Atlas

Benchmarks

← All benchmarks

HLAB-Vals-1.1 - Criteria Pass Rate - Insurance

Professional Work · 2026-10-19

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

Top models (higher is better)

ModelScore
Gemini 4 Argon96.3
Muse Wonder96.1
Muse Wonder Full96.0
Grok 4.794.9
DeepSeek V4.1 Flash 101794.5
Gemini 3.8 Flash94.3
MiMo-V2.6-Pro94.3
MiMo-V2.6-Flash93.8
Mistral Large 4 Preview93.4
Claude Opus 5.593.2
Claude Sonnet 5.592.8
Kimi K392.1
DeepSeek V4 Pro 081391.7
GPT-6 Astra91.7
GLM-5.3 Flash91.5
GLM-5.391.5
GPT-6.1 Sol91.2
Claude Haiku 5.590.8
Hy4 Preview90.4
MiniMax M3.1 Flash90.1
Beam 1.0 501B A23B89.3
Inkling89.0
Mercury 389.0
GPT-6 Luna85.8
Inkling-Small82.9
Muse Spark Open59.7
Loading Atlas data…