Atlas

Benchmarks

← All benchmarks

HLAB-Vals-1.1 - Healthcare Life Sciences

Professional Work · 2026-10-19

Mean of two judges' task pass rates on the Healthcare Life Sciences practice-area tasks of HLAB-Vals-1.1.

Top models (higher is better)

ModelScore
Gemini 4 Argon60.0
GLM-5.3 Flash40.0
Kimi K340.0
MiMo-V2.6-Pro40.0
Mistral Large 4 Preview40.0
Muse Spark Open40.0
Muse Wonder Full40.0
DeepSeek V4.1 Flash 101730.0
Gemini 3.8 Flash30.0
GLM-5.330.0
Beam 1.0 501B A23B20.0
Claude Haiku 5.520.0
Claude Opus 5.520.0
Claude Sonnet 5.520.0
DeepSeek V4 Pro 081320.0
Grok 4.720.0
Mercury 320.0
MiniMax M3.1 Flash20.0
Muse Wonder20.0
GPT-6 Astra10.0
GPT-6 Luna10.0
Inkling-Small10.0
MiMo-V2.6-Flash10.0
GPT-6.1 Sol0.0
Hy4 Preview0.0
Inkling0.0
Loading Atlas data…