# Claude Haiku 5.5Max > Source: Benchize (https://benchize.com) — https://benchize.com/models/claude-haiku-5-5-max. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/claude-haiku-5-5-max. Anthropic Canonical URL: https://benchize.com/models/claude-haiku-5-5-max Last updated: Wed, 21 Oct 2026 18:05:10 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 | | | --- | --- | --- | --- | --- | --- | --- | --- | | [Vals Science Index / biomysterybench](https://benchize.com/benchmarks/vals-ai%3Ascience_index%3Abiomysterybench.md) | 70.37% | SE ±1.34 pp | 9 / 17 | $0.51 | 752.46source 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` \| 70.37 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.512756 \| USD \| per_test \| Lower is better \| \| `latency` \| 752.457 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.34 pp sourcePopulation 21 stderr 1.335 tokenTotals {"cache_read_tokens":217680976,"cache_write_tokens":23494403,"input_tokens":241182764,"output_tokens":16695865,"reasoning_tokens":14393004} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_science_index.CN7FN-f1.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1.0 Observed 2026-10-21T16:45:50.879Z Evidence SHA-256 `fa4313008e91752fcfc185aaa78665f780d0fc23d7c7198a9853dbf2eaaaef1f` Source locator `/tasks/biomysterybench/anthropic~1claude-haiku-5-5` | | | | | | | | | [Tax Agent Bench / weighted pass controversy precedence analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__controversy_precedence_analysis.md) | 54.09% | SE ±8.31 pp | 26 / 46 | $1.36 | 3,496.18source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 54.091 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.356768 \| USD \| per_test \| Lower is better \| \| `latency` \| 3496.18 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.31 pp sourcePopulation 73 stderr 8.306 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-haiku-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-haiku-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) | 93.56% | SE ±1.41 pp | 12 / 14 | $5.57 | 2,951.16source 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` \| 93.564 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.570413 \| USD \| per_test \| Lower is better \| \| `latency` \| 2951.16 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.41 pp sourcePopulation 24 stderr 1.412 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-haiku-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-haiku-5-5` | | | | | | | | | [Terminal-Bench 4.0 / science](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Ascience.md) | 21.43% | SE ±4.12 pp | 19 / 36 | — | — | [Vals AI · 4.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 21.429 \| percent \| reported \| Higher is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.12 pp sourcePopulation 52 stderr 4.124 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-haiku-5-5 Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/science/anthropic~1claude-haiku-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate corporate governance](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__corporate_governance.md) | 85.96% | SE ±2.04 pp | 26 / 49 | $3.67 | 2,145.66source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.959 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.673218 \| USD \| per_test \| Lower is better \| \| `latency` \| 2145.662 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.04 pp sourcePopulation 81 stderr 2.037 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-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__corporate_governance/anthropic~1claude-haiku-5-5` | | | | | | | | | [ClaimBench / missing evidence](https://benchize.com/benchmarks/vals-ai%3Aclaimbench%3Amissing_evidence.md) | 100% | SE ±0 pp | 1 / 5 | $0.00259 | 5.21source 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` \| 0.002589 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.214852 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported 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-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:56.452Z Evidence SHA-256 `c0b96e43a97ed7a9dbb35a06b2ff59446cf8fd70f6d50005b8c58aa860f229d8` Source locator `/tasks/missing_evidence/anthropic~1claude-haiku-5-5` | | | | | | | | | [HLAB-Vals-1.1 / corporate ma](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acorporate_ma.md) | 0% | SE ±0 pp | 12 / 14 | $4.04 | 2,321.54source 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` \| 4.04342 \| USD \| per_test \| Lower is better \| \| `latency` \| 2321.544 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 24 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/corporate_ma/anthropic~1claude-haiku-5-5` | | | | | | | | | [Vals Index / finance agent](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Afinance_agent.md) | 65.37% | SE ±2.06 pp | 6 / 14 | $1.64 | 1,864.63source 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` \| 65.373 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.637243 \| USD \| per_test \| Lower is better \| \| `latency` \| 1864.634 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.06 pp sourcePopulation 23 stderr 2.063 tokenTotals {"cache_read_tokens":378369304,"cache_write_tokens":686667014,"input_tokens":1065081554,"output_tokens":206334140,"reasoning_tokens":194190119} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/finance_agent/anthropic~1claude-haiku-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) | 92.95% | SE ±1.45 pp | 12 / 49 | $3.46 | 2,112.59source 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` \| 92.949 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.457385 \| USD \| per_test \| Lower is better \| \| `latency` \| 2112.592 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.45 pp sourcePopulation 81 stderr 1.452 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-haiku-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-haiku-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / trusts estates private client](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Atrusts_estates_private_client.md) | 0% | SE ±0 pp | 15 / 49 | $3.07 | 1,990.22source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.065155 \| USD \| per_test \| Lower is better \| \| `latency` \| 1990.218 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/trusts_estates_private_client/anthropic~1claude-haiku-5-5` | | | | | | | | | [HLAB-Vals-1.1 / real estate](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Areal_estate.md) | 20% | SE ±20 pp | 3 / 14 | $4.69 | 2,713.79source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.688049 \| USD \| per_test \| Lower is better \| \| `latency` \| 2713.792 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 24 stderr 20 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/real_estate/anthropic~1claude-haiku-5-5` | | | | | | | | | [EMB v1.1 / lbo](https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Albo.md) | 49.13% | SE ±9.09 pp | 17 / 19 | $1.42 | 1,186.83source 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` \| 49.132 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.420952 \| USD \| per_test \| Lower is better \| \| `latency` \| 1186.827 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±9.09 pp sourcePopulation 30 stderr 9.09 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-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/lbo/anthropic~1claude-haiku-5-5` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate environmental esg](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__environmental_esg.md) | 88.35% | SE ±1.92 pp | 11 / 14 | $4.55 | 2,880.8source 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` \| 88.351 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.552595 \| USD \| per_test \| Lower is better \| \| `latency` \| 2880.8 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.92 pp sourcePopulation 24 stderr 1.924 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-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__environmental_esg/anthropic~1claude-haiku-5-5` | | | | | | | | | [HLAB-Vals-1.1 / antitrust competition](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aantitrust_competition.md) | 0% | SE ±0 pp | 8 / 14 | $3.46 | 2,274.68source 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` \| 3.460397 \| USD \| per_test \| Lower is better \| \| `latency` \| 2274.678 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 24 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/antitrust_competition/anthropic~1claude-haiku-5-5` | | | | | | | | | [Tax Agent Bench / weighted pass rule source lookup](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__rule_source_lookup.md) | 66.39% | SE ±8.22 pp | 9 / 46 | $1.09 | 2,822.3source 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` \| 66.389 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.085204 \| USD \| per_test \| Lower is better \| \| `latency` \| 2822.295 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.22 pp sourcePopulation 73 stderr 8.217 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-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/weighted_pass__rule_source_lookup/anthropic~1claude-haiku-5-5` | | | | | | | | | [Tax Agent Bench / weighted pass forms filings](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__forms_filings.md) | 61.82% | SE ±8.22 pp | 17 / 46 | $1.43 | 3,272.35source 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` \| 61.821 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.431486 \| USD \| per_test \| Lower is better \| \| `latency` \| 3272.354 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.22 pp sourcePopulation 73 stderr 8.221 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-haiku-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-haiku-5-5` | | | | | | | | | [Code Migration / code quality](https://benchize.com/benchmarks/vals-ai%3Acode-migration%3Acode_quality.md) | 4.83% | SE ±0.02 pp | 2 / 47 | $6.23 | 4,971.31source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_code_migration.Dttzoqk3.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 4.825 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.23191 \| USD \| per_test \| Lower is better \| \| `latency` \| 4971.306 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.02 pp sourcePopulation 79 stderr 0.022 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_code_migration.Dttzoqk3.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:46:12.712Z Evidence SHA-256 `99194597f2c76c402195be47839409046e18bd30454616da6dd40b736a088fa4` Source locator `/tasks/code_quality/anthropic~1claude-haiku-5-5` | | | | | | | | | [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 58.43% | — | 44 / 125 | $1.08 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5843 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.647 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 1.0803 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort max sourceVersion v1_1 subset extended ### Reported statistics flaggedRate 0.0013 sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label Claude Haiku 5.5 Observed 2026-10-21T16:31:00.878Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Claude%20Haiku%205.5/max/extended` | | | | | | | | | [BullshitBench v2](https://benchize.com/benchmarks/bullshitbench%3Av2.md) | 57% | — | 53 / 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` \| 0.57 \| score_fraction \| all_attempts \| Higher is better \| \| `red_rate` \| 0.08 \| score_fraction \| all_attempts \| Lower is better \| \| `refusal_rate` \| 0.01 \| score_fraction \| all_attempts \| Lower is better \| \| `avg_score` \| 1.4714 \| score \| judge_grade_0_to_2 \| Higher is better \| ### Configuration Reasoning effort max suite v2 thinkingEnabled true ### Reported statistics acceptedCount 8 answeredCount 99 clearCount 57 errorCount 0 partialCount 34 rank 50 refusalCount 1 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-haiku-5.5 Source version v2 Observed 2026-10-21T16:33:56.675Z Evidence SHA-256 `98b485e08764d1c97144bc4f7b28ced1a96d50850947c775870dfda0e5d749b5` Source locator `/rows/49` | | | | | | | | | [MysteryMechanism / overall](https://benchize.com/benchmarks/vals-ai%3Amysterymechanism%3Aoverall.md) | 35.14% | SE ±3.21 pp | 9 / 19 | $0.54 | 805.03source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mysterymechanism.75uyyp4P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 35.135 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.541024 \| USD \| per_test \| Lower is better \| \| `latency` \| 805.031 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.21 pp sourcePopulation 27 stderr 3.211 tokenTotals {"cache_read_tokens":861339525,"cache_write_tokens":48729800,"input_tokens":910086657,"output_tokens":41490334,"reasoning_tokens":33895469} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mysterymechanism.75uyyp4P.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:46:04.766Z Evidence SHA-256 `1ef09cd0a0ee8690b0c07b2272057461242359b1680e24975ea42971e03acea9` Source locator `/tasks/overall/anthropic~1claude-haiku-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / funds asset management](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Afunds_asset_management.md) | 0% | SE ±0 pp | 11 / 49 | $4.21 | 2,262.45source 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` \| 4.211796 \| USD \| per_test \| Lower is better \| \| `latency` \| 2262.452 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/funds_asset_management/anthropic~1claude-haiku-5-5` | | | | | | | | | [BioMysteryBench / human solvable](https://benchize.com/benchmarks/vals-ai%3Abiomysterybench%3Ahuman_solvable.md) | 79.91% | SE ±0.91 pp | 9 / 20 | $0.46 | 705.6source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_biomysterybench.Bley-WAP.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.909 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.462501 \| USD \| per_test \| Lower is better \| \| `latency` \| 705.599 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Terminus 2 maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.91 pp sourcePopulation 27 stderr 0.913 tokenTotals {"cache_read_tokens":147492161,"cache_write_tokens":18322925,"input_tokens":165820569,"output_tokens":12720789,"reasoning_tokens":10977149} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_biomysterybench.Bley-WAP.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:46:04.029Z Evidence SHA-256 `59bf79d38ec415a34ffb1c2901a16ecbbe101b7fa864e86104d2571fc7cfc23d` Source locator `/tasks/human_solvable/anthropic~1claude-haiku-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) | 92.29% | SE ±1.64 pp | 8 / 14 | $4.24 | 2,566.03source 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` \| 92.293 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.235701 \| USD \| per_test \| Lower is better \| \| `latency` \| 2566.032 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.64 pp sourcePopulation 24 stderr 1.638 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-haiku-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-haiku-5-5` | | | | | | | | | [EMB / dcf](https://benchize.com/benchmarks/vals-ai%3Aemb%3Adcf.md) | 55.11% | SE ±10.41 pp | 25 / 47 | $0.92 | 950.59source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 55.108 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.919685 \| USD \| per_test \| Lower is better \| \| `latency` \| 950.59 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±10.41 pp sourcePopulation 76 stderr 10.412 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/dcf/anthropic~1claude-haiku-5-5` | | | | | | | | | [Finance Agent (v2) / comparables](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Acomparables.md) | 45.33% | SE ±6.65 pp | 25 / 50 | $1.96 | 1,742.82source 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` \| 45.325 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.955055 \| USD \| per_test \| Lower is better \| \| `latency` \| 1742.824 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.65 pp sourcePopulation 80 stderr 6.651 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-haiku-5-5 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/comparables/anthropic~1claude-haiku-5-5` | | | | | | | | | [Terminal-Bench 4.0 / security](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Asecurity.md) | 40% | SE ±11.55 pp | 13 / 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` \| 40 \| percent \| reported \| Higher is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±11.55 pp sourcePopulation 52 stderr 11.547 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-haiku-5-5 Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/security/anthropic~1claude-haiku-5-5` | | | | | | | | | [EMB / misc](https://benchize.com/benchmarks/vals-ai%3Aemb%3Amisc.md) | 52.26% | SE ±11.67 pp | 31 / 47 | $0.97 | 981.41source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.261 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.966232 \| USD \| per_test \| Lower is better \| \| `latency` \| 981.406 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±11.67 pp sourcePopulation 76 stderr 11.667 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/misc/anthropic~1claude-haiku-5-5` | | | | | | | | | [Tax Agent Bench / weighted pass](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass.md) | 62.2% | SE ±3.22 pp | 23 / 46 | $1.16 | 2,973.65source 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` \| 62.203 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.164207 \| USD \| per_test \| Lower is better \| \| `latency` \| 2973.647 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.22 pp sourcePopulation 73 stderr 3.222 tokenTotals {"cache_read_tokens":613966554,"cache_write_tokens":168173092,"input_tokens":782193467,"output_tokens":143162719,"reasoning_tokens":133330984} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/weighted_pass/anthropic~1claude-haiku-5-5` | | | | | | | | | [HLAB-Vals-1.1 / insurance](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Ainsurance.md) | 0% | SE ±0 pp | 4 / 14 | $3.28 | 2,167.05source 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` \| 3.276103 \| USD \| per_test \| Lower is better \| \| `latency` \| 2167.052 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 24 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/insurance/anthropic~1claude-haiku-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / corporate ma](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acorporate_ma.md) | 0% | SE ±0 pp | 21 / 49 | $3.46 | 2,112.59source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.457385 \| USD \| per_test \| Lower is better \| \| `latency` \| 2112.592 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/corporate_ma/anthropic~1claude-haiku-5-5` | | | | | | | | | [Legal Research Bench / weighted pass constitutional civil rights](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__constitutional_civil_rights.md) | 79.97% | SE ±4.41 pp | 36 / 50 | $1.54 | 5,402.99source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.972 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.536565 \| USD \| per_test \| Lower is better \| \| `latency` \| 5402.991 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.41 pp sourcePopulation 82 stderr 4.406 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-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__constitutional_civil_rights/anthropic~1claude-haiku-5-5` | | | | | | | | | [Tax Agent Bench / forms filings](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aforms_filings.md) | 20% | SE ±7.43 pp | 11 / 46 | $1.43 | 3,272.35source 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` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.431486 \| USD \| per_test \| Lower is better \| \| `latency` \| 3272.354 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.43 pp sourcePopulation 73 stderr 7.428 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-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/forms_filings/anthropic~1claude-haiku-5-5` | | | | | | | | | [Terminal-Bench-Science / earth sciences](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-science%3Aearth_sciences.md) | 0% | SE ±0 pp | 14 / 30 | — | — | [Vals AI · 0.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_science.o-HR8Nyt.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| ### Configuration computeEffort max harness Mini-SWE-agent maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 41 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_science.o-HR8Nyt.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 0.1 Observed 2026-10-21T16:46:03.529Z Evidence SHA-256 `a30a8618deaecf018ea1c8c9f675576cdd9ab79742d05788067db49afcc5f91b` Source locator `/tasks/earth_sciences/anthropic~1claude-haiku-5-5` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate.md) | 90.1% | SE ±0.36 pp | 11 / 14 | $4.26 | 2,620.8source 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` \| 90.104 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.264376 \| USD \| per_test \| Lower is better \| \| `latency` \| 2620.795 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.36 pp sourcePopulation 24 stderr 0.36 tokenTotals {"cache_read_tokens":4716242036,"cache_write_tokens":188617435,"input_tokens":4904885383,"output_tokens":69221549,"reasoning_tokens":47929104} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate/anthropic~1claude-haiku-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / structured finance securitization](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Astructured_finance_securitization.md) | 0% | SE ±0 pp | 12 / 49 | $3.46 | 2,118.81source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.463381 \| USD \| per_test \| Lower is better \| \| `latency` \| 2118.808 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/structured_finance_securitization/anthropic~1claude-haiku-5-5` | | | | | | | | | [SimpleQA Verified](https://benchize.com/benchmarks/epoch-ai%3Asimpleqa_verified.md) | 23.8% | SE ±1.35 pp | 35 / 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` \| 0.238 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.238 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion SimpleQA Verified reasoningBudget Not reported Reasoning effort max sourceModelVersion claude-haiku-5-5_max ### Reported statistics Uncertainty Standard error: ±1.35 pp standardError 0.013473586661967093 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=simpleqa_verified.csv) Source epoch ai Original model label claude-haiku-5-5 Source version SimpleQA Verified Evaluated 2026-10-09T14:36:06.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `d4ef3a7d6ccc9c611a30e98d0561021e903c0f4a224851311a7c420862154dd8` Source locator `/rows/3` | | | | | | | | | [SAGE / calculus](https://benchize.com/benchmarks/vals-ai%3Asage%3Acalculus.md) | 71.61% | SE ±6.02 pp | 17 / 36 | $0.02 | 92.02source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 71.605 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.019685 \| USD \| per_test \| Lower is better \| \| `latency` \| 92.023 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.02 pp sourcePopulation 91 stderr 6.022 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/calculus/anthropic~1claude-haiku-5-5` | | | | | | | | | [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 89% | — | 67 / 213 | 0.05usd per task | — | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.89 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.05132828800000002 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup anthropic-claude-haiku-5-5 modelType CoT Reasoning effort max sourceModelVersion anthropic-claude-haiku-5-5-max thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label Claude Haiku 5.5 (Max) Source version v1 Observed 2026-10-21T16:34:20.378Z Evidence SHA-256 `302d8267c0522bf450ec1deeac4d060e2cf2fb444ba0a4269014d9535de0bd1f` Source locator `/evaluations/270` | | | | | | | | | [Code Migration / overall](https://benchize.com/benchmarks/vals-ai%3Acode-migration%3Aoverall.md) | 44.57% | SE ±4.23 pp | 16 / 47 | $6.23 | 4,971.31source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_code_migration.Dttzoqk3.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 44.568 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.23191 \| USD \| per_test \| Lower is better \| \| `latency` \| 4971.306 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.23 pp sourcePopulation 79 stderr 4.231 tokenTotals {"cache_read_tokens":13121904638,"cache_write_tokens":115469948,"input_tokens":13237438344,"output_tokens":65785285,"reasoning_tokens":null} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_code_migration.Dttzoqk3.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:46:12.712Z Evidence SHA-256 `99194597f2c76c402195be47839409046e18bd30454616da6dd40b736a088fa4` Source locator `/tasks/overall/anthropic~1claude-haiku-5-5` | | | | | | | | | [Finance Agent (v2) / overall](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Aoverall.md) | 54.14% | SE ±2.13 pp | 21 / 50 | $1.64 | 1,849source 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` \| 54.138 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.636603 \| USD \| per_test \| Lower is better \| \| `latency` \| 1849 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.13 pp sourcePopulation 80 stderr 2.132 tokenTotals {"cache_read_tokens":434937131,"cache_write_tokens":690320292,"input_tokens":1125304863,"output_tokens":207972605,"reasoning_tokens":195320438} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/overall/anthropic~1claude-haiku-5-5` | | | | | | | | | [SWE-bench Multimodal / scratch gui](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Ascratch_gui.md) | 16.67% | SE ±16.67 pp | 6 / 14 | — | — | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 16.667 \| percent \| reported \| Higher is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±16.67 pp sourcePopulation 20 stderr 16.667 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/scratch_gui/anthropic~1claude-haiku-5-5` | | | | | | | | | [IOI / overall](https://benchize.com/benchmarks/vals-ai%3Aioi%3Aoverall.md) | 47.28% | SE ±10.72 pp | 20 / 29 | $0.83 | 753.82source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.278 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.826826 \| USD \| per_test \| Lower is better \| \| `latency` \| 753.816 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±10.72 pp sourcePopulation 44 stderr 10.721 tokenTotals {"cache_read_tokens":31449829,"cache_write_tokens":1921938,"input_tokens":33372069,"output_tokens":1490525,"reasoning_tokens":1377357} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/overall/anthropic~1claude-haiku-5-5` | | | | | | | | | [Code Migration v1.1 / cli](https://benchize.com/benchmarks/vals-ai%3Acode-migration-v1-1%3Acli.md) | 42.15% | SE ±2.61 pp | 10 / 17 | $6.32 | 4,908.19source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_code_migration_v1_1.bJHk6HEY.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 42.147 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.315451 \| USD \| per_test \| Lower is better \| \| `latency` \| 4908.187 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.61 pp sourcePopulation 26 stderr 2.61 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_code_migration_v1_1.bJHk6HEY.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:46:09.631Z Evidence SHA-256 `352faac603c73f05cc01e89214fb4adcafa05ea7432ea71ea9903a6b5fe36b08` Source locator `/tasks/cli/anthropic~1claude-haiku-5-5` | | | | | | | | | [Code Migration v1.1 / code quality](https://benchize.com/benchmarks/vals-ai%3Acode-migration-v1-1%3Acode_quality.md) | 4.12% | SE ±0.03 pp | 1 / 17 | $6.2 | 5,158.09source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_code_migration_v1_1.bJHk6HEY.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 4.122 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.199353 \| USD \| per_test \| Lower is better \| \| `latency` \| 5158.092 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.03 pp sourcePopulation 26 stderr 0.027 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_code_migration_v1_1.bJHk6HEY.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:46:09.631Z Evidence SHA-256 `352faac603c73f05cc01e89214fb4adcafa05ea7432ea71ea9903a6b5fe36b08` Source locator `/tasks/code_quality/anthropic~1claude-haiku-5-5` | | | | | | | | | [Tax Agent Bench / rule source lookup](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Arule_source_lookup.md) | 45.55% | SE ±9.1 pp | 8 / 46 | $1.09 | 2,822.3source 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` \| 45.554 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.085204 \| USD \| per_test \| Lower is better \| \| `latency` \| 2822.295 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±9.1 pp sourcePopulation 73 stderr 9.096 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-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/rule_source_lookup/anthropic~1claude-haiku-5-5` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate emerging companies venture capital](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__emerging_companies_venture_capital.md) | 92.49% | SE ±1.54 pp | 9 / 14 | $4.16 | 2,505.31source 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` \| 92.491 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.158411 \| USD \| per_test \| Lower is better \| \| `latency` \| 2505.308 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.54 pp sourcePopulation 24 stderr 1.542 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-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__emerging_companies_venture_capital/anthropic~1claude-haiku-5-5` | | | | | | | | | [Legal Research Bench / weighted pass administrative regulatory](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__administrative_regulatory.md) | 88.68% | SE ±2.24 pp | 11 / 50 | $1.44 | 3,941.13source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.676 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.441703 \| USD \| per_test \| Lower is better \| \| `latency` \| 3941.13 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported 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-haiku-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-haiku-5-5` | | | | | | | | | [Vals Index / overall](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Aoverall.md) | 58.71% | SE ±1.28 pp | 8 / 14 | $3.17 | 2,988.33source 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` \| 58.708 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.173012 \| USD \| per_test \| Lower is better \| \| `latency` \| 2988.332 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.28 pp sourcePopulation 23 stderr 1.282 tokenTotals {"cache_read_tokens":21612053476,"cache_write_tokens":1458667521,"input_tokens":23071048400,"output_tokens":765852692,"reasoning_tokens":673025505} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/overall/anthropic~1claude-haiku-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate banking finance](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__banking_finance.md) | 68.77% | SE ±2.83 pp | 44 / 49 | $3.28 | 2,008.81source 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` \| 68.773 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.278736 \| USD \| per_test \| Lower is better \| \| `latency` \| 2008.814 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.83 pp sourcePopulation 81 stderr 2.831 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-haiku-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-haiku-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) | 84.34% | SE ±2.11 pp | 13 / 14 | $5.02 | 3,043.18source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.343 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.01937 \| USD \| per_test \| Lower is better \| \| `latency` \| 3043.182 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.11 pp sourcePopulation 24 stderr 2.112 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-haiku-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-haiku-5-5` | | | | | | | | | [HLAB-Vals-1.1 / healthcare life sciences](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Ahealthcare_life_sciences.md) | 20% | SE ±20 pp | 5 / 14 | $3.98 | 2,608.92source 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` \| 3.982873 \| USD \| per_test \| Lower is better \| \| `latency` \| 2608.918 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 24 stderr 20 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/healthcare_life_sciences/anthropic~1claude-haiku-5-5` | | | | | | | | | [Terminal-Bench-Science / engineering sciences](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-science%3Aengineering_sciences.md) | 0% | SE ±0 pp | 12 / 30 | — | — | [Vals AI · 0.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_science.o-HR8Nyt.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| ### Configuration computeEffort max harness Mini-SWE-agent maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 41 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_science.o-HR8Nyt.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 0.1 Observed 2026-10-21T16:46:03.529Z Evidence SHA-256 `a30a8618deaecf018ea1c8c9f675576cdd9ab79742d05788067db49afcc5f91b` Source locator `/tasks/engineering_sciences/anthropic~1claude-haiku-5-5` | | | | | | | | | [Legal Research Bench / criminal](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Acriminal.md) | 40.35% | SE ±6.56 pp | 9 / 50 | $1.69 | 5,414.37source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 40.351 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.688834 \| USD \| per_test \| Lower is better \| \| `latency` \| 5414.371 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.56 pp sourcePopulation 82 stderr 6.556 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-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/criminal/anthropic~1claude-haiku-5-5` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate capital markets](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__capital_markets.md) | 95.88% | SE ±1.25 pp | 5 / 14 | $3.75 | 2,223.11source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.882 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.753987 \| USD \| per_test \| Lower is better \| \| `latency` \| 2223.106 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.25 pp sourcePopulation 24 stderr 1.247 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-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__capital_markets/anthropic~1claude-haiku-5-5` | | | | | | | | | [HLAB-Vals-1.1 / corporate governance](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acorporate_governance.md) | 0% | SE ±0 pp | 9 / 14 | $4.58 | 2,758.19source 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` \| 4.581533 \| USD \| per_test \| Lower is better \| \| `latency` \| 2758.188 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 24 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/corporate_governance/anthropic~1claude-haiku-5-5` | | | | | | | | | [Vals Index / code migration](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Acode_migration.md) | 50.2% | SE ±4.21 pp | 9 / 14 | $6.13 | 5,148.21source 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` \| 50.199 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.130933 \| USD \| per_test \| Lower is better \| \| `latency` \| 5148.212 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.21 pp sourcePopulation 23 stderr 4.208 tokenTotals {"cache_read_tokens":5550232078,"cache_write_tokens":58450205,"input_tokens":5608709357,"output_tokens":30123861,"reasoning_tokens":17474500} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/code_migration/anthropic~1claude-haiku-5-5` | | | | | | | | | [SAGE / overall](https://benchize.com/benchmarks/vals-ai%3Asage%3Aoverall.md) | 45.78% | SE ±3.42 pp | 28 / 41 | $0.02 | 143.28source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 45.783 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.019327 \| USD \| per_test \| Lower is better \| \| `latency` \| 143.279 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.42 pp sourcePopulation 91 stderr 3.423 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/overall/anthropic~1claude-haiku-5-5` | | | | | | | | | [Vals Index / emb](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Aemb.md) | 65.48% | SE ±3.69 pp | 13 / 14 | $1.36 | 1,195.53source 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` \| 65.477 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.364559 \| USD \| per_test \| Lower is better \| \| `latency` \| 1195.527 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.69 pp sourcePopulation 23 stderr 3.691 tokenTotals {"cache_read_tokens":1444841999,"cache_write_tokens":37877007,"input_tokens":1482730908,"output_tokens":25203657,"reasoning_tokens":19717258} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/emb/anthropic~1claude-haiku-5-5` | | | | | | | | | [ClaimBench / subtle contradiction](https://benchize.com/benchmarks/vals-ai%3Aclaimbench%3Asubtle_contradiction.md) | 100% | SE ±0 pp | 1 / 5 | $0.00251 | 5.32source 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` \| 0.002508 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.318388 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported 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-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:56.452Z Evidence SHA-256 `c0b96e43a97ed7a9dbb35a06b2ff59446cf8fd70f6d50005b8c58aa860f229d8` Source locator `/tasks/subtle_contradiction/anthropic~1claude-haiku-5-5` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate immigration](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__immigration.md) | 90.91% | SE ±1.74 pp | 10 / 14 | $2.86 | 2,118.59source 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` \| 90.909 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.855998 \| USD \| per_test \| Lower is better \| \| `latency` \| 2118.592 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.74 pp sourcePopulation 24 stderr 1.737 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-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__immigration/anthropic~1claude-haiku-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / immigration](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aimmigration.md) | 0% | SE ±0 pp | 6 / 49 | $2.7 | 2,130.83source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.704387 \| USD \| per_test \| Lower is better \| \| `latency` \| 2130.83 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/immigration/anthropic~1claude-haiku-5-5` | | | | | | | | | [Finance Agent v2.1 / disclosure analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Adisclosure_analysis.md) | 71.79% | SE ±5.98 pp | 10 / 18 | $2.7 | 2,872.99source 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` \| 71.787 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.697765 \| USD \| per_test \| Lower is better \| \| `latency` \| 2872.991 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.98 pp sourcePopulation 28 stderr 5.982 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-haiku-5-5 Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/disclosure_analysis/anthropic~1claude-haiku-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) | 91.95% | SE ±1.58 pp | 12 / 14 | $3.98 | 2,608.92source 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` \| 91.946 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.982873 \| USD \| per_test \| Lower is better \| \| `latency` \| 2608.918 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.58 pp sourcePopulation 24 stderr 1.579 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-haiku-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-haiku-5-5` | | | | | | | | | [Finance Agent (v2) / financial modeling](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Afinancial_modeling.md) | 28.33% | SE ±6.04 pp | 8 / 50 | $1.08 | 1,096.71source 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` \| 28.33 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.081013 \| USD \| per_test \| Lower is better \| \| `latency` \| 1096.71 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.04 pp sourcePopulation 80 stderr 6.039 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-haiku-5-5 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/financial_modeling/anthropic~1claude-haiku-5-5` | | | | | | | | | [Finance Agent (v2) / general quantitative analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Ageneral_quantitative_analysis.md) | 74.36% | SE ±5.39 pp | 22 / 50 | $1.38 | 1,399.64source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 74.362 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.377648 \| USD \| per_test \| Lower is better \| \| `latency` \| 1399.637 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.39 pp sourcePopulation 80 stderr 5.385 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-haiku-5-5 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/general_quantitative_analysis/anthropic~1claude-haiku-5-5` | | | | | | | | | [Legal Research Bench / immigration](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aimmigration.md) | 36.36% | SE ±15.21 pp | 9 / 50 | $2.04 | 5,391.65source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 36.364 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.04155 \| USD \| per_test \| Lower is better \| \| `latency` \| 5391.649 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±15.21 pp sourcePopulation 82 stderr 15.212 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-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/immigration/anthropic~1claude-haiku-5-5` | | | | | | | | | [Terminal-Bench 4.0 / ml](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Aml.md) | 63.64% | SE ±5.25 pp | 6 / 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` \| 63.636 \| percent \| reported \| Higher is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.25 pp sourcePopulation 52 stderr 5.249 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-haiku-5-5 Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/ml/anthropic~1claude-haiku-5-5` | | | | | | | | | [Tax Agent Bench / weighted pass fact pattern analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__fact_pattern_analysis.md) | 59.23% | SE ±6.87 pp | 23 / 46 | $1.16 | 2,681.73source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.228 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.15627 \| USD \| per_test \| Lower is better \| \| `latency` \| 2681.727 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.87 pp sourcePopulation 73 stderr 6.866 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-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/weighted_pass__fact_pattern_analysis/anthropic~1claude-haiku-5-5` | | | | | | | | | [HLAB-Vals-1.1 / employment labor](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aemployment_labor.md) | 0% | SE ±0 pp | 1 / 14 | $3.64 | 2,478.52source 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` \| 3.640709 \| USD \| per_test \| Lower is better \| \| `latency` \| 2478.518 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 24 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/employment_labor/anthropic~1claude-haiku-5-5` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate intellectual property](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__intellectual_property.md) | 91.82% | SE ±1.64 pp | 14 / 14 | $4.59 | 2,882.97source 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` \| 91.815 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.592565 \| USD \| per_test \| Lower is better \| \| `latency` \| 2882.972 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.64 pp sourcePopulation 24 stderr 1.638 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-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__intellectual_property/anthropic~1claude-haiku-5-5` | | | | | | | | | [Legal Research Bench / weighted pass civil litigation](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__civil_litigation.md) | 83.04% | SE ±5.59 pp | 33 / 50 | $1.75 | 5,529.8source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.039 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.750979 \| USD \| per_test \| Lower is better \| \| `latency` \| 5529.804 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.59 pp sourcePopulation 82 stderr 5.588 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-haiku-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-haiku-5-5` | | | | | | | | | [HLAB-Vals-1.1 / bankruptcy restructuring](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Abankruptcy_restructuring.md) | 0% | SE ±0 pp | 7 / 14 | $5.08 | 2,985.2source 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` \| 5.081934 \| USD \| per_test \| Lower is better \| \| `latency` \| 2985.2 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 24 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/bankruptcy_restructuring/anthropic~1claude-haiku-5-5` | | | | | | | | | [SWE-bench Multimodal / lighthouse](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Alighthouse.md) | 24.07% | SE ±5.87 pp | 7 / 14 | — | — | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 24.074 \| percent \| reported \| Higher is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.87 pp sourcePopulation 20 stderr 5.873 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-haiku-5-5 Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/lighthouse/anthropic~1claude-haiku-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / international trade sanctions](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Ainternational_trade_sanctions.md) | 0% | SE ±0 pp | 4 / 49 | $3.31 | 2,095.02source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.310241 \| USD \| per_test \| Lower is better \| \| `latency` \| 2095.02 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/international_trade_sanctions/anthropic~1claude-haiku-5-5` | | | | | | | | | [Code Migration v1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Acode-migration-v1-1%3Aoverall.md) | 52.36% | SE ±3.49 pp | 9 / 17 | $6.2 | 5,158.09source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_code_migration_v1_1.bJHk6HEY.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.36 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.199353 \| USD \| per_test \| Lower is better \| \| `latency` \| 5158.092 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.49 pp sourcePopulation 26 stderr 3.489 tokenTotals {"cache_read_tokens":12266227987,"cache_write_tokens":133437957,"input_tokens":12399726054,"output_tokens":66282396,"reasoning_tokens":37421536} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_code_migration_v1_1.bJHk6HEY.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:46:09.631Z Evidence SHA-256 `352faac603c73f05cc01e89214fb4adcafa05ea7432ea71ea9903a6b5fe36b08` Source locator `/tasks/overall/anthropic~1claude-haiku-5-5` | | | | | | | | | [Finance Agent v2.1 / financial modeling](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Afinancial_modeling.md) | 51.52% | SE ±6.9 pp | 3 / 18 | $1.09 | 1,164.57source 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` \| 51.518 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.090725 \| USD \| per_test \| Lower is better \| \| `latency` \| 1164.571 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.9 pp sourcePopulation 28 stderr 6.902 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-haiku-5-5 Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/financial_modeling/anthropic~1claude-haiku-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate energy natural resources](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__energy_natural_resources.md) | 33% | SE ±2.71 pp | 44 / 49 | $3.63 | 1,976.13source 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` \| 33.003 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.629968 \| USD \| per_test \| Lower is better \| \| `latency` \| 1976.13 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.71 pp sourcePopulation 81 stderr 2.706 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-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__energy_natural_resources/anthropic~1claude-haiku-5-5` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate corporate ma](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__corporate_ma.md) | 93.25% | SE ±1.43 pp | 13 / 14 | $4.04 | 2,321.54source 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` \| 93.248 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.04342 \| USD \| per_test \| Lower is better \| \| `latency` \| 2321.544 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.43 pp sourcePopulation 24 stderr 1.425 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-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__corporate_ma/anthropic~1claude-haiku-5-5` | | | | | | | | | [Tax Agent Bench / numbers calculations](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Anumbers_calculations.md) | 53.25% | SE ±9.25 pp | 7 / 46 | $0.54 | 1,793.9source 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` \| 53.25 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.539077 \| USD \| per_test \| Lower is better \| \| `latency` \| 1793.902 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±9.25 pp sourcePopulation 73 stderr 9.25 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-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/numbers_calculations/anthropic~1claude-haiku-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) | 88.24% | SE ±2.02 pp | 25 / 49 | $3.17 | 1,787.54source 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` \| 88.235 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.174123 \| USD \| per_test \| Lower is better \| \| `latency` \| 1787.54 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.02 pp sourcePopulation 81 stderr 2.022 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-haiku-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-haiku-5-5` | | | | | | | | | [Terminal-Bench-Science / overall](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-science%3Aoverall.md) | 10% | SE ±3.61 pp | 12 / 30 | $4.52 | 5,637.47source 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` \| 10 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.523698 \| USD \| per_test \| Lower is better \| \| `latency` \| 5637.472 \| 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 Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.61 pp sourcePopulation 41 stderr 3.612 tokenTotals {"cache_read_tokens":4931170604,"cache_write_tokens":33540337,"input_tokens":9929451142,"output_tokens":45171153,"reasoning_tokens":19018280} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_science.o-HR8Nyt.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 0.1 Observed 2026-10-21T16:46:03.529Z Evidence SHA-256 `a30a8618deaecf018ea1c8c9f675576cdd9ab79742d05788067db49afcc5f91b` Source locator `/tasks/overall/anthropic~1claude-haiku-5-5` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate real estate](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__real_estate.md) | 60.93% | SE ±2.64 pp | 37 / 49 | $4.01 | 2,101.34source 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` \| 60.933 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.008978 \| USD \| per_test \| Lower is better \| \| `latency` \| 2101.336 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.64 pp sourcePopulation 81 stderr 2.638 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-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__real_estate/anthropic~1claude-haiku-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) | 82.33% | SE ±2.34 pp | 21 / 49 | $3.46 | 2,118.81source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.331 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.463381 \| USD \| per_test \| Lower is better \| \| `latency` \| 2118.808 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.34 pp sourcePopulation 81 stderr 2.343 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-haiku-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-haiku-5-5` | | | | | | | | | [ProgramBench / strict](https://benchize.com/benchmarks/vals-ai%3Aprogrambench%3Astrict.md) | 2.5% | SE ±1.11 pp | 7 / 40 | $6.83 | 4,389.65source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 2.5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.828942 \| USD \| per_test \| Lower is better \| \| `latency` \| 4389.65 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.11 pp sourcePopulation 64 stderr 1.107 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:46:10.137Z Evidence SHA-256 `e9bbb4378c7a058441a21d456baf9316b96c2cf5b58d371a3c7c803f5000bd8c` Source locator `/tasks/strict/anthropic~1claude-haiku-5-5` | | | | | | | | | [Tax Agent Bench / weighted pass current temporal analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__current_temporal_analysis.md) | 56.2% | SE ±8.71 pp | 31 / 46 | $1.42 | 3,939.14source 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` \| 56.197 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.419874 \| USD \| per_test \| Lower is better \| \| `latency` \| 3939.143 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.71 pp sourcePopulation 73 stderr 8.712 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-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/weighted_pass__current_temporal_analysis/anthropic~1claude-haiku-5-5` | | | | | | | | | [Furniture Assembly Benchmark](https://benchize.com/benchmarks/epoch-ai%3Afurniture_assembly.md) | 47.5% | SE ±6.45 pp | 11 / 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` \| 0.475 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.475 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion Furniture Assembly reasoningBudget Not reported Reasoning effort max sourceModelVersion claude-haiku-5-5_max ### Reported statistics Uncertainty Standard error: ±6.45 pp standardError 0.06446761548504554 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=furniture_assembly.csv) Source epoch ai Original model label claude-haiku-5-5 Source version Furniture Assembly Evaluated 2026-10-07T20:22:18.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `d62ab28005a1b7ab0e57b227d04b0cf86c70a5d8a1981addb26d2ac41c116865` Source locator `/rows/4` | | | | | | | | | [EMB / overall](https://benchize.com/benchmarks/vals-ai%3Aemb%3Aoverall.md) | 59.02% | SE ±4.17 pp | 28 / 47 | $1.15 | 1,082.9source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.015 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.146892 \| USD \| per_test \| Lower is better \| \| `latency` \| 1082.902 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.17 pp sourcePopulation 76 stderr 4.17 tokenTotals {"cache_read_tokens":1207542704,"cache_write_tokens":32752108,"input_tokens":1240305362,"output_tokens":21428591,"reasoning_tokens":16654436} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/overall/anthropic~1claude-haiku-5-5` | | | | | | | | | [IOI / ioi2025](https://benchize.com/benchmarks/vals-ai%3Aioi%3Aioi2025.md) | 31.33% | SE ±14.52 pp | 26 / 29 | $1.22 | 1,109.98source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 31.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.222573 \| USD \| per_test \| Lower is better \| \| `latency` \| 1109.984 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±14.52 pp sourcePopulation 44 stderr 14.521 tokenTotals {"cache_read_tokens":45957889,"cache_write_tokens":2624882,"input_tokens":48583121,"output_tokens":1989749,"reasoning_tokens":1843916} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/anthropic~1claude-haiku-5-5` | | | | | | | | | [Legal Research Bench / family](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Afamily.md) | 22.73% | SE ±9.15 pp | 13 / 50 | $1.72 | 5,152.11source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 22.727 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.724456 \| USD \| per_test \| Lower is better \| \| `latency` \| 5152.106 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±9.15 pp sourcePopulation 82 stderr 9.145 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-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/family/anthropic~1claude-haiku-5-5` | | | | | | | | | [HLAB-Vals-1.1 / intellectual property](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aintellectual_property.md) | 10% | SE ±10 pp | 7 / 14 | $4.59 | 2,882.97source 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` \| 4.592565 \| USD \| per_test \| Lower is better \| \| `latency` \| 2882.972 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±10 pp sourcePopulation 24 stderr 10 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/intellectual_property/anthropic~1claude-haiku-5-5` | | | | | | | | | [BioMysteryBench / human difficult](https://benchize.com/benchmarks/vals-ai%3Abiomysterybench%3Ahuman_difficult.md) | 29.41% | SE ±3.4 pp | 8 / 20 | $0.73 | 953.67source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_biomysterybench.Bley-WAP.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 29.412 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.72856 \| USD \| per_test \| Lower is better \| \| `latency` \| 953.669 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Terminus 2 maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.4 pp sourcePopulation 27 stderr 3.396 tokenTotals {"cache_read_tokens":70188815,"cache_write_tokens":5171477,"input_tokens":75362195,"output_tokens":3975076,"reasoning_tokens":3415856} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_biomysterybench.Bley-WAP.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:46:04.029Z Evidence SHA-256 `59bf79d38ec415a34ffb1c2901a16ecbbe101b7fa864e86104d2571fc7cfc23d` Source locator `/tasks/human_difficult/anthropic~1claude-haiku-5-5` | | | | | | | | | [EMB v1.1 / scratch](https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Ascratch.md) | 57.65% | SE ±4.55 pp | 19 / 19 | $1.33 | 1,210.58source 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` \| 57.654 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.331689 \| USD \| per_test \| Lower is better \| \| `latency` \| 1210.577 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.55 pp sourcePopulation 30 stderr 4.548 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-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/scratch/anthropic~1claude-haiku-5-5` | | | | | | | | | [SWE-bench Multimodal / overall](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Aoverall.md) | 43.96% | SE ±2.27 pp | 7 / 14 | $0.7 | 975.9source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 43.958 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.704848 \| USD \| per_test \| Lower is better \| \| `latency` \| 975.904 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.27 pp sourcePopulation 20 stderr 2.268 tokenTotals {"cache_read_tokens":4549542924,"cache_write_tokens":93785405,"input_tokens":4643396325,"output_tokens":62236326,"reasoning_tokens":49493415} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/overall/anthropic~1claude-haiku-5-5` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate banking finance](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__banking_finance.md) | 91.23% | SE ±1.73 pp | 11 / 14 | $4.63 | 2,593.16source 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` \| 91.231 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.633581 \| USD \| per_test \| Lower is better \| \| `latency` \| 2593.164 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.73 pp sourcePopulation 24 stderr 1.731 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-haiku-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__banking_finance/anthropic~1claude-haiku-5-5` | | | | | | | | | [Terminal-Bench-Science / physical sciences](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-science%3Aphysical_sciences.md) | 11.77% | SE ±8.06 pp | 13 / 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` \| 11.765 \| percent \| reported \| Higher is better \| ### Configuration computeEffort max harness Mini-SWE-agent maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.06 pp sourcePopulation 41 stderr 8.055 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_science.o-HR8Nyt.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 0.1 Observed 2026-10-21T16:46:03.529Z Evidence SHA-256 `a30a8618deaecf018ea1c8c9f675576cdd9ab79742d05788067db49afcc5f91b` Source locator `/tasks/physical_sciences/anthropic~1claude-haiku-5-5` | | | | | | | | | [Terminal-Bench 4.0 / hardware](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Ahardware.md) | 20% | SE ±0 pp | 13 / 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` \| 20 \| percent \| reported \| Higher is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 52 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/hardware/anthropic~1claude-haiku-5-5` | | | | | | | | | [SWE-bench Multimodal / openlayers](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Aopenlayers.md) | 79.22% | SE ±4.65 pp | 8 / 14 | — | — | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.221 \| percent \| reported \| Higher is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.65 pp sourcePopulation 20 stderr 4.654 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-haiku-5-5 Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/openlayers/anthropic~1claude-haiku-5-5` | | | | | | | | | [Finance Agent (v2) / precedents](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Aprecedents.md) | 26.98% | SE ±6.29 pp | 23 / 50 | $2.2 | 2,427.31source 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` \| 26.976 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.195932 \| USD \| per_test \| Lower is better \| \| `latency` \| 2427.307 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.29 pp sourcePopulation 80 stderr 6.289 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-haiku-5-5 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/precedents/anthropic~1claude-haiku-5-5` | | | | | | | | | [Legal Research Bench / overall](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aoverall.md) | 43.27% | SE ±3.44 pp | 13 / 50 | $1.63 | 4,911.73source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 43.269 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.633459 \| USD \| per_test \| Lower is better \| \| `latency` \| 4911.734 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.44 pp sourcePopulation 82 stderr 3.444 tokenTotals {"cache_read_tokens":1396606112,"cache_write_tokens":248419597,"input_tokens":1645146593,"output_tokens":246336648,"reasoning_tokens":230649495} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/overall/anthropic~1claude-haiku-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) | 66.53% | SE ±2.98 pp | 40 / 49 | $3.4 | 2,395.06source 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` \| 66.534 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.397341 \| USD \| per_test \| Lower is better \| \| `latency` \| 2395.058 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.98 pp sourcePopulation 81 stderr 2.984 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-haiku-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-haiku-5-5` | | | | | | | | [Next page](https://benchize.com/models/claude-haiku-5-5-max.md?cursor=5cf5520604d26de6e21219687dcaee480273f988b3015ce2d93a61e71c40f103) --- Cite as: Claude Haiku 5.5Max — Benchize, https://benchize.com/models/claude-haiku-5-5-max (retrieved 2026-10-21)