Atlas

Benchmarks

← All benchmarks

HLAB-Vals-1.1 - Criteria Pass Rate - Healthcare Life Sciences

Professional Work · 2026-10-19

Criteria pass rate (judge-averaged, Harvey's definition) on the Healthcare Life Sciences practice-area tasks of HLAB-Vals-1.1, distinct from that area's task pass rate.

Top models (higher is better)

ModelScore
Gemini 4 Argon97.8
Kimi K397.3
Mistral Large 4 Preview96.8
Muse Wonder Full96.6
GLM-5.396.1
DeepSeek V4.1 Flash 101796.0
GLM-5.3 Flash96.0
MiMo-V2.6-Pro96.0
MiMo-V2.6-Flash95.3
Grok 4.795.1
MiniMax M3.1 Flash95.1
Muse Wonder95.1
Gemini 3.8 Flash94.6
Claude Sonnet 5.594.1
Beam 1.0 501B A23B93.6
GPT-6 Astra93.3
Mercury 393.3
Claude Opus 5.592.8
DeepSeek V4 Pro 081392.1
Claude Haiku 5.591.9
GPT-6.1 Sol91.6
Hy4 Preview91.4
Inkling-Small90.8
GPT-6 Luna87.1
Muse Spark Open74.0
Inkling40.3
Loading Atlas data…