# Harvey's Legal Agent Benchmark v1 / criteria pass rate international trade sanctions > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__international_trade_sanctions. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__international_trade_sanctions. Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools Canonical URL: https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__international_trade_sanctions Last updated: Wed, 21 Oct 2026 18:52:20 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools Professional work · Models tested: 49 · Score publishers: Vals AI ## Model results | # | Model | Score | ± | Cost | Latency | | | --- | --- | --- | --- | --- | --- | --- | | 1 | [Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3-xhigh.md)Extra high | 94.55% | SE ±1.6 pp | $1.9 | 1,489.08source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 94.554 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.89638 \| USD \| per_test \| Lower is better \| \| `latency` \| 1489.08 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 131072 provider Meta reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.6 pp sourcePopulation 81 stderr 1.601 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 meta/muse_spark_1_3 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/meta~1muse_spark_1_3` | | | | | | | | 2 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max | 94.05% | SE ±1.49 pp | $28.21 | 3,028.72source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 94.048 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 28.213056 \| USD \| per_test \| Lower is better \| \| `latency` \| 3028.722 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.49 pp sourcePopulation 81 stderr 1.493 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-fable-5-1 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/anthropic~1claude-fable-5-1` | | | | | | | | 3 | [Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High | 93.25% | SE ±1.58 pp | $7.01 | 2,018.01source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 93.254 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.007018 \| USD \| per_test \| Lower is better \| \| `latency` \| 2018.01 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.58 pp sourcePopulation 81 stderr 1.583 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 google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/google~1gemini-4-argon` | | | | | | | | 4 | [Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high | 93.07% | SE ±1.79 pp | $2.12 | 2,085.61source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 93.069 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.123477 \| USD \| per_test \| Lower is better \| \| `latency` \| 2085.605 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 131072 provider Meta reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.79 pp sourcePopulation 81 stderr 1.791 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 meta/muse_spark_1_2 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/meta~1muse_spark_1_2` | | | | | | | | 4 | [Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max | 93.07% | SE ±1.79 pp | $3.6 | 1,674.93source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 93.069 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.602648 \| USD \| per_test \| Lower is better \| \| `latency` \| 1674.933 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 131072 provider Meta reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.79 pp sourcePopulation 81 stderr 1.791 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 meta/muse-wonder Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/meta~1muse-wonder` | | | | | | | | 6 | [Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max | 92.46% | SE ±1.67 pp | $15.32 | 1,640.22source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.46 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 15.317586 \| USD \| per_test \| Lower is better \| \| `latency` \| 1640.224 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.67 pp sourcePopulation 81 stderr 1.667 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-fable-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/anthropic~1claude-fable-5` | | | | | | | | 7 | [DeepSeek V4.1 Flash 1017](https://benchize.com/models/deepseek-v4-1-flash-1017-max.md)Max | 92.06% | SE ±1.71 pp | $0.54 | 1,376.24source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.063 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.535948 \| USD \| per_test \| Lower is better \| \| `latency` \| 1376.242 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature 1 topP 1 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.71 pp sourcePopulation 81 stderr 1.706 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 deepseek/deepseek-v4.1-flash-1017 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/deepseek~1deepseek-v4.1-flash-1017` | | | | | | | | 8 | [MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md) | 91.27% | SE ±1.78 pp | $0.19 | 1,563.18source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.27 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.192448 \| USD \| per_test \| Lower is better \| \| `latency` \| 1563.178 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.78 pp sourcePopulation 81 stderr 1.782 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 xiaomi/mimo-v2.6-pro Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/xiaomi~1mimo-v2.6-pro` | | | | | | | | 9 | [Step 5 Preview](https://benchize.com/models/step-5-preview.md) | 90.87% | SE ±1.82 pp | $0.9 | 1,780.01source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.873 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.89711 \| USD \| per_test \| Lower is better \| \| `latency` \| 1780.01 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 1024000 provider Stepfun reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.82 pp sourcePopulation 81 stderr 1.818 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 stepfun/step-5-preview Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/stepfun~1step-5-preview` | | | | | | | | 10 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1-xhigh.md)Extra high | 90% | SE ±4.29 pp | $0.36 | 372.4source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.355364 \| USD \| per_test \| Lower is better \| \| `latency` \| 372.4 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 256000 provider Meta reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.29 pp sourcePopulation 81 stderr 4.286 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 meta/muse_spark_1_1 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/meta~1muse_spark_1_1` | | | | | | | | 11 | [MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md) | 89.68% | SE ±1.92 pp | $0.07 | 955.07source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.683 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.06912 \| USD \| per_test \| Lower is better \| \| `latency` \| 955.068 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.92 pp sourcePopulation 81 stderr 1.92 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 xiaomi/mimo-v2.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/xiaomi~1mimo-v2.6-flash` | | | | | | | | 12 | [DeepSeek V4 Flash 0731](https://benchize.com/models/deepseek-v4-flash-0731-high.md)High | 89.11% | SE ±2.2 pp | $0.04 | 643.49source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.109 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.03909 \| USD \| per_test \| Lower is better \| \| `latency` \| 643.488 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.2 pp sourcePopulation 81 stderr 2.197 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 deepseek/deepseek-v4-flash-0731 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/deepseek~1deepseek-v4-flash-0731` | | | | | | | | 13 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max | 88.49% | SE ±2.01 pp | $16.27 | 3,708.43source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.492 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 16.269947 \| USD \| per_test \| Lower is better \| \| `latency` \| 3708.434 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.01 pp sourcePopulation 81 stderr 2.014 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-sonnet-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/anthropic~1claude-sonnet-5-5` | | | | | | | | 13 | [DeepSeek V4 Pro 0813](https://benchize.com/models/deepseek-v4-pro-0813-max.md)Max | 88.49% | SE ±2.01 pp | $0.12 | 1,246.82source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.492 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.1231 \| USD \| per_test \| Lower is better \| \| `latency` \| 1246.816 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.01 pp sourcePopulation 81 stderr 2.014 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 deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/deepseek~1deepseek-v4-pro-0813` | | | | | | | | 15 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 88.1% | SE ±2.04 pp | $3.92 | 859.2source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.095 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.921448 \| USD \| per_test \| Lower is better \| \| `latency` \| 859.204 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.04 pp sourcePopulation 81 stderr 2.044 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 google/gemini-3.8-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/google~1gemini-3.8-flash` | | | | | | | | 15 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-max.md)Max | 88.1% | SE ±2.04 pp | $7.9 | 1,357.18source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.095 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.899077 \| USD \| per_test \| Lower is better \| \| `latency` \| 1357.182 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.04 pp sourcePopulation 81 stderr 2.044 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label anthropic/claude-opus-4-7 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/anthropic~1claude-opus-4-7` | | | | | | | | 17 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max | 87.7% | SE ±2.07 pp | $20.68 | 3,099.47source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.698 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 20.677557 \| USD \| per_test \| Lower is better \| \| `latency` \| 3099.466 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.07 pp sourcePopulation 81 stderr 2.073 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/anthropic~1claude-opus-5-5` | | | | | | | | 17 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max | 87.7% | SE ±2.07 pp | $20.46 | 2,972.59source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.698 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 20.461751 \| USD \| per_test \| Lower is better \| \| `latency` \| 2972.586 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.07 pp sourcePopulation 81 stderr 2.073 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/anthropic~1claude-opus-5` | | | | | | | | 19 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash-max.md)Max | 86.91% | SE ±2.13 pp | $0.16 | 555.68source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.905 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.163871 \| USD \| per_test \| Lower is better \| \| `latency` \| 555.678 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature 1 topP 1 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.13 pp sourcePopulation 81 stderr 2.129 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 deepseek/deepseek-v4.1-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/deepseek~1deepseek-v4.1-flash` | | | | | | | | 19 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 86.91% | SE ±2.13 pp | $13.63 | 1,239.72source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.905 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 13.625923 \| USD \| per_test \| Lower is better \| \| `latency` \| 1239.718 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.13 pp sourcePopulation 81 stderr 2.129 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/openai~1gpt-6-astra` | | | | | | | | 21 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 86.51% | SE ±2.16 pp | $0.89 | 1,095.19source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.508 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.888266 \| USD \| per_test \| Lower is better \| \| `latency` \| 1095.19 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.16 pp sourcePopulation 81 stderr 2.156 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 minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/minimax~1MiniMax-M3` | | | | | | | | 22 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-max.md)Max | 85.71% | SE ±2.21 pp | $7.69 | 1,470.57source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.714 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.692416 \| USD \| per_test \| Lower is better \| \| `latency` \| 1470.566 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.21 pp sourcePopulation 81 stderr 2.209 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label anthropic/claude-opus-4-8 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/anthropic~1claude-opus-4-8` | | | | | | | | 23 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max | 85.32% | SE ±2.23 pp | $2.11 | 2,309.22source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.317 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.114472 \| USD \| per_test \| Lower is better \| \| `latency` \| 2309.216 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.23 pp sourcePopulation 81 stderr 2.234 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-6.1-sol Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/openai~1gpt-6.1-sol` | | | | | | | | 23 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-max.md)Max | 85.32% | SE ±2.23 pp | $7.46 | 2,010.35source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.317 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.464714 \| USD \| per_test \| Lower is better \| \| `latency` \| 2010.348 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.23 pp sourcePopulation 81 stderr 2.234 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-sonnet-5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/anthropic~1claude-sonnet-5` | | | | | | | | 25 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-high.md)High | 84.92% | SE ±2.26 pp | $1.59 | 857.59source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.921 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.591969 \| USD \| per_test \| Lower is better \| \| `latency` \| 857.59 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.26 pp sourcePopulation 81 stderr 2.259 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/google~1gemini-3.6-flash` | | | | | | | | 25 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High | 84.92% | SE ±2.26 pp | $2.32 | 912.21source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.921 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.317735 \| USD \| per_test \| Lower is better \| \| `latency` \| 912.208 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.26 pp sourcePopulation 81 stderr 2.259 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 google/gemini-3.7-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/google~1gemini-3.7-flash` | | | | | | | | 27 | [Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max | 84.52% | SE ±2.28 pp | $3.31 | 2,095.02source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.524 \| 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: ±2.28 pp sourcePopulation 81 stderr 2.283 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__international_trade_sanctions/anthropic~1claude-haiku-5-5` | | | | | | | | 28 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-max.md)Max | 83.73% | SE ±2.33 pp | $0.26 | 566.31source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.73 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.257491 \| USD \| per_test \| Lower is better \| \| `latency` \| 566.308 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.33 pp sourcePopulation 81 stderr 2.33 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-5.6-luna Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/openai~1gpt-5.6-luna` | | | | | | | | 29 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 83.33% | SE ±2.35 pp | $0.13 | 676.88source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.129464 \| USD \| per_test \| Lower is better \| \| `latency` \| 676.884 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.35 pp sourcePopulation 81 stderr 2.352 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-6-luna Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/openai~1gpt-6-luna` | | | | | | | | 30 | [DeepSeek V4 Pro](https://benchize.com/models/deepseek-v4-pro-max.md)Max | 82.94% | SE ±2.37 pp | $0.64 | 461.64source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.937 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.642446 \| USD \| per_test \| Lower is better \| \| `latency` \| 461.638 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.37 pp sourcePopulation 81 stderr 2.374 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 deepseek/deepseek-v4-pro Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/deepseek~1deepseek-v4-pro` | | | | | | | | 31 | [Nemotron 3 Ultra](https://benchize.com/models/nemotron-3-ultra-550b-a55b.md) | 82.54% | SE ±2.4 pp | — | 1,963.4source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.54 \| percent \| reported \| Higher is better \| \| `latency` \| 1963.404 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Nvidia reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.4 pp sourcePopulation 81 stderr 2.396 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 nvidia/nemotron-3-ultra-550b-a55b Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/nvidia~1nemotron-3-ultra-550b-a55b` | | | | | | | | 32 | [MiMo-V2.5-Pro](https://benchize.com/models/mimo-v2-5-pro.md) | 81.75% | SE ±2.44 pp | $0.09 | 631.42source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 81.746 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.093679 \| USD \| per_test \| Lower is better \| \| `latency` \| 631.42 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.44 pp sourcePopulation 81 stderr 2.438 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 xiaomi/mimo-v2.5-pro Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/xiaomi~1mimo-v2.5-pro` | | | | | | | | 32 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol-max.md)Max | 81.75% | SE ±2.44 pp | $2.96 | 751.33source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 81.746 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.96028 \| USD \| per_test \| Lower is better \| \| `latency` \| 751.328 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.44 pp sourcePopulation 81 stderr 2.438 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-6-sol Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/openai~1gpt-6-sol` | | | | | | | | 32 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6-max.md)Max | 81.75% | SE ±2.44 pp | $2.39 | 1,055.99source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 81.746 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.391323 \| USD \| per_test \| Lower is better \| \| `latency` \| 1055.988 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning true Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.44 pp sourcePopulation 81 stderr 2.438 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-sonnet-4-6 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/anthropic~1claude-sonnet-4-6` | | | | | | | | 35 | [GPT-5.5](https://benchize.com/models/gpt-5-5-xhigh.md)Extra high | 80.95% | SE ±2.48 pp | $2.36 | 636.4source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.952 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.359423 \| USD \| per_test \| Lower is better \| \| `latency` \| 636.396 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.48 pp sourcePopulation 81 stderr 2.479 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/openai~1gpt-5.5` | | | | | | | | 36 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-max.md)Max | 80.56% | SE ±2.5 pp | $6.24 | 1,023.83source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.556 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.235021 \| USD \| per_test \| Lower is better \| \| `latency` \| 1023.826 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.5 pp sourcePopulation 81 stderr 2.498 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-5.6-sol Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/openai~1gpt-5.6-sol` | | | | | | | | 37 | [MiMo-V2.5](https://benchize.com/models/mimo-v2-5.md) | 79.76% | SE ±2.54 pp | $0.03 | 397.64source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.762 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.026269 \| USD \| per_test \| Lower is better \| \| `latency` \| 397.638 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.54 pp sourcePopulation 81 stderr 2.536 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 xiaomi/mimo-v2.5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/xiaomi~1mimo-v2.5` | | | | | | | | 38 | [MiniMax M2.7](https://benchize.com/models/minimax-m2-7.md) | 78.97% | SE ±2.57 pp | $0.56 | 521.3source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 78.968 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.564526 \| USD \| per_test \| Lower is better \| \| `latency` \| 521.298 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 80000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.57 pp sourcePopulation 81 stderr 2.572 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 minimax/MiniMax-M2.7 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/minimax~1MiniMax-M2.7` | | | | | | | | 39 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High | 78.57% | SE ±2.59 pp | $1.88 | 414.77source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 78.571 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.880602 \| USD \| per_test \| Lower is better \| \| `latency` \| 414.772 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.59 pp sourcePopulation 81 stderr 2.59 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 google/gemini-3.5-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/google~1gemini-3.5-flash` | | | | | | | | 40 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra-max.md)Max | 76.98% | SE ±2.66 pp | $1.85 | 728.32source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 76.984 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.85423 \| USD \| per_test \| Lower is better \| \| `latency` \| 728.318 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.66 pp sourcePopulation 81 stderr 2.657 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label openai/gpt-5.6-terra Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/openai~1gpt-5.6-terra` | | | | | | | | 41 | [Muse Spark Open](https://benchize.com/models/muse-spark-open-xhigh.md)Extra high | 76.19% | SE ±2.69 pp | $9.69 | 12,102.36source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 76.19 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 9.688157 \| USD \| per_test \| Lower is better \| \| `latency` \| 12102.358 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 131072 provider Together AI reasoning Not reported Reasoning effort xhigh Temperature 1 topP 1 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.69 pp sourcePopulation 81 stderr 2.688 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 meta/muse-spark-open Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/meta~1muse-spark-open` | | | | | | | | 42 | [Gemini 3.5 Flash-Lite](https://benchize.com/models/gemini-3-5-flash-lite-high.md)High | 73.81% | SE ±2.78 pp | $0.33 | 271.01source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 73.81 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.333493 \| USD \| per_test \| Lower is better \| \| `latency` \| 271.008 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.78 pp sourcePopulation 81 stderr 2.775 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 google/gemini-3.5-flash-lite Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/google~1gemini-3.5-flash-lite` | | | | | | | | 43 | [Laguna M 1](https://benchize.com/models/laguna-m-1.md) | 68.25% | SE ±2.94 pp | $0.53 | 673.62source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.254 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.52976 \| USD \| per_test \| Lower is better \| \| `latency` \| 673.618 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 32768 provider Poolside reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.94 pp sourcePopulation 81 stderr 2.938 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 poolside/laguna-m.1 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/poolside~1laguna-m.1` | | | | | | | | 44 | [Mercury 2.5](https://benchize.com/models/mercury-2-5-high.md)High | 59.52% | SE ±3.1 pp | $0.18 | 86.68source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.524 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.180981 \| USD \| per_test \| Lower is better \| \| `latency` \| 86.68 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Inception reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.1 pp sourcePopulation 81 stderr 3.098 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 inception/mercury-2.5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/inception~1mercury-2.5` | | | | | | | | 45 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High | 51.98% | SE ±3.15 pp | $0.59 | 551.72source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 51.984 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.590442 \| USD \| per_test \| Lower is better \| \| `latency` \| 551.724 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.15 pp sourcePopulation 81 stderr 3.153 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 google/gemini-3.1-pro-preview Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/google~1gemini-3.1-pro-preview` | | | | | | | | 46 | [Mistral Medium 3.5](https://benchize.com/models/mistral-medium-3-5-high.md)High | 45.64% | SE ±3.14 pp | $3.38 | 2,783.9source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 45.635 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.380109 \| USD \| per_test \| Lower is better \| \| `latency` \| 2783.904 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 80000 provider Mistral AI reasoning Not reported Reasoning effort high Temperature 0.7 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.14 pp sourcePopulation 81 stderr 3.144 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 mistralai/mistral-medium-3.5 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/mistralai~1mistral-medium-3.5` | | | | | | | | 47 | [Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High | 40.87% | SE ±3.1 pp | $0.23 | 292.1source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 40.873 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.228541 \| USD \| per_test \| Lower is better \| \| `latency` \| 292.1 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.1 pp sourcePopulation 81 stderr 3.103 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 google/gemini-3-flash-preview Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/google~1gemini-3-flash-preview` | | | | | | | | 48 | [Gemini 3.1 Flash Lite Preview](https://benchize.com/models/gemini-3-1-flash-lite-preview-high.md)High | 32.14% | SE ±2.95 pp | $0.05 | 47.57source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 32.143 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.051418 \| USD \| per_test \| Lower is better \| \| `latency` \| 47.572 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.95 pp sourcePopulation 81 stderr 2.948 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 google/gemini-3.1-flash-lite-preview Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/google~1gemini-3.1-flash-lite-preview` | | | | | | | | 49 | [Laguna Xs 2](https://benchize.com/models/laguna-xs-2.md) | 0% | SE ±0 pp | — | — | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 32768 provider Poolside reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label poolside/laguna-xs.2 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/poolside~1laguna-xs.2` | | | | | | | --- Cite as: Harvey's Legal Agent Benchmark v1 / criteria pass rate international trade sanctions — Benchize, https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__international_trade_sanctions (retrieved 2026-10-21)