Atlas

Benchmarks

← All benchmarks

HLAB-Vals-1.1 - Criteria Pass Rate - Banking Finance

Professional Work · 2026-10-19

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

Top models (higher is better)

ModelScore
Muse Wonder Full97.6
Gemini 4 Argon97.4
Muse Wonder96.5
Grok 4.795.3
MiMo-V2.6-Flash94.0
DeepSeek V4 Pro 081393.7
Gemini 3.8 Flash93.7
MiniMax M3.1 Flash93.7
GLM-5.3 Flash93.5
GPT-6.1 Sol93.3
Claude Sonnet 5.593.1
GPT-6 Astra93.1
GLM-5.392.7
Kimi K392.7
MiMo-V2.6-Pro92.7
Claude Haiku 5.591.2
Inkling91.0
Hy4 Preview90.5
GPT-6 Luna90.3
Mercury 390.1
Beam 1.0 501B A23B89.2
Inkling-Small88.4
Muse Spark Open78.5
DeepSeek V4.1 Flash 101774.8
Mistral Large 4 Preview74.8
Claude Opus 5.574.3
Loading Atlas data…