Harvey's Legal Agent BenchmarkBrowse 296

Harvey's Legal Agent Benchmark

Can the model produce useful work in a professional knowledge-work setting?

Version not specifiedExact reported variant
Knowledge Work7 ranked models7 reported values2 reportsHigher is better

Top rankings

One row per model, using its best reported score across effort settings.

7
RankModelBest scoreBest reported setting
1Grok 4.7SpaceXAI19.6%xhigh effortSpaceXAI report1 value · 1 reportSep 21, 2026 · source
2Gemini 3.8 FlashGoogle10.0%Reported configurationGoogle DeepMind report1 value · 1 reportSep 2, 2026 · source
3Gemini 3.7 FlashGoogle8.8%Reported configurationGoogle DeepMind report1 value · 1 reportSep 2, 2026 · source
4Claude Opus 5Anthropic6.7%Reported configurationGoogle DeepMind report1 value · 1 reportSep 2, 2026 · source
5Claude Sonnet 5Anthropic5.0%Reported configurationGoogle DeepMind report1 value · 1 reportSep 2, 2026 · source
6GPT-5.6 SolOpenAI2.5%Reported configurationGoogle DeepMind report1 value · 1 reportSep 2, 2026 · source
7GPT-5.6 TerraOpenAI0.8%Reported configurationGoogle DeepMind report1 value · 1 reportSep 2, 2026 · source

Effort curve

Every sourced cost-linked effort value for this exact version. Lines connect complete sweeps only.

0
No cost-linked effort sweep for this version.
Definition and comparison boundarypublic methodology

Can the model produce useful work in a professional knowledge-work setting?

Professional analysis, document, finance, office, or domain-specific tasks. Higher is better. The value is the percentage reported in this lab's table.

Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.

SpaceXAI reports 19.6% for Grok 4.7 at xhigh; the table labels this metric as legal work but does not print the harness or task revision. Complex legal workflows; the model card labels this metric All pass rate.

Method / source