Atlas

Benchmarks

← All benchmarks

HLAB-Vals-1.1 - Criteria Pass Rate - Capital Markets

Professional Work · 2026-10-19

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

Top models (higher is better)

ModelScore
Muse Spark Open97.8
Gemini 4 Argon96.7
Gemini 3.8 Flash96.5
Grok 4.796.5
Muse Wonder96.3
GPT-6 Astra96.1
Muse Wonder Full96.1
Claude Haiku 5.595.9
MiMo-V2.6-Flash95.5
Mistral Large 4 Preview95.1
Kimi K394.5
GLM-5.394.3
GPT-6.1 Sol94.3
DeepSeek V4.1 Flash 101794.1
Claude Opus 5.593.7
MiMo-V2.6-Pro93.3
Mercury 393.1
Hy4 Preview92.9
DeepSeek V4 Pro 081392.5
MiniMax M3.1 Flash92.4
GPT-6 Luna91.6
GLM-5.3 Flash91.4
Beam 1.0 501B A23B89.6
Inkling-Small86.5
Claude Sonnet 5.583.5
Inkling73.9
Loading Atlas data…