Atlas

Benchmarks

← All benchmarks

HLAB-Vals-1.1 - Criteria Pass Rate - Immigration

Professional Work · 2026-10-19

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

Top models (higher is better)

ModelScore
Muse Wonder96.2
Muse Wonder Full95.5
Gemini 4 Argon94.5
Grok 4.794.4
Claude Sonnet 5.594.0
GLM-5.393.1
DeepSeek V4.1 Flash 101792.5
Gemini 3.8 Flash92.0
GPT-6 Astra92.0
Hy4 Preview92.0
Kimi K392.0
Claude Opus 5.591.8
GPT-6.1 Sol91.5
Mistral Large 4 Preview91.3
MiMo-V2.6-Pro91.1
Claude Haiku 5.590.9
MiMo-V2.6-Flash90.9
MiniMax M3.1 Flash90.7
GLM-5.3 Flash90.2
DeepSeek V4 Pro 081388.4
Beam 1.0 501B A23B87.3
Inkling87.3
Mercury 387.3
GPT-6 Luna85.6
Inkling-Small81.3
Muse Spark Open71.3
Loading Atlas data…