# Claude Opus 5.5Max > Source: Benchize (https://benchize.com) — https://benchize.com/models/claude-opus-5-5-max. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/claude-opus-5-5-max. Anthropic Canonical URL: https://benchize.com/models/claude-opus-5-5-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. Anthropic ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Latency | Source | | | --- | --- | --- | --- | --- | --- | --- | --- | | [HLAB-Vals-1.1 / criteria pass rate real estate](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__real_estate.md) | 92.13% | SE ±1.46 pp | 13 / 14 | $21.78 | 3,861.44source 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` \| 92.128 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 21.779478 \| USD \| per_test \| Lower is better \| \| `latency` \| 3861.442 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.46 pp sourcePopulation 24 stderr 1.456 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__real_estate/anthropic~1claude-opus-5-5` | | | | | | | | | [Finance Agent (v2) / financial modeling](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Afinancial_modeling.md) | 26.89% | SE ±1.19 pp | 9 / 50 | $6.37 | 1,192.95source 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` \| 26.886 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.369203 \| USD \| per_test \| Lower is better \| \| `latency` \| 1192.947 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.19 pp sourcePopulation 80 stderr 1.186 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/financial_modeling/anthropic~1claude-opus-5-5` | | | | | | | | | [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 | $19.62 | 3,178.4source 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` \| 19.621784 \| USD \| per_test \| Lower is better \| \| `latency` \| 3178.396 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 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 anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/emerging_companies_venture_capital/anthropic~1claude-opus-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / insurance](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Ainsurance.md) | 0% | SE ±0 pp | 2 / 49 | $16.38 | 2,860.73source 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` \| 16.375474 \| USD \| per_test \| Lower is better \| \| `latency` \| 2860.728 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 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 anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/insurance/anthropic~1claude-opus-5-5` | | | | | | | | | [ClaimBench / non supporting citation](https://benchize.com/benchmarks/vals-ai%3Aclaimbench%3Anon_supporting_citation.md) | 100% | SE ±0 pp | 1 / 5 | $0.09 | 6.91source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_claimbench.cK2bPt2E.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.094023 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.912532 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 19 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_claimbench.cK2bPt2E.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:56.452Z Evidence SHA-256 `c0b96e43a97ed7a9dbb35a06b2ff59446cf8fd70f6d50005b8c58aa860f229d8` Source locator `/tasks/non_supporting_citation/anthropic~1claude-opus-5-5` | | | | | | | | | [EMB / misc](https://benchize.com/benchmarks/vals-ai%3Aemb%3Amisc.md) | 70.97% | SE ±3.18 pp | 4 / 47 | $9.16 | 1,828.93source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.972 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 9.159194 \| USD \| per_test \| Lower is better \| \| `latency` \| 1828.925 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.18 pp sourcePopulation 76 stderr 3.179 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/misc/anthropic~1claude-opus-5-5` | | | | | | | | | [EMB / lbo](https://benchize.com/benchmarks/vals-ai%3Aemb%3Albo.md) | 69.01% | SE ±6 pp | 3 / 47 | $10.81 | 1,926.23source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.013 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.806996 \| USD \| per_test \| Lower is better \| \| `latency` \| 1926.226 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6 pp sourcePopulation 76 stderr 5.999 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/anthropic~1claude-opus-5-5` | | | | | | | | | [Terminal-Bench 4.0 / science](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Ascience.md) | 71.43% | SE ±0 pp | 1 / 36 | — | — | [Vals AI · 4.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 71.429 \| percent \| reported \| Higher is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 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 anthropic/claude-opus-5-5 Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/science/anthropic~1claude-opus-5-5` | | | | | | | | | [Legal Research Bench / overall](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aoverall.md) | 50.48% | SE ±3.48 pp | 4 / 50 | $25.16 | 6,749.53source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50.481 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 25.163725 \| USD \| per_test \| Lower is better \| \| `latency` \| 6749.531 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.48 pp sourcePopulation 82 stderr 3.475 tokenTotals {"cache_read_tokens":1456137656,"cache_write_tokens":254987053,"input_tokens":1711216726,"output_tokens":144935934,"reasoning_tokens":126915044} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/overall/anthropic~1claude-opus-5-5` | | | | | | | | | [BioMysteryBench / human difficult](https://benchize.com/benchmarks/vals-ai%3Abiomysterybench%3Ahuman_difficult.md) | 47.06% | SE ±3.4 pp | 1 / 20 | $8.02 | 1,445.98source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_biomysterybench.Bley-WAP.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.059 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.015376 \| USD \| per_test \| Lower is better \| \| `latency` \| 1445.982 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Terminus 2 maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.4 pp sourcePopulation 27 stderr 3.396 tokenTotals {"cache_read_tokens":171437188,"cache_write_tokens":3481507,"input_tokens":174924667,"output_tokens":2234886,"reasoning_tokens":1548857} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_biomysterybench.Bley-WAP.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:46:04.029Z Evidence SHA-256 `59bf79d38ec415a34ffb1c2901a16ecbbe101b7fa864e86104d2571fc7cfc23d` Source locator `/tasks/human_difficult/anthropic~1claude-opus-5-5` | | | | | | | | | [Chess Puzzles](https://benchize.com/benchmarks/epoch-ai%3Achess_puzzles.md) | 67% | SE ±4.73 pp | 5 / 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` \| 0.67 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.67 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion Chess Puzzles reasoningBudget Not reported Reasoning effort max sourceModelVersion claude-opus-5-5_max ### Reported statistics Uncertainty Standard error: ±4.73 pp standardError 0.04725815626252609 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=chess_puzzles.csv) Source epoch ai Original model label claude-opus-5-5 Source version Chess Puzzles Evaluated 2026-10-13T13:01:31.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `fa0a449c370b0cceaf273d9472078cce3e5aef6be7009bddf115e6df7f930c54` Source locator `/rows/139` | | | | | | | | | [CyberBench v1.1 / overall](https://benchize.com/benchmarks/benchmark%3Acyber%3Aoverall.md) | 55.36% | SE ±5.13 pp | 22 / 28 | $3.48 | 1,091.13source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 55.357 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.476604 \| USD \| per_test \| Lower is better \| \| `latency` \| 1091.126 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.13 pp sourcePopulation 47 stderr 5.133 tokenTotals {"cache_read_tokens":265061380,"cache_write_tokens":5933202,"input_tokens":271001170,"output_tokens":2436060,"reasoning_tokens":1656850} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:46:15.238Z Evidence SHA-256 `943f593f929f8971a6b746269a2851b5febc2aad4e2f1066895f715033cdc7f1` Source locator `/tasks/overall/anthropic~1claude-opus-5-5` | | | | | | | | | [Terminal-Bench-Science / overall](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-science%3Aoverall.md) | 47.14% | SE ±6.01 pp | 3 / 30 | $19.12 | 8,856.12source duration | [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` \| 47.143 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 19.121966 \| USD \| per_test \| Lower is better \| \| `latency` \| 8856.116 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Mini-SWE-agent maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.01 pp sourcePopulation 41 stderr 6.009 tokenTotals {"cache_read_tokens":1700954981,"cache_write_tokens":128339444,"input_tokens":3658605476,"output_tokens":29236526,"reasoning_tokens":11843007} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_science.o-HR8Nyt.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 0.1 Observed 2026-10-21T16:46:03.529Z Evidence SHA-256 `a30a8618deaecf018ea1c8c9f675576cdd9ab79742d05788067db49afcc5f91b` Source locator `/tasks/overall/anthropic~1claude-opus-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / banking finance](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Abanking_finance.md) | 0% | SE ±0 pp | 5 / 49 | $23.53 | 3,006.78source 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` \| 23.532694 \| USD \| per_test \| Lower is better \| \| `latency` \| 3006.784 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 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 anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/banking_finance/anthropic~1claude-opus-5-5` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate healthcare life sciences](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__healthcare_life_sciences.md) | 92.79% | SE ±1.5 pp | 10 / 14 | $28.86 | 4,038.17source 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` \| 92.785 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 28.864668 \| USD \| per_test \| Lower is better \| \| `latency` \| 4038.166 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.5 pp sourcePopulation 24 stderr 1.501 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__healthcare_life_sciences/anthropic~1claude-opus-5-5` | | | | | | | | | [Vals Index / tax agent bench](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Atax_agent_bench.md) | 45.57% | SE ±3.59 pp | 1 / 14 | $15.09 | 4,012.55source duration | [Vals AI · 2.2](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 45.573 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 15.086184 \| USD \| per_test \| Lower is better \| \| `latency` \| 4012.548 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.59 pp sourcePopulation 23 stderr 3.593 tokenTotals {"cache_read_tokens":648981098,"cache_write_tokens":166280701,"input_tokens":815304119,"output_tokens":88000495,"reasoning_tokens":76703031} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/tax_agent_bench/anthropic~1claude-opus-5-5` | | | | | | | | | [SpireClimb](https://benchize.com/benchmarks/epoch-ai%3Aspireclimb.md) | 3.33% | SE ±1.45 pp | 4 / 7 | — | — | [epoch ai · SpireClimb](https://epoch.ai/data/benchmark_data.zip#file=spireclimb.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.03333333333333333 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.03333333333333333 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion SpireClimb reasoningBudget Not reported Reasoning effort max sourceModelVersion claude-opus-5-5_max ### Reported statistics Uncertainty Standard error: ±1.45 pp standardError 0.014498627873361331 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=spireclimb.csv) Source epoch ai Original model label claude-opus-5-5 Source version SpireClimb Evaluated 2026-09-24T20:02:22.932Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `8bb2bda1fd232b776c132133a46df08f18ceabdc5552e9d61eb5802dc85f4a5e` Source locator `/rows/4` | | | | | | | | | [Terminal-Bench-Science / engineering sciences](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-science%3Aengineering_sciences.md) | 22.22% | SE ±14.7 pp | 5 / 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` \| 22.222 \| percent \| reported \| Higher is better \| ### Configuration computeEffort max harness Mini-SWE-agent maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±14.7 pp sourcePopulation 41 stderr 14.699 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 anthropic/claude-opus-5-5 Source version 0.1 Observed 2026-10-21T16:46:03.529Z Evidence SHA-256 `a30a8618deaecf018ea1c8c9f675576cdd9ab79742d05788067db49afcc5f91b` Source locator `/tasks/engineering_sciences/anthropic~1claude-opus-5-5` | | | | | | | | | [SRE Bench / overall](https://benchize.com/benchmarks/vals-ai%3Asrebench%3Aoverall.md) | 33.59% | SE ±2.92 pp | 4 / 24 | $34.65 | 5,795.03source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sre_bench.Bd0uBJxH.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.588 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 34.654445 \| USD \| per_test \| Lower is better \| \| `latency` \| 5795.029 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.92 pp sourcePopulation 35 stderr 2.923 tokenTotals {"cache_read_tokens":13577780702,"cache_write_tokens":251504746,"input_tokens":13829392481,"output_tokens":60087914,"reasoning_tokens":39110972} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sre_bench.Bd0uBJxH.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:46:15.724Z Evidence SHA-256 `a10b2c964f5878b0fc21c888703f311a5ef7d7a74fc3c529cab3ddd9fa474e2b` Source locator `/tasks/overall/anthropic~1claude-opus-5-5` | | | | | | | | | [BullshitBench v2](https://benchize.com/benchmarks/bullshitbench%3Av2.md) | 62% | — | 43 / 191 | — | — | [bullshitbench · v2](https://api.github.com/repos/petergpt/bullshit-benchmark/contents/data/v2/latest/leaderboard.csv?ref=3c655234d15967738f95da696e3f938d4862dcf7) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `green_rate` \| 0.62 \| score_fraction \| all_attempts \| Higher is better \| \| `red_rate` \| 0.02 \| score_fraction \| all_attempts \| Lower is better \| \| `refusal_rate` \| 0.1 \| score_fraction \| all_attempts \| Lower is better \| \| `avg_score` \| 1.6296 \| score \| judge_grade_0_to_2 \| Higher is better \| ### Configuration Reasoning effort max suite v2 thinkingEnabled true ### Reported statistics acceptedCount 2 answeredCount 90 clearCount 62 errorCount 0 partialCount 26 rank 27 refusalCount 10 sampleSize 100 ### Source [Original source](https://api.github.com/repos/petergpt/bullshit-benchmark/contents/data/v2/latest/leaderboard.csv?ref=3c655234d15967738f95da696e3f938d4862dcf7) Source bullshitbench Original model label anthropic/claude-opus-5.5 Source version v2 Observed 2026-10-21T16:33:56.675Z Evidence SHA-256 `98b485e08764d1c97144bc4f7b28ced1a96d50850947c775870dfda0e5d749b5` Source locator `/rows/26` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate.md) | 75.77% | SE ±0.54 pp | 36 / 49 | $21.38 | 3,175.13source 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` \| 75.77 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 21.37949 \| USD \| per_test \| Lower is better \| \| `latency` \| 3175.128 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.54 pp sourcePopulation 81 stderr 0.539 tokenTotals {"cache_read_tokens":2286257168,"cache_write_tokens":176308820,"input_tokens":2462576678,"output_tokens":38472452,"reasoning_tokens":24925173} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate/anthropic~1claude-opus-5-5` | | | | | | | | | [EMB / overall](https://benchize.com/benchmarks/vals-ai%3Aemb%3Aoverall.md) | 75.94% | SE ±2.38 pp | 2 / 47 | $11.02 | 2,106.43source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.938 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 11.018974 \| USD \| per_test \| Lower is better \| \| `latency` \| 2106.434 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.38 pp sourcePopulation 76 stderr 2.383 tokenTotals {"cache_read_tokens":861165257,"cache_write_tokens":61067293,"input_tokens":922243024,"output_tokens":23704546,"reasoning_tokens":18569025} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/overall/anthropic~1claude-opus-5-5` | | | | | | | | | [SWE-bench Multimodal / overall](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Aoverall.md) | 70.21% | SE ±2.09 pp | 1 / 14 | $4.92 | 1,111.6source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.208 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.920591 \| USD \| per_test \| Lower is better \| \| `latency` \| 1111.602 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.09 pp sourcePopulation 20 stderr 2.09 tokenTotals {"cache_read_tokens":3106799485,"cache_write_tokens":71481242,"input_tokens":3178343409,"output_tokens":38075346,"reasoning_tokens":28587621} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/overall/anthropic~1claude-opus-5-5` | | | | | | | | | [Robo-bench / ninja course](https://benchize.com/benchmarks/vals-ai%3Arobo_bench%3Aninja_course.md) | 0% | SE ±0 pp | 1 / 5 | $0.29 | 68.54source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_robo_bench.DzDVSjnk.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.2937 \| USD \| per_test \| Lower is better \| \| `latency` \| 68.54 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness claude-code maxOutputTokens Not reported provider anthropic reasoning true Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 7 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_robo_bench.DzDVSjnk.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:46:05.362Z Evidence SHA-256 `79018880e0e64e5ee8ea196976a86b4ef42ed28e4ec2284db5d302d8aa6226a5` Source locator `/tasks/ninja_course/anthropic~1claude-opus-5-5` | | | | | | | | | [Legal Research Bench / weighted pass family](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__family.md) | 66.03% | SE ±7.45 pp | 37 / 50 | $27.64 | 7,441.78source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.028 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 27.642257 \| USD \| per_test \| Lower is better \| \| `latency` \| 7441.78 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.45 pp sourcePopulation 82 stderr 7.454 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__family/anthropic~1claude-opus-5-5` | | | | | | | | | [Legal Research Bench / weighted pass civil litigation](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__civil_litigation.md) | 74.02% | SE ±7.86 pp | 41 / 50 | $23.94 | 6,638.64source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 74.02 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 23.940556 \| USD \| per_test \| Lower is better \| \| `latency` \| 6638.643 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.86 pp sourcePopulation 82 stderr 7.86 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__civil_litigation/anthropic~1claude-opus-5-5` | | | | | | | | | [HLAB-Vals-1.1 / litigation dispute resolution](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Alitigation_dispute_resolution.md) | 0% | SE ±0 pp | 10 / 14 | $21.15 | 4,130.84source 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` \| 21.148726 \| USD \| per_test \| Lower is better \| \| `latency` \| 4130.842 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 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 anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/litigation_dispute_resolution/anthropic~1claude-opus-5-5` | | | | | | | | | [Vals Science Index / biomysterybench](https://benchize.com/benchmarks/vals-ai%3Ascience_index%3Abiomysterybench.md) | 79.26% | SE ±0.98 pp | 3 / 17 | $3.64 | 739.25source duration | [Vals AI · 1.0](https://www.vals.ai/_astro/benchmark_view_science_index.CN7FN-f1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.259 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.642341 \| USD \| per_test \| Lower is better \| \| `latency` \| 739.252 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.98 pp sourcePopulation 21 stderr 0.98 tokenTotals {"cache_read_tokens":348450323,"cache_write_tokens":10652845,"input_tokens":359126168,"output_tokens":6342038,"reasoning_tokens":4159050} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_science_index.CN7FN-f1.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.0 Observed 2026-10-21T16:45:50.879Z Evidence SHA-256 `fa4313008e91752fcfc185aaa78665f780d0fc23d7c7198a9853dbf2eaaaef1f` Source locator `/tasks/biomysterybench/anthropic~1claude-opus-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate trusts estates private client](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__trusts_estates_private_client.md) | 70.53% | SE ±3.18 pp | 39 / 49 | $21.78 | 3,375.65source 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` \| 70.531 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 21.781833 \| USD \| per_test \| Lower is better \| \| `latency` \| 3375.65 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.18 pp sourcePopulation 81 stderr 3.176 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 anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__trusts_estates_private_client/anthropic~1claude-opus-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate immigration](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__immigration.md) | 87.27% | SE ±2.01 pp | 17 / 49 | $18.52 | 2,903.42source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.273 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 18.52264 \| USD \| per_test \| Lower is better \| \| `latency` \| 2903.422 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.01 pp sourcePopulation 81 stderr 2.013 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 anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__immigration/anthropic~1claude-opus-5-5` | | | | | | | | | [Finance Agent (v2) / precedents](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Aprecedents.md) | 34.59% | SE ±0.54 pp | 6 / 50 | $11.86 | 2,586.85source 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` \| 34.59 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 11.856107 \| USD \| per_test \| Lower is better \| \| `latency` \| 2586.845 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.54 pp sourcePopulation 80 stderr 0.538 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/precedents/anthropic~1claude-opus-5-5` | | | | | | | | | [HLAB-Vals-1.1 / international trade sanctions](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Ainternational_trade_sanctions.md) | 0% | SE ±0 pp | 5 / 14 | $20.68 | 3,447.77source 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` \| 20.677557 \| USD \| per_test \| Lower is better \| \| `latency` \| 3447.774 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 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 anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/international_trade_sanctions/anthropic~1claude-opus-5-5` | | | | | | | | | [MirrorCode](https://benchize.com/benchmarks/epoch-ai%3Amirrorcode.md) | 77.4% | SE ±8.31 pp | 1 / 8 | — | — | [epoch ai · MirrorCode](https://epoch.ai/data/benchmark_data.zip#file=mirrorcode.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.774 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.774 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion MirrorCode reasoningBudget Not reported Reasoning effort max sourceModelVersion claude-opus-5-5_max ### Reported statistics Uncertainty Standard error: ±8.31 pp standardError 0.0831 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=mirrorcode.csv) Source epoch ai Original model label claude-opus-5-5 Source version MirrorCode Evaluated 2026-09-22T16:42:00.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `5c31ffdeca24dd23e8d1dc40da67f2ec3e2e6f6d63e1a2b2791239e29f5b454e` Source locator `/rows/0` | | | | | | | | | [Tax Agent Bench / weighted pass controversy precedence analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__controversy_precedence_analysis.md) | 66.87% | SE ±8.19 pp | 7 / 46 | $18.11 | 4,856.11source 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` \| 66.871 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 18.106388 \| USD \| per_test \| Lower is better \| \| `latency` \| 4856.106 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.19 pp sourcePopulation 73 stderr 8.194 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/weighted_pass__controversy_precedence_analysis/anthropic~1claude-opus-5-5` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate white collar defense investigations](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__white_collar_defense_investigations.md) | 83.33% | SE ±2.17 pp | 14 / 14 | $24.22 | 3,518.71source 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` \| 83.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 24.223778 \| USD \| per_test \| Lower is better \| \| `latency` \| 3518.708 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.17 pp sourcePopulation 24 stderr 2.166 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__white_collar_defense_investigations/anthropic~1claude-opus-5-5` | | | | | | | | | [Terminal-Bench 4.0 / hardware](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Ahardware.md) | 60% | SE ±0 pp | 1 / 36 | — | — | [Vals AI · 4.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 60 \| percent \| reported \| Higher is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 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 anthropic/claude-opus-5-5 Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/hardware/anthropic~1claude-opus-5-5` | | | | | | | | | [HLAB-Vals-1.1 / insurance](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Ainsurance.md) | 0% | SE ±0 pp | 4 / 14 | $16.38 | 3,072.69source 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` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 16.375474 \| USD \| per_test \| Lower is better \| \| `latency` \| 3072.686 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 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 anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/insurance/anthropic~1claude-opus-5-5` | | | | | | | | | [Legal Research Bench / weighted pass](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass.md) | 80.38% | SE ±2.24 pp | 35 / 50 | $25.16 | 6,749.53source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.378 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 25.163725 \| USD \| per_test \| Lower is better \| \| `latency` \| 6749.531 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.24 pp sourcePopulation 82 stderr 2.238 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass/anthropic~1claude-opus-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / emerging companies venture capital](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aemerging_companies_venture_capital.md) | 0% | SE ±0 pp | 18 / 49 | $19.62 | 2,910.82source 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` \| 19.621784 \| USD \| per_test \| Lower is better \| \| `latency` \| 2910.816 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 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 anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/emerging_companies_venture_capital/anthropic~1claude-opus-5-5` | | | | | | | | | [EMB / dcf](https://benchize.com/benchmarks/vals-ai%3Aemb%3Adcf.md) | 70.14% | SE ±7.67 pp | 1 / 47 | $9.33 | 1,663.97source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.139 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 9.328331 \| USD \| per_test \| Lower is better \| \| `latency` \| 1663.966 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.67 pp sourcePopulation 76 stderr 7.674 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/dcf/anthropic~1claude-opus-5-5` | | | | | | | | | [Legal Research Bench / criminal](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Acriminal.md) | 42.11% | SE ±6.6 pp | 7 / 50 | $27.1 | 7,162.35source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 42.105 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 27.102205 \| USD \| per_test \| Lower is better \| \| `latency` \| 7162.351 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.6 pp sourcePopulation 82 stderr 6.598 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/criminal/anthropic~1claude-opus-5-5` | | | | | | | | | [Vals Index / overall](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Aoverall.md) | 70.18% | SE ±1 pp | 2 / 14 | $28.12 | 5,071.09source duration | [Vals AI · 2.2](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.177 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 28.122421 \| USD \| per_test \| Lower is better \| \| `latency` \| 5071.089 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1 pp sourcePopulation 23 stderr 1.004 tokenTotals {"cache_read_tokens":30671467913,"cache_write_tokens":1290041704,"input_tokens":31961837560,"output_tokens":499754233,"reasoning_tokens":381319414} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/overall/anthropic~1claude-opus-5-5` | | | | | | | | | [Legal Research Bench / civil litigation](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Acivil_litigation.md) | 48.15% | SE ±9.8 pp | 5 / 50 | $23.94 | 6,638.64source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.148 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 23.940556 \| USD \| per_test \| Lower is better \| \| `latency` \| 6638.643 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±9.8 pp sourcePopulation 82 stderr 9.799 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/civil_litigation/anthropic~1claude-opus-5-5` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate bankruptcy restructuring](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__bankruptcy_restructuring.md) | 87.54% | SE ±1.95 pp | 9 / 14 | $22.05 | 3,463.16source 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` \| 87.543 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 22.051917 \| USD \| per_test \| Lower is better \| \| `latency` \| 3463.16 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 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 anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__bankruptcy_restructuring/anthropic~1claude-opus-5-5` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate energy natural resources](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__energy_natural_resources.md) | 91.75% | SE ±1.58 pp | 13 / 14 | $26.38 | 3,915.46source 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` \| 91.749 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 26.383042 \| USD \| per_test \| Lower is better \| \| `latency` \| 3915.456 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.58 pp sourcePopulation 24 stderr 1.583 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__energy_natural_resources/anthropic~1claude-opus-5-5` | | | | | | | | | [Finance Agent v2.1 / financial modeling](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Afinancial_modeling.md) | 56.98% | SE ±6.79 pp | 1 / 18 | $6.47 | 1,284.64source 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` \| 56.983 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.466784 \| USD \| per_test \| Lower is better \| \| `latency` \| 1284.64 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.79 pp sourcePopulation 28 stderr 6.794 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 anthropic/claude-opus-5-5 Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/financial_modeling/anthropic~1claude-opus-5-5` | | | | | | | | | [BioMysteryBench / overall](https://benchize.com/benchmarks/vals-ai%3Abiomysterybench%3Aoverall.md) | 79.26% | SE ±0.98 pp | 3 / 20 | $3.64 | 739.25source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_biomysterybench.Bley-WAP.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.259 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.642341 \| USD \| per_test \| Lower is better \| \| `latency` \| 739.252 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Terminus 2 maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.98 pp sourcePopulation 27 stderr 0.98 tokenTotals {"cache_read_tokens":348450323,"cache_write_tokens":10652845,"input_tokens":359126168,"output_tokens":6342038,"reasoning_tokens":4159050} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_biomysterybench.Bley-WAP.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:46:04.029Z Evidence SHA-256 `59bf79d38ec415a34ffb1c2901a16ecbbe101b7fa864e86104d2571fc7cfc23d` Source locator `/tasks/overall/anthropic~1claude-opus-5-5` | | | | | | | | | [Time Horizon Index: KSP / mean progress to date](https://benchize.com/benchmarks/vals-ai%3Atime_horizon_index%3Amean_progress_to_date.md) | 69.83% | SE ±0 pp | 2 / 10 | $1,303.37 | 0source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_ksp_bench.CDDTSam7.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.825 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1303.37376 \| USD \| per_test \| Lower is better \| \| `latency` \| 0 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 13 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ksp_bench.CDDTSam7.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:46:16.730Z Evidence SHA-256 `be251b72ecceae7912b9577f9b3a3512740c308a34f81ac823952e919adae50f` Source locator `/tasks/mean_progress_to_date/anthropic~1claude-opus-5-5` | | | | | | | | | [Robo-bench / lego manual](https://benchize.com/benchmarks/vals-ai%3Arobo_bench%3Alego_manual.md) | 15% | SE ±0 pp | 1 / 5 | $0.47 | 166.48source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_robo_bench.DzDVSjnk.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 15 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.467 \| USD \| per_test \| Lower is better \| \| `latency` \| 166.48 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness claude-code maxOutputTokens Not reported provider anthropic reasoning true Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 7 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_robo_bench.DzDVSjnk.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:46:05.362Z Evidence SHA-256 `79018880e0e64e5ee8ea196976a86b4ef42ed28e4ec2284db5d302d8aa6226a5` Source locator `/tasks/lego_manual/anthropic~1claude-opus-5-5` | | | | | | | | | [CUA-bench / held out sandbox](https://benchize.com/benchmarks/vals-ai%3Acua_bench%3Aheld_out_sandbox.md) | 20% | SE ±0 pp | 1 / 8 | $28.01 | 15.16source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_cua_bench.DpgrKYWA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 28.012298 \| USD \| per_test \| Lower is better \| \| `latency` \| 15.16 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness claude-code maxOutputTokens 128000 provider anthropic reasoning true Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 9 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_cua_bench.DpgrKYWA.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:46:16.228Z Evidence SHA-256 `8c415c63f28cd80496a4ccca27d1062ec98bb55268e58cba105b8cf2d7ee53d3` Source locator `/tasks/held_out_sandbox/anthropic~1claude-opus-5-5` | | | | | | | | | [Legal Research Bench / health](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Ahealth.md) | 80% | SE ±7.43 pp | 1 / 50 | $22.01 | 5,675.96source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 22.007354 \| USD \| per_test \| Lower is better \| \| `latency` \| 5675.961 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.43 pp sourcePopulation 82 stderr 7.428 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/health/anthropic~1claude-opus-5-5` | | | | | | | | | [HLAB-Vals-1.1 / funds asset management](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Afunds_asset_management.md) | 20% | SE ±20 pp | 4 / 14 | $21.46 | 4,100.02source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 21.45996 \| USD \| per_test \| Lower is better \| \| `latency` \| 4100.024 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 24 stderr 20 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/funds_asset_management/anthropic~1claude-opus-5-5` | | | | | | | | | [Vals Science Index / terminal bench science](https://benchize.com/benchmarks/vals-ai%3Ascience_index%3Aterminal_bench_science.md) | 47.14% | SE ±6.01 pp | 3 / 17 | $19.12 | 8,856.12source duration | [Vals AI · 1.0](https://www.vals.ai/_astro/benchmark_view_science_index.CN7FN-f1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.143 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 19.121966 \| USD \| per_test \| Lower is better \| \| `latency` \| 8856.116 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.01 pp sourcePopulation 21 stderr 6.009 tokenTotals {"cache_read_tokens":1700954981,"cache_write_tokens":128339444,"input_tokens":3658605476,"output_tokens":29236526,"reasoning_tokens":11843007} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_science_index.CN7FN-f1.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.0 Observed 2026-10-21T16:45:50.879Z Evidence SHA-256 `fa4313008e91752fcfc185aaa78665f780d0fc23d7c7198a9853dbf2eaaaef1f` Source locator `/tasks/terminal_bench_science/anthropic~1claude-opus-5-5` | | | | | | | | | [Tax Agent Bench / overall](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aoverall.md) | 45.57% | SE ±3.59 pp | 2 / 46 | $15.09 | 4,012.55source 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` \| 45.573 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 15.086184 \| USD \| per_test \| Lower is better \| \| `latency` \| 4012.548 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.59 pp sourcePopulation 73 stderr 3.593 tokenTotals {"cache_read_tokens":648981098,"cache_write_tokens":166280701,"input_tokens":815304119,"output_tokens":88000495,"reasoning_tokens":76703031} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/overall/anthropic~1claude-opus-5-5` | | | | | | | | | [Tax Agent Bench / forms filings](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aforms_filings.md) | 30% | SE ±8.51 pp | 4 / 46 | $17.01 | 4,397.82source 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` \| 30 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 17.005457 \| USD \| per_test \| Lower is better \| \| `latency` \| 4397.815 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.51 pp sourcePopulation 73 stderr 8.51 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/forms_filings/anthropic~1claude-opus-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate corporate ma](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__corporate_ma.md) | 92.31% | SE ±1.51 pp | 16 / 49 | $24.67 | 3,182.29source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.308 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 24.674742 \| USD \| per_test \| Lower is better \| \| `latency` \| 3182.286 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.51 pp sourcePopulation 81 stderr 1.511 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 anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__corporate_ma/anthropic~1claude-opus-5-5` | | | | | | | | | [Finance Agent (v2) / all pass](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Aall_pass.md) | 48.11% | SE ±0.62 pp | 6 / 50 | $9.22 | 1,987.81source 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` \| 48.111 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 9.215734 \| USD \| per_test \| Lower is better \| \| `latency` \| 1987.81 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.62 pp sourcePopulation 80 stderr 0.622 tokenTotals {"cache_read_tokens":413590027,"cache_write_tokens":350117722,"input_tokens":763751733,"output_tokens":109304455,"reasoning_tokens":94811735} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/all_pass/anthropic~1claude-opus-5-5` | | | | | | | | | [SWE-bench Multimodal / lighthouse](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Alighthouse.md) | 72.22% | SE ±6.15 pp | 1 / 14 | — | — | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 72.222 \| percent \| reported \| Higher is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.15 pp sourcePopulation 20 stderr 6.152 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/lighthouse/anthropic~1claude-opus-5-5` | | | | | | | | | [Vals Index / emb](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Aemb.md) | 75.84% | SE ±2.41 pp | 2 / 14 | $11.02 | 2,106.43source duration | [Vals AI · 2.2](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.836 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 11.018974 \| USD \| per_test \| Lower is better \| \| `latency` \| 2106.434 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.41 pp sourcePopulation 23 stderr 2.41 tokenTotals {"cache_read_tokens":861165257,"cache_write_tokens":61067293,"input_tokens":922243024,"output_tokens":23704546,"reasoning_tokens":18569025} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/emb/anthropic~1claude-opus-5-5` | | | | | | | | | [EMB / template](https://benchize.com/benchmarks/vals-ai%3Aemb%3Atemplate.md) | 81.39% | SE ±2.55 pp | 1 / 47 | $10.77 | 1,928.47source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 81.385 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.771299 \| USD \| per_test \| Lower is better \| \| `latency` \| 1928.473 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.55 pp sourcePopulation 76 stderr 2.545 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/anthropic~1claude-opus-5-5` | | | | | | | | | [SimpleQA Verified](https://benchize.com/benchmarks/epoch-ai%3Asimpleqa_verified.md) | 72.2% | SE ±1.42 pp | 5 / 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` \| 0.722 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.722 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion SimpleQA Verified reasoningBudget Not reported Reasoning effort max sourceModelVersion claude-opus-5-5_max ### Reported statistics Uncertainty Standard error: ±1.42 pp standardError 0.014174516461485273 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=simpleqa_verified.csv) Source epoch ai Original model label claude-opus-5-5 Source version SimpleQA Verified Evaluated 2026-09-22T18:27:39.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `d4ef3a7d6ccc9c611a30e98d0561021e903c0f4a224851311a7c420862154dd8` Source locator `/rows/10` | | | | | | | | | [HLAB-Vals-1.1 / data privacy cybersecurity](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Adata_privacy_cybersecurity.md) | 30% | SE ±20 pp | 3 / 14 | $21.05 | 3,116.62source 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` \| 30 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 21.050628 \| USD \| per_test \| Lower is better \| \| `latency` \| 3116.616 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 24 stderr 20 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/data_privacy_cybersecurity/anthropic~1claude-opus-5-5` | | | | | | | | | [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 91.67% | — | 9 / 212 | 1.85usd per task | — | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.9166666666666666 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 1.8517409666666667 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup anthropic-claude-opus-5-5 modelType CoT Reasoning effort max sourceModelVersion anthropic-claude-opus-5-5-max thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label Claude Opus 5.5 (Max) Source version v2 Observed 2026-10-21T16:34:20.750Z Evidence SHA-256 `bca68e12cc9a01954ae21b641844c1ecbabe146cb24b87f0f8e9b1db27433c29` Source locator `/evaluations/239` | | | | | | | | | [Vals Science Index / mysterymechanism](https://benchize.com/benchmarks/vals-ai%3Ascience_index%3Amysterymechanism.md) | 49.55% | SE ±3.36 pp | 2 / 17 | $4.62 | 1,178.45source duration | [Vals AI · 1.0](https://www.vals.ai/_astro/benchmark_view_science_index.CN7FN-f1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 49.55 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.619754 \| USD \| per_test \| Lower is better \| \| `latency` \| 1178.454 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.36 pp sourcePopulation 21 stderr 3.363 tokenTotals {"cache_read_tokens":619837485,"cache_write_tokens":38715822,"input_tokens":658569339,"output_tokens":29182250,"reasoning_tokens":23537093} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_science_index.CN7FN-f1.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.0 Observed 2026-10-21T16:45:50.879Z Evidence SHA-256 `fa4313008e91752fcfc185aaa78665f780d0fc23d7c7198a9853dbf2eaaaef1f` Source locator `/tasks/mysterymechanism/anthropic~1claude-opus-5-5` | | | | | | | | | [Finance Agent v2.1 / all pass](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Aall_pass.md) | 56.28% | SE ±2.24 pp | 2 / 18 | $8.91 | 1,980.12source 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` \| 56.275 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.908721 \| USD \| per_test \| Lower is better \| \| `latency` \| 1980.122 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.24 pp sourcePopulation 28 stderr 2.24 tokenTotals {"cache_read_tokens":362746415,"cache_write_tokens":348503177,"input_tokens":711290297,"output_tokens":106934250,"reasoning_tokens":92568283} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/all_pass/anthropic~1claude-opus-5-5` | | | | | | | | | [Vals Index / legal research](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Alegal_research.md) | 50.48% | SE ±3.48 pp | 2 / 14 | $25.16 | 6,749.53source duration | [Vals AI · 2.2](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50.481 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 25.163725 \| USD \| per_test \| Lower is better \| \| `latency` \| 6749.531 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.48 pp sourcePopulation 23 stderr 3.475 tokenTotals {"cache_read_tokens":1456137656,"cache_write_tokens":254987053,"input_tokens":1711216726,"output_tokens":144935934,"reasoning_tokens":126915044} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/legal_research/anthropic~1claude-opus-5-5` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate data privacy cybersecurity](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__data_privacy_cybersecurity.md) | 96.64% | SE ±1.07 pp | 7 / 14 | $21.05 | 3,116.62source 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` \| 96.643 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 21.050628 \| USD \| per_test \| Lower is better \| \| `latency` \| 3116.616 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.07 pp sourcePopulation 24 stderr 1.073 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__data_privacy_cybersecurity/anthropic~1claude-opus-5-5` | | | | | | | | | [Finance Agent v2.1 / earnings analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Aearnings_analysis.md) | 88.89% | SE ±4.29 pp | 3 / 18 | $4.82 | 1,444.7source 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` \| 88.886 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.822133 \| USD \| per_test \| Lower is better \| \| `latency` \| 1444.703 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.29 pp sourcePopulation 28 stderr 4.289 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 anthropic/claude-opus-5-5 Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/earnings_analysis/anthropic~1claude-opus-5-5` | | | | | | | | | [EMB v1.1 / dataroom](https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Adataroom.md) | 86.2% | SE ±4.62 pp | 7 / 19 | $7.83 | 1,493.03source 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` \| 86.197 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.825198 \| USD \| per_test \| Lower is better \| \| `latency` \| 1493.027 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.62 pp sourcePopulation 30 stderr 4.622 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/dataroom/anthropic~1claude-opus-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate structured finance securitization](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__structured_finance_securitization.md) | 79.9% | SE ±2.89 pp | 30 / 49 | $13.72 | 2,994.18source 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` \| 79.897 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 13.720065 \| USD \| per_test \| Lower is better \| \| `latency` \| 2994.183 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.89 pp sourcePopulation 81 stderr 2.885 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 anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__structured_finance_securitization/anthropic~1claude-opus-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate bankruptcy restructuring](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__bankruptcy_restructuring.md) | 69.9% | SE ±2.7 pp | 38 / 49 | $22.05 | 2,768.73source 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` \| 69.896 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 22.051917 \| USD \| per_test \| Lower is better \| \| `latency` \| 2768.728 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.7 pp sourcePopulation 81 stderr 2.703 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 anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__bankruptcy_restructuring/anthropic~1claude-opus-5-5` | | | | | | | | | [Furniture Assembly Benchmark](https://benchize.com/benchmarks/epoch-ai%3Afurniture_assembly.md) | 83.33% | SE ±4.7 pp | 1 / 21 | — | — | [epoch ai · Furniture Assembly](https://epoch.ai/data/benchmark_data.zip#file=furniture_assembly.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.8333333333333334 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.8333333333333334 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion Furniture Assembly reasoningBudget Not reported Reasoning effort max sourceModelVersion claude-opus-5-5_max ### Reported statistics Uncertainty Standard error: ±4.7 pp standardError 0.047040472216649226 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=furniture_assembly.csv) Source epoch ai Original model label claude-opus-5-5 Source version Furniture Assembly Evaluated 2026-09-22T16:51:00.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `d62ab28005a1b7ab0e57b227d04b0cf86c70a5d8a1981addb26d2ac41c116865` Source locator `/rows/12` | | | | | | | | | [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) | 88.85% | SE ±1.92 pp | 21 / 49 | $23.53 | 3,006.78source 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` \| 88.848 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 23.532694 \| USD \| per_test \| Lower is better \| \| `latency` \| 3006.784 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.92 pp sourcePopulation 81 stderr 1.923 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 anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__banking_finance/anthropic~1claude-opus-5-5` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate antitrust competition](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__antitrust_competition.md) | 88.41% | SE ±1.93 pp | 12 / 14 | $23.05 | 3,063.88source 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` \| 88.406 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 23.046646 \| USD \| per_test \| Lower is better \| \| `latency` \| 3063.884 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.93 pp sourcePopulation 24 stderr 1.931 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__antitrust_competition/anthropic~1claude-opus-5-5` | | | | | | | | | [Finance Agent v2.1 / market analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Amarket_analysis.md) | 67.8% | SE ±6.71 pp | 4 / 18 | $5.62 | 1,354.84source 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` \| 67.795 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.618355 \| USD \| per_test \| Lower is better \| \| `latency` \| 1354.839 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.71 pp sourcePopulation 28 stderr 6.707 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 anthropic/claude-opus-5-5 Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/market_analysis/anthropic~1claude-opus-5-5` | | | | | | | | | [HLAB-Vals-1.1 / intellectual property](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aintellectual_property.md) | 10% | SE ±10 pp | 7 / 14 | $20.7 | 3,385.32source 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` \| 20.701364 \| USD \| per_test \| Lower is better \| \| `latency` \| 3385.322 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 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 anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/intellectual_property/anthropic~1claude-opus-5-5` | | | | | | | | | [Tax Agent Bench / current temporal analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Acurrent_temporal_analysis.md) | 46.56% | SE ±9.24 pp | 11 / 46 | $19.64 | 5,343.65source 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` \| 46.558 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 19.635953 \| USD \| per_test \| Lower is better \| \| `latency` \| 5343.646 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±9.24 pp sourcePopulation 73 stderr 9.243 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/current_temporal_analysis/anthropic~1claude-opus-5-5` | | | | | | | | | [HLAB-Vals-1.1 / structured finance securitization](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Astructured_finance_securitization.md) | 10% | SE ±10 pp | 7 / 14 | $13.72 | 3,832.73source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 10 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 13.720065 \| USD \| per_test \| Lower is better \| \| `latency` \| 3832.726 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 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 anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/structured_finance_securitization/anthropic~1claude-opus-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate healthcare life sciences](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__healthcare_life_sciences.md) | 86.14% | SE ±1.99 pp | 27 / 49 | $28.86 | 4,054.91source 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` \| 86.139 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 28.864668 \| USD \| per_test \| Lower is better \| \| `latency` \| 4054.91 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.99 pp sourcePopulation 81 stderr 1.988 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 anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__healthcare_life_sciences/anthropic~1claude-opus-5-5` | | | | | | | | | [CyberBench v1.1 / poc](https://benchize.com/benchmarks/benchmark%3Acyber%3Apoc.md) | 25% | SE ±5.59 pp | 23 / 28 | $2.62 | 806.34source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 25 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.619409 \| USD \| per_test \| Lower is better \| \| `latency` \| 806.336 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.59 pp sourcePopulation 47 stderr 5.59 tokenTotals {"cache_read_tokens":178561509,"cache_write_tokens":4399125,"input_tokens":182966246,"output_tokens":1638628,"reasoning_tokens":1132881} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:46:15.238Z Evidence SHA-256 `943f593f929f8971a6b746269a2851b5febc2aad4e2f1066895f715033cdc7f1` Source locator `/tasks/poc/anthropic~1claude-opus-5-5` | | | | | | | | | [Finance Agent v2.1 / general quantitative analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Ageneral_quantitative_analysis.md) | 79.38% | SE ±5.05 pp | 9 / 18 | $7.78 | 1,491.81source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.378 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.784115 \| USD \| per_test \| Lower is better \| \| `latency` \| 1491.808 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.05 pp sourcePopulation 28 stderr 5.051 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 anthropic/claude-opus-5-5 Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/general_quantitative_analysis/anthropic~1claude-opus-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate international trade sanctions](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__international_trade_sanctions.md) | 87.7% | SE ±2.07 pp | 17 / 49 | $20.68 | 3,099.47source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.698 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 20.677557 \| USD \| per_test \| Lower is better \| \| `latency` \| 3099.466 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.07 pp sourcePopulation 81 stderr 2.073 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 anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/anthropic~1claude-opus-5-5` | | | | | | | | | [Legal Research Bench / constitutional civil rights](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aconstitutional_civil_rights.md) | 42.11% | SE ±8.12 pp | 9 / 50 | $23.75 | 6,438.62source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 42.105 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 23.750422 \| USD \| per_test \| Lower is better \| \| `latency` \| 6438.62 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.12 pp sourcePopulation 82 stderr 8.117 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/constitutional_civil_rights/anthropic~1claude-opus-5-5` | | | | | | | | | [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) | 90.2% | SE ±1.87 pp | 19 / 49 | $20.39 | 2,863.46source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.196 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 20.393428 \| USD \| per_test \| Lower is better \| \| `latency` \| 2863.46 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.87 pp sourcePopulation 81 stderr 1.866 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 anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__capital_markets/anthropic~1claude-opus-5-5` | | | | | | | | | [HLAB-Vals-1.1 / capital markets](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acapital_markets.md) | 0% | SE ±0 pp | 12 / 14 | $20.39 | 2,995.25source 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` \| 20.393428 \| USD \| per_test \| Lower is better \| \| `latency` \| 2995.246 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 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 anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/capital_markets/anthropic~1claude-opus-5-5` | | | | | | | | | [EMB v1.1 / dcf](https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Adcf.md) | 69.87% | SE ±7.69 pp | 3 / 19 | $9.33 | 1,663.97source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.87 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 9.328331 \| USD \| per_test \| Lower is better \| \| `latency` \| 1663.966 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.69 pp sourcePopulation 30 stderr 7.694 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/dcf/anthropic~1claude-opus-5-5` | | | | | | | | | [HLAB-Vals-1.1 / immigration](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aimmigration.md) | 10% | SE ±10 pp | 7 / 14 | $18.52 | 3,151.27source 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` \| 10 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 18.52264 \| USD \| per_test \| Lower is better \| \| `latency` \| 3151.272 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 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 anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/immigration/anthropic~1claude-opus-5-5` | | | | | | | | | [Tax Agent Bench / weighted pass forms filings](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__forms_filings.md) | 63.83% | SE ±8.42 pp | 15 / 46 | $17.01 | 4,397.82source 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` \| 63.833 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 17.005457 \| USD \| per_test \| Lower is better \| \| `latency` \| 4397.815 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.42 pp sourcePopulation 73 stderr 8.421 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/weighted_pass__forms_filings/anthropic~1claude-opus-5-5` | | | | | | | | | [Terminal-Bench 4.0 / overall](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Aoverall.md) | 65.15% | SE ±0 pp | 1 / 36 | $13.2 | 3,810.85source 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` \| 65.152 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 13.198632 \| USD \| per_test \| Lower is better \| \| `latency` \| 3810.852 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 52 stderr 0 tokenTotals {"cache_read_tokens":1824613192,"cache_write_tokens":26310456,"input_tokens":1850938631,"output_tokens":14913437,"reasoning_tokens":10690470} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/overall/anthropic~1claude-opus-5-5` | | | | | | | | | [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 63.58% | — | 10 / 125 | $5.28 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.6358 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.6947 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 5.2832 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort max sourceVersion v1_1 subset extended ### Reported statistics flaggedRate 0.0053 sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label Claude Opus 5.5 Observed 2026-10-21T16:31:00.878Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Claude%20Opus%205.5/max/extended` | | | | | | | | | [Legal Research Bench / weighted pass administrative regulatory](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__administrative_regulatory.md) | 85.43% | SE ±3.72 pp | 29 / 50 | $22.21 | 5,979.93source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.427 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 22.210129 \| USD \| per_test \| Lower is better \| \| `latency` \| 5979.926 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.72 pp sourcePopulation 82 stderr 3.718 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__administrative_regulatory/anthropic~1claude-opus-5-5` | | | | | | | | | [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 | $21.05 | 2,891.98source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 21.050628 \| USD \| per_test \| Lower is better \| \| `latency` \| 2891.984 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 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 anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/data_privacy_cybersecurity/anthropic~1claude-opus-5-5` | | | | | | | | | [Tax Agent Bench / numbers calculations](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Anumbers_calculations.md) | 70% | SE ±8.51 pp | 1 / 46 | $7.94 | 2,259.55source 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` \| 70 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.944016 \| USD \| per_test \| Lower is better \| \| `latency` \| 2259.551 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.51 pp sourcePopulation 73 stderr 8.51 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/numbers_calculations/anthropic~1claude-opus-5-5` | | | | | | | | | [EMB / dataroom](https://benchize.com/benchmarks/vals-ai%3Aemb%3Adataroom.md) | 84.87% | SE ±4.79 pp | 12 / 47 | $7.83 | 1,493.03source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.873 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.825198 \| USD \| per_test \| Lower is better \| \| `latency` \| 1493.027 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.79 pp sourcePopulation 76 stderr 4.792 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/dataroom/anthropic~1claude-opus-5-5` | | | | | | | | | [Legal Research Bench / weighted pass business commercial](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__business_commercial.md) | 70.96% | SE ±6.32 pp | 44 / 50 | $27.89 | 7,461.12source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.961 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 27.89298 \| USD \| per_test \| Lower is better \| \| `latency` \| 7461.121 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.32 pp sourcePopulation 82 stderr 6.321 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__business_commercial/anthropic~1claude-opus-5-5` | | | | | | | | | [ClaimBench / overall](https://benchize.com/benchmarks/vals-ai%3Aclaimbench%3Aoverall.md) | 100% | SE ±0 pp | 1 / 5 | $0.09 | 6.47source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_claimbench.cK2bPt2E.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.091833 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.47 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 19 stderr 0 tokenTotals {"cache_read_tokens":0,"cache_write_tokens":33087830,"input_tokens":33103510,"output_tokens":724589,"reasoning_tokens":594453} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_claimbench.cK2bPt2E.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:56.452Z Evidence SHA-256 `c0b96e43a97ed7a9dbb35a06b2ff59446cf8fd70f6d50005b8c58aa860f229d8` Source locator `/tasks/overall/anthropic~1claude-opus-5-5` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate litigation dispute resolution](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__litigation_dispute_resolution.md) | 93.05% | SE ±1.56 pp | 5 / 14 | $21.15 | 4,130.84source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 93.045 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 21.148726 \| USD \| per_test \| Lower is better \| \| `latency` \| 4130.842 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.56 pp sourcePopulation 24 stderr 1.563 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__litigation_dispute_resolution/anthropic~1claude-opus-5-5` | | | | | | | | | [MedCode / overall](https://benchize.com/benchmarks/vals-ai%3Amedcode%3Aoverall.md) | 49.8% | SE ±2.27 pp | 15 / 49 | $0.66 | 246.88source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medcode.DehpEDgG.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 49.797 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.658237 \| USD \| per_test \| Lower is better \| \| `latency` \| 246.876 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.27 pp sourcePopulation 107 stderr 2.273 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medcode.DehpEDgG.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:59.516Z Evidence SHA-256 `988a6ae1e07e33ce031572ed4a804be11c36ee97a1dd75cbe4740fff3b534f8c` Source locator `/tasks/overall/anthropic~1claude-opus-5-5` | | | | | | | | | [CUA-bench / held out reflex](https://benchize.com/benchmarks/vals-ai%3Acua_bench%3Aheld_out_reflex.md) | 22% | SE ±0 pp | 1 / 8 | $25.37 | 18.6source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_cua_bench.DpgrKYWA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 22 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 25.365201 \| USD \| per_test \| Lower is better \| \| `latency` \| 18.6 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness claude-code maxOutputTokens 128000 provider anthropic reasoning true Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 9 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_cua_bench.DpgrKYWA.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:46:16.228Z Evidence SHA-256 `8c415c63f28cd80496a4ccca27d1062ec98bb55268e58cba105b8cf2d7ee53d3` Source locator `/tasks/held_out_reflex/anthropic~1claude-opus-5-5` | | | | | | | | | [FrontierMath Tiers 1–3 v2 (private)](https://benchize.com/benchmarks/epoch-ai%3Afrontiermath_tiers_1_3_v2.md) | 91.23% | SE ±1.68 pp | 3 / 49 | — | — | [epoch ai · FrontierMath-Tiers-1-3-v2-Private](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tiers_1_3_v2.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.9122807017543859 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.9122807017543859 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tiers-1-3-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion claude-opus-5-5_max ### Reported statistics Uncertainty Standard error: ±1.68 pp standardError 0.016786209858442095 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tiers_1_3_v2.csv) Source epoch ai Original model label claude-opus-5-5 Source version FrontierMath-Tiers-1-3-v2-Private Evaluated 2026-09-22T18:27:39.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `6e31ece7503f8f89dffe8af33010ed7d1d6f0aa3a80cff14fa79f9b34a7b258f` Source locator `/rows/11` | | | | | | | | [Next page](https://benchize.com/models/claude-opus-5-5-max.md?cursor=544ade0993cc0a203bcbd2be4f16682d9e49d070f341ad0715dfaebbdc2d31dd) --- Cite as: Claude Opus 5.5Max — Benchize, https://benchize.com/models/claude-opus-5-5-max (retrieved 2026-10-21)