# HLAB-Vals-1.1 / criteria pass rate arbitration international dispute resolution > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__arbitration_international_dispute_resolution. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__arbitration_international_dispute_resolution. 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%3Acriteria_pass_rate__arbitration_international_dispute_resolution 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: 14 · Score publishers: Vals AI ## Model results | # | Model | Score | ± | Cost | Latency | | | --- | --- | --- | --- | --- | --- | --- | | 1 | [MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md) | 96.95% | SE ±1.03 pp | $0.1 | 1,107.1source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.953 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.098258 \| USD \| per_test \| Lower is better \| \| `latency` \| 1107.096 \| 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: ±1.03 pp sourcePopulation 24 stderr 1.031 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label xiaomi/mimo-v2.6-flash Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__arbitration_international_dispute_resolution/xiaomi~1mimo-v2.6-flash` | | | | | | | | 2 | [DeepSeek V4 Pro 0813](https://benchize.com/models/deepseek-v4-pro-0813-max.md)Max | 96.24% | SE ±1.14 pp | $0.93 | 626.44source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.237 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.933152 \| USD \| per_test \| Lower is better \| \| `latency` \| 626.442 \| 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: ±1.14 pp sourcePopulation 24 stderr 1.141 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__arbitration_international_dispute_resolution/deepseek~1deepseek-v4-pro-0813` | | | | | | | | 3 | [Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High | 96.06% | SE ±1.17 pp | $12.52 | 2,222.16source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.057 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 12.524633 \| USD \| per_test \| Lower is better \| \| `latency` \| 2222.162 \| 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 Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.17 pp sourcePopulation 24 stderr 1.167 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label google/gemini-4-argon Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__arbitration_international_dispute_resolution/google~1gemini-4-argon` | | | | | | | | 4 | [Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max | 95.88% | SE ±1.19 pp | $6.85 | 842.76source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.878 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.853377 \| USD \| per_test \| Lower is better \| \| `latency` \| 842.758 \| 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: ±1.19 pp sourcePopulation 24 stderr 1.192 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label meta/muse-wonder Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__arbitration_international_dispute_resolution/meta~1muse-wonder` | | | | | | | | 5 | [MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md) | 95.52% | SE ±1.24 pp | $0.23 | 1,735.19source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.52 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.22831 \| USD \| per_test \| Lower is better \| \| `latency` \| 1735.19 \| 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: ±1.24 pp sourcePopulation 24 stderr 1.241 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label xiaomi/mimo-v2.6-pro Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__arbitration_international_dispute_resolution/xiaomi~1mimo-v2.6-pro` | | | | | | | | 6 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max | 92.83% | SE ±1.55 pp | $16.01 | 5,100.89source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.832 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 16.01159 \| USD \| per_test \| Lower is better \| \| `latency` \| 5100.89 \| 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: ±1.55 pp sourcePopulation 24 stderr 1.547 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-sonnet-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__arbitration_international_dispute_resolution/anthropic~1claude-sonnet-5-5` | | | | | | | | 7 | [DeepSeek V4.1 Flash 1017](https://benchize.com/models/deepseek-v4-1-flash-1017-max.md)Max | 91.76% | SE ±1.65 pp | $0.67 | 1,273.8source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.756 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.66721 \| USD \| per_test \| Lower is better \| \| `latency` \| 1273.796 \| 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: ±1.65 pp sourcePopulation 24 stderr 1.65 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4.1-flash-1017 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__arbitration_international_dispute_resolution/deepseek~1deepseek-v4.1-flash-1017` | | | | | | | | 7 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 91.76% | SE ±1.65 pp | $4.27 | 1,260.93source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.756 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.266851 \| USD \| per_test \| Lower is better \| \| `latency` \| 1260.926 \| 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 Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.65 pp sourcePopulation 24 stderr 1.65 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label google/gemini-3.8-flash Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__arbitration_international_dispute_resolution/google~1gemini-3.8-flash` | | | | | | | | 9 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max | 91.58% | SE ±1.67 pp | $22.28 | 3,841.33source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.577 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 22.280508 \| USD \| per_test \| Lower is better \| \| `latency` \| 3841.334 \| 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 24 stderr 1.666 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__arbitration_international_dispute_resolution/anthropic~1claude-opus-5-5` | | | | | | | | 10 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 91.22% | SE ±1.7 pp | $37.28 | 2,052.19source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.219 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 37.28026 \| USD \| per_test \| Lower is better \| \| `latency` \| 2052.194 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.7 pp sourcePopulation 24 stderr 1.697 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__arbitration_international_dispute_resolution/openai~1gpt-6-astra` | | | | | | | | 11 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max | 91.04% | SE ±1.71 pp | $5.1 | 2,687.46source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.039 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.097847 \| USD \| per_test \| Lower is better \| \| `latency` \| 2687.456 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.71 pp sourcePopulation 24 stderr 1.713 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label openai/gpt-6.1-sol Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__arbitration_international_dispute_resolution/openai~1gpt-6.1-sol` | | | | | | | | 12 | [Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max | 90.68% | SE ±1.74 pp | $5.27 | 3,010.74source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.681 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.265369 \| USD \| per_test \| Lower is better \| \| `latency` \| 3010.736 \| 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 1.743 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__arbitration_international_dispute_resolution/anthropic~1claude-haiku-5-5` | | | | | | | | 13 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 90.14% | SE ±1.79 pp | $0.42 | 1,371.91source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.143 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.423667 \| USD \| per_test \| Lower is better \| \| `latency` \| 1371.914 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.79 pp sourcePopulation 24 stderr 1.788 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label openai/gpt-6-luna Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__arbitration_international_dispute_resolution/openai~1gpt-6-luna` | | | | | | | | 14 | [MiniMax M3.1 Flash](https://benchize.com/models/minimax-m3-1-flash-max.md)Max | 88.35% | SE ±1.92 pp | $0.57 | 1,490.44source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.351 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.572096 \| USD \| per_test \| Lower is better \| \| `latency` \| 1490.442 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 262144 provider MiniMax reasoning Not reported Reasoning effort max Temperature 1 topP 0.95 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 minimax/MiniMax-M3.1-flash Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__arbitration_international_dispute_resolution/minimax~1MiniMax-M3.1-flash` | | | | | | | --- Cite as: HLAB-Vals-1.1 / criteria pass rate arbitration international dispute resolution — Benchize, https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__arbitration_international_dispute_resolution (retrieved 2026-10-21)