List your company

Graduate-level Reasoning on GPQA main (Pass@10)

76.7Pass@10Multi-chain
71.354472.742274.1375.5178Jan 2, 2026

Evaluation results

MethodLinks
Multi-chainModel=Qwen2.5-32B-Instruct2026.0176.7
Entropy-TreeModel=Qwen2.5-32B-Instruct2026.0175.93
Entropy-TreeModel=Qwen2.5-14B-Instruct2026.0173.53
Multi-chainModel=Qwen2.5-14B-Instruct2026.0172.11
Entropy-TreeModel=Qwen2.5-7B-Instruct2026.0172.07
Multi-chainModel=Qwen2.5-7B-Instruct2026.0171.56