Atlas

Benchmarks

← All benchmarks

Harvey HLAB - Criteria Pass Rate - Corporate M&A

Professional Work · 2026-05-06

The Corporate M&A practice-area split of Harvey's Legal Agent Benchmark held-out evaluation criteria pass rate. This reports pooled rubric criteria passed within that split and is distinct from the all-pass task-score split.

Top models (higher is better)

ModelScore
Muse Spark 1.196.2
Grok 4.595.2
Claude Opus 593.9
Kimi K393.3
Opus 4.892.9
Claude Fable 592.0
Sonnet 4.691.0
Kimi K2.691.0
MiniMax M390.1
Qwen3.7-Max88.8
Sonnet 588.5
DeepSeek-V4-Pro88.5
Gemini 3.6 Flash87.5
GPT-5.587.5
GPT-5.6 Luna87.2
Gemini 3.5 Flash86.5
GLM-5.185.9
GPT-5.6 Sol85.6
GPT-5.6 Terra83.0
GPT-5.481.7
GLM-5.278.8
Gemini 3.5 Flash-Lite77.2
Grok 4.370.2
Qwen3.7-Plus61.2
Laguna M.159.0
Inkling58.7
Laguna XS.238.5
Loading Atlas data…