Atlas

Benchmarks

← All benchmarks

Harvey HLAB - Criteria Pass Rate - Capital Markets

Professional Work · 2026-05-06

The Capital Markets 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 4.594.5
Muse Spark 1.192.5
Opus 4.892.2
Kimi K392.2
Gemini 3.6 Flash91.8
Claude Fable 591.4
Sonnet 589.0
MiniMax M389.0
Claude Opus 587.5
GLM-5.287.1
GPT-5.6 Luna87.1
Sonnet 4.686.7
DeepSeek-V4-Pro86.3
GPT-5.6 Terra85.9
Qwen3.7-Max84.7
Gemini 3.5 Flash82.7
GPT-5.481.6
Gemini 3.5 Flash-Lite77.6
Grok 4.374.9
GPT-5.573.7
Qwen3.7-Plus72.9
Kimi K2.672.2
GLM-5.171.8
Inkling71.8
GPT-5.6 Sol71.4
Laguna M.156.1
Laguna XS.254.5
Loading Atlas data…