Atlas

Benchmarks

← All benchmarks

Harvey HLAB - Criteria Pass Rate - Healthcare Life Sciences

Professional Work · 2026-05-06

The Healthcare Life Sciences 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
Grok 4.592.7
Muse Spark 1.192.7
Claude Fable 591.4
Opus 4.891.4
GLM-5.291.4
Kimi K391.1
Claude Opus 590.8
MiniMax M389.8
Sonnet 4.688.8
Gemini 3.6 Flash87.1
DeepSeek-V4-Pro86.1
Sonnet 585.5
Qwen3.7-Max84.8
GPT-5.6 Sol82.5
GPT-5.581.8
Gemini 3.5 Flash80.5
GPT-5.6 Luna78.2
GPT-5.474.3
GPT-5.6 Terra73.6
Grok 4.372.6
Qwen3.7-Plus69.3
GLM-5.168.0
Kimi K2.663.4
Gemini 3.5 Flash-Lite60.4
Laguna M.160.1
Inkling43.2
Laguna XS.242.9
Loading Atlas data…