Atlas

Benchmarks

← All benchmarks

HLAB-Vals-1.1 - Immigration

Professional Work · 2026-10-19

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

Top models (higher is better)

ModelScore
Muse Wonder40.0
Claude Sonnet 5.520.0
DeepSeek V4.1 Flash 101720.0
DeepSeek V4 Pro 081320.0
GLM-5.320.0
Hy4 Preview20.0
MiMo-V2.6-Pro20.0
MiniMax M3.1 Flash20.0
Muse Spark Open20.0
Muse Wonder Full20.0
Claude Opus 5.510.0
Grok 4.710.0
Beam 1.0 501B A23B0.0
Claude Haiku 5.50.0
Gemini 3.8 Flash0.0
Gemini 4 Argon0.0
GLM-5.3 Flash0.0
GPT-6.1 Sol0.0
GPT-6 Astra0.0
GPT-6 Luna0.0
Inkling0.0
Inkling-Small0.0
Kimi K30.0
Mercury 30.0
MiMo-V2.6-Flash0.0
Mistral Large 4 Preview0.0
Loading Atlas data…