Atlas

Benchmarks

← All benchmarks

HLAB-Vals-1.1 - Litigation Dispute Resolution

Professional Work · 2026-10-19

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

Top models (higher is better)

ModelScore
Grok 4.740.0
GLM-5.330.0
Hy4 Preview30.0
Muse Spark Open30.0
DeepSeek V4.1 Flash 101720.0
DeepSeek V4 Pro 081320.0
GLM-5.3 Flash20.0
Kimi K320.0
MiMo-V2.6-Flash20.0
Mistral Large 4 Preview20.0
Claude Haiku 5.510.0
Gemini 3.8 Flash10.0
Gemini 4 Argon10.0
GPT-6 Astra10.0
MiniMax M3.1 Flash10.0
Muse Wonder10.0
Beam 1.0 501B A23B0.0
Claude Opus 5.50.0
Claude Sonnet 5.50.0
GPT-6.1 Sol0.0
GPT-6 Luna0.0
Inkling0.0
Inkling-Small0.0
Mercury 30.0
MiMo-V2.6-Pro0.0
Muse Wonder Full0.0
Loading Atlas data…