Atlas

Benchmarks

← All benchmarks

Harvey HLAB - Criteria Pass Rate - Environmental ESG

Professional Work · 2026-05-06

The Environmental ESG 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 1.192.5
Grok 4.591.4
Kimi K389.2
Claude Fable 587.8
GLM-5.287.8
Opus 4.886.7
Sonnet 4.685.7
Sonnet 583.9
DeepSeek-V4-Pro83.9
Gemini 3.6 Flash83.5
MiniMax M383.5
GPT-5.582.1
Qwen3.7-Max81.0
GPT-5.6 Sol80.6
Kimi K2.679.2
GLM-5.178.5
GPT-5.6 Luna77.4
GPT-5.6 Terra73.5
Gemini 3.5 Flash72.8
GPT-5.472.4
Claude Opus 572.0
Gemini 3.5 Flash-Lite67.7
Inkling62.4
Grok 4.362.0
Laguna M.160.9
Qwen3.7-Plus55.5
Laguna XS.238.5
Loading Atlas data…