| \| `latency` \| 1965.568 \| 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 52 stderr 1.515 tokenTotals {"cache_read_tokens":988222853,"cache_write_tokens":15670624,"input_tokens":1004162895,"output_tokens":10957435,"reasoning_tokens":7328334} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) Source Vals AI Original model label openai/gpt-6-luna Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/overall/openai~1gpt-6-luna` | | | | | | | | | [ProgramBench / partial](https://benchize.com/benchmarks/vals-ai%3Aprogrambench%3Apartial.md) | 66.22% | SE ±1.81 pp | 24 / 40 | $0.18 | 1,734.86source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.223 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.180944 \| USD \| per_test \| Lower is better \| \| `latency` \| 1734.863 \| 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: ±1.81 pp sourcePopulation 64 stderr 1.807 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) Source Vals AI Original model label openai/gpt-6-luna Source version 1 Observed 2026-10-21T16:46:10.137Z Evidence SHA-256 `e9bbb4378c7a058441a21d456baf9316b96c2cf5b58d371a3c7c803f5000bd8c` Source locator `/tasks/partial/openai~1gpt-6-luna` | | | | | | | | | [Legal Research Bench / weighted pass business commercial](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__business_commercial.md) | 79.09% | SE ±3.27 pp | 38 / 50 | $0.46 | 2,678.68source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.086 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.455548 \| USD \| per_test \| Lower is better \| \| `latency` \| 2678.679 \| 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: ±3.27 pp sourcePopulation 82 stderr 3.272 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-luna Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__business_commercial/openai~1gpt-6-luna` | | | | | | | | | [Arena vision style control / chinese](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Achinese.md) | 1,291.65 | — | 38 / 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` \| 1291.6549476879022 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1247.845375060499 rank 48 upper 1335.4645203153054 variance 499.62234228738276 votes 169 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/248/row` | | | | | | | | | [IOI / ioi2024](https://benchize.com/benchmarks/vals-ai%3Aioi%3Aioi2024.md) | 69.33% | SE ±14.06 pp | 13 / 29 | $0.28 | 2,908.98source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.280681 \| USD \| per_test \| Lower is better \| \| `latency` \| 2908.975 \| 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: ±14.06 pp sourcePopulation 44 stderr 14.061 tokenTotals {"cache_read_tokens":32253025,"cache_write_tokens":1137051,"input_tokens":33390628,"output_tokens":703757,"reasoning_tokens":639764} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label openai/gpt-6-luna Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2024/openai~1gpt-6-luna` | | | | | | | | | [Tax Agent Bench / weighted pass rule source lookup](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__rule_source_lookup.md) | 45.9% | SE ±8.6 pp | 34 / 46 | $0.12 | 1,517.94source 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` \| 45.904 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.123429 \| USD \| per_test \| Lower is better \| \| `latency` \| 1517.938 \| 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: ±8.6 pp sourcePopulation 73 stderr 8.604 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-luna Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/weighted_pass__rule_source_lookup/openai~1gpt-6-luna` | | | | | | | | | [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,439.27 | — | 55 / 150 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1439.2726321439163 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1431.6757379421588 rank 92 upper 1446.8695263456743 variance 15.023667884137385 votes 8535 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10475/row` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate banking finance](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__banking_finance.md) | 85.87% | SE ±2.13 pp | 32 / 49 | $0.32 | 848.69source 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` \| 85.874 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.318436 \| USD \| per_test \| Lower is better \| \| `latency` \| 848.694 \| 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 81 stderr 2.128 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-luna Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__banking_finance/openai~1gpt-6-luna` | | | | | | | | | [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 56.1% | — | 57 / 125 | $0.08 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.561 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.6227 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.0831 \| 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 Luna Observed 2026-10-21T16:31:00.878Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/GPT-6%20Luna/max/extended` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / overall](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aoverall.md) | 2.92% | SE ±1.36 pp | 30 / 49 | $0.3 | 1,051.83source 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` \| 2.917 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.303552 \| USD \| per_test \| Lower is better \| \| `latency` \| 1051.83 \| 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 81 stderr 1.362 tokenTotals {"cache_read_tokens":1422964599,"cache_write_tokens":37829190,"input_tokens":1460813994,"output_tokens":12095727,"reasoning_tokens":6619071} ### 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-luna Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/overall/openai~1gpt-6-luna` | | | | | | | | | [Finance Agent (v2) / overall](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Aoverall.md) | 49.87% | SE ±0.23 pp | 33 / 50 | $0.12 | 897.88source 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` \| 49.873 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.124338 \| USD \| per_test \| Lower is better \| \| `latency` \| 897.881 \| 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: ±0.23 pp sourcePopulation 80 stderr 0.232 tokenTotals {"cache_read_tokens":199389488,"cache_write_tokens":214114651,"input_tokens":413604271,"output_tokens":45731435,"reasoning_tokens":41794427} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label openai/gpt-6-luna Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/overall/openai~1gpt-6-luna` | | | | | | | | | [Chess Puzzles](https://benchize.com/benchmarks/epoch-ai%3Achess_puzzles.md) | 36% | SE ±4.82 pp | 32 / 63 | — | — | [epoch ai · Chess Puzzles](https://epoch.ai/data/benchmark_data.zip#file=chess_puzzles.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.36 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.36 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion Chess Puzzles reasoningBudget Not reported Reasoning effort max sourceModelVersion gpt-6-luna_max ### Reported statistics Uncertainty Standard error: ±4.82 pp standardError 0.04824181513244218 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=chess_puzzles.csv) Source epoch ai Original model label gpt-6-luna Source version Chess Puzzles Evaluated 2026-10-13T13:37:06.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `fa0a449c370b0cceaf273d9472078cce3e5aef6be7009bddf115e6df7f930c54` Source locator `/rows/99` | | | | | | | | | [Finance Agent (v2) / general quantitative analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Ageneral_quantitative_analysis.md) | 70.08% | SE ±0.93 pp | 30 / 50 | $0.1 | 670.48source 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` \| 70.084 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.102148 \| USD \| per_test \| Lower is better \| \| `latency` \| 670.483 \| 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: ±0.93 pp sourcePopulation 80 stderr 0.934 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-luna Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/general_quantitative_analysis/openai~1gpt-6-luna` | | | | | | | | | [EMB / template](https://benchize.com/benchmarks/vals-ai%3Aemb%3Atemplate.md) | 70.41% | SE ±3.7 pp | 14 / 47 | $0.17 | 1,085.67source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.405 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.174611 \| USD \| per_test \| Lower is better \| \| `latency` \| 1085.666 \| 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: ±3.7 pp sourcePopulation 76 stderr 3.702 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-luna Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/openai~1gpt-6-luna` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate international trade sanctions](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__international_trade_sanctions.md) | 83.33% | SE ±2.35 pp | 29 / 49 | $0.13 | 676.88source 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` \| 83.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.129464 \| USD \| per_test \| Lower is better \| \| `latency` \| 676.884 \| 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: ±2.35 pp sourcePopulation 81 stderr 2.352 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-luna Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/openai~1gpt-6-luna` | | | | | | | | | [Finance Agent (v2) / precedents](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Aprecedents.md) | 27.38% | SE ±1.65 pp | 22 / 50 | $0.21 | 1,470.22source 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` \| 27.379 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.214229 \| USD \| per_test \| Lower is better \| \| `latency` \| 1470.22 \| 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 80 stderr 1.645 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-luna Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/precedents/openai~1gpt-6-luna` | | | | | | | | [Next page](https://benchize.com/models/gpt-6-luna-max.md?cursor=4cb91ec56e37c52fa9b6033f191adf8a02de371df1282fef0d6ed630d5d4b07c) --- Cite as: GPT-6 LunaMax — Benchize, https://benchize.com/models/gpt-6-luna-max (retrieved 2026-10-21)