List your company

Open-Web Reasoning on Humanity’s Last Exam (HLE) Open-web via SERPER (test)

14.8Pass@4Gemma3-12B
9.49610.87312.2513.627Jun 15, 2026

Evaluation results

MethodLinks
Gemma3-12BSampling Method=DivInit (DI)2026.0614.8
Qwen3-4BSampling Method=DivInit (DI)2026.0614.3
Qwen3-8BSampling Method=DivInit (DI)2026.0614.1
Gemma3-12BSampling Method=Standard parallel sampling (S)2026.0612.7
Qwen3-8BSampling Method=Standard parallel sampling (S)2026.0610
Qwen3-4BSampling Method=Standard parallel sampling (S)2026.069.7