# Harvey's Legal Agent Benchmark v1 / criteria pass rate energy natural resources > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__energy_natural_resources. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__energy_natural_resources. 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__energy_natural_resources 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 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high | 98.68% | SE ±0.66 pp | $3.51 | 2,031.21source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 98.68 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.505056 \| USD \| per_test \| Lower is better \| \| `latency` \| 2031.21 \| 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: ±0.66 pp sourcePopulation 81 stderr 0.657 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 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__energy_natural_resources/meta~1muse_spark_1_2` | | | | | | | | 2 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-max.md)Max | 97.03% | SE ±0.98 pp | $17.56 | 1,738.25source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 97.03 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 17.557582 \| USD \| per_test \| Lower is better \| \| `latency` \| 1738.252 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.98 pp sourcePopulation 81 stderr 0.977 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__energy_natural_resources/anthropic~1claude-opus-4-8` | | | | | | | | 3 | [DeepSeek V4 Pro 0813](https://benchize.com/models/deepseek-v4-pro-0813-max.md)Max | 96.7% | SE ±1.03 pp | $0.22 | 1,538.62source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.7 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.224328 \| USD \| per_test \| Lower is better \| \| `latency` \| 1538.616 \| 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: ±1.03 pp sourcePopulation 81 stderr 1.028 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__energy_natural_resources/deepseek~1deepseek-v4-pro-0813` | | | | | | | | 3 | [Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High | 96.7% | SE ±1.03 pp | $14.06 | 3,028.42source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.7 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 14.055481 \| USD \| per_test \| Lower is better \| \| `latency` \| 3028.416 \| 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: ±1.03 pp sourcePopulation 81 stderr 1.028 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__energy_natural_resources/google~1gemini-4-argon` | | | | | | | | 5 | [Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3-xhigh.md)Extra high | 96.37% | SE ±1.08 pp | $7.73 | 1,638.98source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.37 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.731016 \| USD \| per_test \| Lower is better \| \| `latency` \| 1638.978 \| 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: ±1.08 pp sourcePopulation 81 stderr 1.076 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__energy_natural_resources/meta~1muse_spark_1_3` | | | | | | | | 5 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1-xhigh.md)Extra high | 96.37% | SE ±1.08 pp | $1.22 | 1,031.51source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.37 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.224794 \| USD \| per_test \| Lower is better \| \| `latency` \| 1031.512 \| 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: ±1.08 pp sourcePopulation 81 stderr 1.076 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__energy_natural_resources/meta~1muse_spark_1_1` | | | | | | | | 5 | [MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md) | 96.37% | SE ±1.08 pp | $0.29 | 1,774.8source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.37 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.288516 \| USD \| per_test \| Lower is better \| \| `latency` \| 1774.802 \| 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: ±1.08 pp sourcePopulation 81 stderr 1.076 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__energy_natural_resources/xiaomi~1mimo-v2.6-pro` | | | | | | | | 5 | [MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md) | 96.37% | SE ±1.08 pp | $0.13 | 1,540.42source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.37 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.125628 \| USD \| per_test \| Lower is better \| \| `latency` \| 1540.416 \| 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: ±1.08 pp sourcePopulation 81 stderr 1.076 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__energy_natural_resources/xiaomi~1mimo-v2.6-flash` | | | | | | | | 5 | [Step 5 Preview](https://benchize.com/models/step-5-preview.md) | 96.37% | SE ±1.08 pp | $1.16 | 1,767.97source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.37 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.160357 \| USD \| per_test \| Lower is better \| \| `latency` \| 1767.97 \| 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: ±1.08 pp sourcePopulation 81 stderr 1.076 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__energy_natural_resources/stepfun~1step-5-preview` | | | | | | | | 10 | [Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max | 96.04% | SE ±1.12 pp | $32.18 | 1,808.58source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.04 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 32.1783 \| USD \| per_test \| Lower is better \| \| `latency` \| 1808.578 \| 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: ±1.12 pp sourcePopulation 81 stderr 1.122 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__energy_natural_resources/anthropic~1claude-fable-5` | | | | | | | | 11 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max | 95.71% | SE ±1.17 pp | $5.85 | 2,822.94source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.71 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.852595 \| USD \| per_test \| Lower is better \| \| `latency` \| 2822.94 \| 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: ±1.17 pp sourcePopulation 81 stderr 1.166 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__energy_natural_resources/openai~1gpt-6.1-sol` | | | | | | | | 11 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High | 95.71% | SE ±1.17 pp | $3.89 | 447.69source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.71 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.885089 \| USD \| per_test \| Lower is better \| \| `latency` \| 447.692 \| 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: ±1.17 pp sourcePopulation 81 stderr 1.166 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__energy_natural_resources/google~1gemini-3.7-flash` | | | | | | | | 11 | [DeepSeek V4.1 Flash 1017](https://benchize.com/models/deepseek-v4-1-flash-1017-max.md)Max | 95.71% | SE ±1.17 pp | $0.57 | 1,200.08source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.71 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.569183 \| USD \| per_test \| Lower is better \| \| `latency` \| 1200.084 \| 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: ±1.17 pp sourcePopulation 81 stderr 1.166 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__energy_natural_resources/deepseek~1deepseek-v4.1-flash-1017` | | | | | | | | 14 | [Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max | 95.38% | SE ±1.21 pp | $11.54 | 1,527.86source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.38 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 11.537685 \| USD \| per_test \| Lower is better \| \| `latency` \| 1527.862 \| 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: ±1.21 pp sourcePopulation 81 stderr 1.208 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__energy_natural_resources/meta~1muse-wonder` | | | | | | | | 14 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 95.38% | SE ±1.21 pp | $4.41 | 3,374.35source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.38 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.405884 \| USD \| per_test \| Lower is better \| \| `latency` \| 3374.346 \| 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: ±1.21 pp sourcePopulation 81 stderr 1.208 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__energy_natural_resources/google~1gemini-3.8-flash` | | | | | | | | 16 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max | 95.05% | SE ±1.25 pp | $31.65 | 3,747.78source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.05 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 31.649398 \| USD \| per_test \| Lower is better \| \| `latency` \| 3747.78 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.25 pp sourcePopulation 81 stderr 1.248 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__energy_natural_resources/anthropic~1claude-opus-5` | | | | | | | | 16 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6-max.md)Max | 95.05% | SE ±1.25 pp | $4.48 | 1,396.08source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.05 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.475508 \| USD \| per_test \| Lower is better \| \| `latency` \| 1396.084 \| 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: ±1.25 pp sourcePopulation 81 stderr 1.248 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__energy_natural_resources/anthropic~1claude-sonnet-4-6` | | | | | | | | 18 | [Mistral Medium 3.5](https://benchize.com/models/mistral-medium-3-5-high.md)High | 94.44% | SE ±1.71 pp | $9.06 | 4,775.52source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 94.444 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 9.063118 \| USD \| per_test \| Lower is better \| \| `latency` \| 4775.52 \| 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: ±1.71 pp sourcePopulation 81 stderr 1.712 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__energy_natural_resources/mistralai~1mistral-medium-3.5` | | | | | | | | 19 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-max.md)Max | 94.06% | SE ±1.36 pp | $14.54 | 1,560.88source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 94.059 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 14.535287 \| USD \| per_test \| Lower is better \| \| `latency` \| 1560.884 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.36 pp sourcePopulation 81 stderr 1.36 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__energy_natural_resources/anthropic~1claude-opus-4-7` | | | | | | | | 19 | [DeepSeek V4 Flash 0731](https://benchize.com/models/deepseek-v4-flash-0731-high.md)High | 94.06% | SE ±1.36 pp | $0.1 | 1,183.83source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 94.059 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.100514 \| USD \| per_test \| Lower is better \| \| `latency` \| 1183.832 \| 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: ±1.36 pp sourcePopulation 81 stderr 1.36 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__energy_natural_resources/deepseek~1deepseek-v4-flash-0731` | | | | | | | | 21 | [GPT-5.5](https://benchize.com/models/gpt-5-5-xhigh.md)Extra high | 93.73% | SE ±1.4 pp | $11.83 | 1,415.76source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 93.729 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 11.82685 \| USD \| per_test \| Lower is better \| \| `latency` \| 1415.76 \| 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: ±1.4 pp sourcePopulation 81 stderr 1.395 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__energy_natural_resources/openai~1gpt-5.5` | | | | | | | | 22 | [DeepSeek V4 Pro](https://benchize.com/models/deepseek-v4-pro-max.md)Max | 93.4% | SE ±1.43 pp | $0.98 | 388.47source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 93.399 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.983444 \| USD \| per_test \| Lower is better \| \| `latency` \| 388.468 \| 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: ±1.43 pp sourcePopulation 81 stderr 1.429 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__energy_natural_resources/deepseek~1deepseek-v4-pro` | | | | | | | | 22 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 93.4% | SE ±1.43 pp | $1.8 | 1,700.96source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 93.399 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.80131 \| USD \| per_test \| Lower is better \| \| `latency` \| 1700.96 \| 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: ±1.43 pp sourcePopulation 81 stderr 1.429 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__energy_natural_resources/minimax~1MiniMax-M3` | | | | | | | | 24 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash-max.md)Max | 93.07% | SE ±1.46 pp | $0.22 | 398.4source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 93.069 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.219636 \| USD \| per_test \| Lower is better \| \| `latency` \| 398.398 \| 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: ±1.46 pp sourcePopulation 81 stderr 1.461 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__energy_natural_resources/deepseek~1deepseek-v4.1-flash` | | | | | | | | 25 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-max.md)Max | 92.74% | SE ±1.49 pp | $17.77 | 1,722.81source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.739 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 17.774066 \| USD \| per_test \| Lower is better \| \| `latency` \| 1722.806 \| 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: ±1.49 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 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__energy_natural_resources/openai~1gpt-5.6-sol` | | | | | | | | 25 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol-max.md)Max | 92.74% | SE ±1.49 pp | $8.24 | 1,169.82source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.739 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.24435 \| USD \| per_test \| Lower is better \| \| `latency` \| 1169.822 \| 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: ±1.49 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 openai/gpt-6-sol Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__energy_natural_resources/openai~1gpt-6-sol` | | | | | | | | 27 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 92.41% | SE ±1.52 pp | $50.66 | 1,943.2source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.409 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 50.660049 \| USD \| per_test \| Lower is better \| \| `latency` \| 1943.202 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.52 pp sourcePopulation 81 stderr 1.524 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__energy_natural_resources/openai~1gpt-6-astra` | | | | | | | | 28 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-max.md)Max | 91.75% | SE ±1.58 pp | $0.61 | 753.42source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.749 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.613118 \| USD \| per_test \| Lower is better \| \| `latency` \| 753.42 \| 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: ±1.58 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 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__energy_natural_resources/openai~1gpt-5.6-luna` | | | | | | | | 29 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-max.md)Max | 91.42% | SE ±1.61 pp | $13.63 | 2,085.85source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.419 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 13.632671 \| USD \| per_test \| Lower is better \| \| `latency` \| 2085.852 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.61 pp sourcePopulation 81 stderr 1.612 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__energy_natural_resources/anthropic~1claude-sonnet-5` | | | | | | | | 30 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra-max.md)Max | 90.76% | SE ±1.67 pp | $4.84 | 1,571.69source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.759 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.843052 \| USD \| per_test \| Lower is better \| \| `latency` \| 1571.69 \| 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: ±1.67 pp sourcePopulation 81 stderr 1.666 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__energy_natural_resources/openai~1gpt-5.6-terra` | | | | | | | | 31 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 89.77% | SE ±1.74 pp | $0.67 | 1,207.45source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.769 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.670627 \| USD \| per_test \| Lower is better \| \| `latency` \| 1207.448 \| 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: ±1.74 pp sourcePopulation 81 stderr 1.744 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__energy_natural_resources/openai~1gpt-6-luna` | | | | | | | | 32 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-high.md)High | 88.12% | SE ±1.86 pp | $1.81 | 1,203.2source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.119 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.814778 \| USD \| per_test \| Lower is better \| \| `latency` \| 1203.204 \| 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: ±1.86 pp sourcePopulation 81 stderr 1.862 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__energy_natural_resources/google~1gemini-3.6-flash` | | | | | | | | 33 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High | 85.48% | SE ±2.03 pp | $2.01 | 458.45source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.479 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.006452 \| USD \| per_test \| Lower is better \| \| `latency` \| 458.446 \| 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: ±2.03 pp sourcePopulation 81 stderr 2.027 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__energy_natural_resources/google~1gemini-3.5-flash` | | | | | | | | 34 | [MiMo-V2.5-Pro](https://benchize.com/models/mimo-v2-5-pro.md) | 83.5% | SE ±2.14 pp | $0.14 | 411.3source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.498 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.138008 \| USD \| per_test \| Lower is better \| \| `latency` \| 411.296 \| 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: ±2.14 pp sourcePopulation 81 stderr 2.136 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__energy_natural_resources/xiaomi~1mimo-v2.5-pro` | | | | | | | | 34 | [MiMo-V2.5](https://benchize.com/models/mimo-v2-5.md) | 83.5% | SE ±2.14 pp | $0.04 | 413.79source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.498 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.042392 \| USD \| per_test \| Lower is better \| \| `latency` \| 413.794 \| 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: ±2.14 pp sourcePopulation 81 stderr 2.136 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__energy_natural_resources/xiaomi~1mimo-v2.5` | | | | | | | | 36 | [Gemini 3.5 Flash-Lite](https://benchize.com/models/gemini-3-5-flash-lite-high.md)High | 73.93% | SE ±2.53 pp | $0.33 | 360.4source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 73.927 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.330094 \| USD \| per_test \| Lower is better \| \| `latency` \| 360.398 \| 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: ±2.53 pp sourcePopulation 81 stderr 2.526 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__energy_natural_resources/google~1gemini-3.5-flash-lite` | | | | | | | | 37 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max | 71.95% | SE ±2.59 pp | $54.27 | 7,358.54source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 71.947 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 54.268239 \| USD \| per_test \| Lower is better \| \| `latency` \| 7358.538 \| 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: ±2.59 pp sourcePopulation 81 stderr 2.585 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__energy_natural_resources/anthropic~1claude-fable-5-1` | | | | | | | | 38 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max | 64.68% | SE ±3.02 pp | $26.38 | 3,653.83source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 64.683 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 26.383042 \| USD \| per_test \| Lower is better \| \| `latency` \| 3653.828 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.02 pp sourcePopulation 81 stderr 3.017 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__energy_natural_resources/anthropic~1claude-opus-5-5` | | | | | | | | 39 | [Muse Spark Open](https://benchize.com/models/muse-spark-open-xhigh.md)Extra high | 55.12% | SE ±2.86 pp | $7.23 | 4,399.51source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 55.116 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.228934 \| USD \| per_test \| Lower is better \| \| `latency` \| 4399.508 \| 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: ±2.86 pp sourcePopulation 81 stderr 2.862 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__energy_natural_resources/meta~1muse-spark-open` | | | | | | | | 40 | [Laguna M 1](https://benchize.com/models/laguna-m-1.md) | 54.13% | SE ±2.87 pp | $0.46 | 384.89source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 54.125 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.461391 \| USD \| per_test \| Lower is better \| \| `latency` \| 384.886 \| 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: ±2.87 pp sourcePopulation 81 stderr 2.867 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__energy_natural_resources/poolside~1laguna-m.1` | | | | | | | | 41 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High | 52.15% | SE ±2.88 pp | $1.92 | 350.94source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.145 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.916498 \| USD \| per_test \| Lower is better \| \| `latency` \| 350.94 \| 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: ±2.88 pp sourcePopulation 81 stderr 2.875 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__energy_natural_resources/google~1gemini-3.1-pro-preview` | | | | | | | | 42 | [Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High | 48.19% | SE ±2.88 pp | $0.37 | 327.08source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.185 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.37291 \| USD \| per_test \| Lower is better \| \| `latency` \| 327.076 \| 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: ±2.88 pp sourcePopulation 81 stderr 2.875 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__energy_natural_resources/google~1gemini-3-flash-preview` | | | | | | | | 43 | [Gemini 3.1 Flash Lite Preview](https://benchize.com/models/gemini-3-1-flash-lite-preview-high.md)High | 38.28% | SE ±2.8 pp | $0.21 | 87.67source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 38.284 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.205085 \| USD \| per_test \| Lower is better \| \| `latency` \| 87.666 \| 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: ±2.8 pp sourcePopulation 81 stderr 2.797 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__energy_natural_resources/google~1gemini-3.1-flash-lite-preview` | | | | | | | | 44 | [Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max | 33% | SE ±2.71 pp | $3.63 | 1,976.13source duration | | | ### 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` | | | | | | | | 45 | [Laguna Xs 2](https://benchize.com/models/laguna-xs-2.md) | 31.94% | SE ±5.53 pp | $0.54 | 1,391.76source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 31.944 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.539658 \| USD \| per_test \| Lower is better \| \| `latency` \| 1391.76 \| 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: ±5.53 pp sourcePopulation 81 stderr 5.534 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__energy_natural_resources/poolside~1laguna-xs.2` | | | | | | | | 46 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max | 30.36% | SE ±2.65 pp | $17.61 | 3,233.78source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 30.363 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 17.609237 \| USD \| per_test \| Lower is better \| \| `latency` \| 3233.776 \| 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: ±2.65 pp sourcePopulation 81 stderr 2.646 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__energy_natural_resources/anthropic~1claude-sonnet-5-5` | | | | | | | | 47 | [Mercury 2.5](https://benchize.com/models/mercury-2-5-high.md)High | 28.05% | SE ±2.59 pp | $0.16 | 382.35source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 28.053 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.164729 \| USD \| per_test \| Lower is better \| \| `latency` \| 382.348 \| 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: ±2.59 pp sourcePopulation 81 stderr 2.585 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__energy_natural_resources/inception~1mercury-2.5` | | | | | | | | 48 | [MiniMax M2.7](https://benchize.com/models/minimax-m2-7.md) | 21.12% | SE ±2.35 pp | $0.24 | 93.15source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 21.122 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.235869 \| USD \| per_test \| Lower is better \| \| `latency` \| 93.152 \| 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: ±2.35 pp sourcePopulation 81 stderr 2.349 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__energy_natural_resources/minimax~1MiniMax-M2.7` | | | | | | | | 49 | [Nemotron 3 Ultra](https://benchize.com/models/nemotron-3-ultra-550b-a55b.md) | 7.76% | SE ±1.71 pp | — | 1,283.06source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 7.755 \| percent \| reported \| Higher is better \| \| `latency` \| 1283.055 \| 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: ±1.71 pp sourcePopulation 81 stderr 1.712 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__energy_natural_resources/nvidia~1nemotron-3-ultra-550b-a55b` | | | | | | | --- Cite as: Harvey's Legal Agent Benchmark v1 / criteria pass rate energy natural resources — Benchize, https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__energy_natural_resources (retrieved 2026-10-21)