Atlas

Benchmarks

← All benchmarks

HLAB-Vals-1.1 - Antitrust Competition

Professional Work · 2026-10-19

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

Top models (higher is better)

ModelScore
Gemini 4 Argon60.0
Muse Wonder Full40.0
DeepSeek V4.1 Flash 101730.0
Grok 4.720.0
Muse Spark Open20.0
Muse Wonder20.0
Claude Sonnet 5.510.0
GPT-6.1 Sol10.0
GPT-6 Astra10.0
MiMo-V2.6-Flash10.0
Beam 1.0 501B A23B0.0
Claude Haiku 5.50.0
Claude Opus 5.50.0
DeepSeek V4 Pro 08130.0
Gemini 3.8 Flash0.0
GLM-5.3 Flash0.0
GLM-5.30.0
GPT-6 Luna0.0
Hy4 Preview0.0
Inkling0.0
Inkling-Small0.0
Kimi K30.0
Mercury 30.0
MiMo-V2.6-Pro0.0
MiniMax M3.1 Flash0.0
Mistral Large 4 Preview0.0
Loading Atlas data…