Atlas

Benchmarks

← All benchmarks

Harvey HLAB - Criteria Pass Rate - International Trade Sanctions

Professional Work · 2026-05-06

The International Trade Sanctions 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
Claude Fable 592.5
Kimi K392.1
Muse Spark 1.190.0
Grok 4.589.7
Claude Opus 587.7
Inkling86.5
MiniMax M386.5
Opus 4.885.7
Sonnet 585.3
Gemini 3.6 Flash84.9
GPT-5.6 Luna83.7
Kimi K2.683.7
DeepSeek-V4-Pro82.9
Sonnet 4.681.7
GPT-5.581.0
GPT-5.6 Sol80.6
GLM-5.180.2
Qwen3.7-Max79.4
Gemini 3.5 Flash78.6
GPT-5.6 Terra76.2
GPT-5.474.6
Gemini 3.5 Flash-Lite73.8
GLM-5.271.0
Qwen3.7-Plus71.0
Laguna M.168.3
Grok 4.367.1
Laguna XS.20.0
Loading Atlas data…