List your company

Graduate-Level Question Answering on GPQA Diamond

40ScoreEntropy-Cut MH
2730.37533.7537.125Mar 31, 2026Apr 9, 2026Apr 19, 2026Apr 29, 2026May 8, 2026May 18, 2026May 28, 2026

Evaluation results

MethodLinks
Entropy-Cut MHModel=Qwen3-8B-Base2026.0540
Uniform-Cut MHModel=Qwen3-8B-Base2026.0538.8
TMCModel=Qwen3-8B-Base2026.0538.6
SMCModel=Qwen3-8B-Base2026.0538.1
Low-TemperatureModel=Qwen3-8B-Base2026.0537.6
InternVL 3.5 2BNumber of Parameters=2B, Input Modality=Text-Only2026.0334.34
Entropy-Cut MHModel=Qwen2.5-Math-7B2026.0534.1
Entropy-Cut MHModel=Phi-4-mini-instruct2026.0533.3
Low-TemperatureModel=Qwen2.5-Math-7B2026.0533.1
Xuanwu VL-2BNumber of Parameters=2B, Input Modality=Text-Only2026.0332.83
Entropy-Cut MHModel=Phi-3.5-mini-instruct2026.0532.8
TMCModel=Qwen2.5-Math-7B2026.0532.5
Low-TemperatureModel=Phi-3.5-mini-instruct2026.0532.5
Uniform-Cut MHModel=Qwen2.5-Math-7B2026.0532.4
Low-TemperatureModel=Phi-4-mini-instruct2026.0532.1
TMCModel=Phi-4-mini-instruct2026.0532.1
SMCModel=Qwen2.5-Math-7B2026.0532
Uniform-Cut MHModel=Phi-4-mini-instruct2026.0532
SMCModel=Phi-4-mini-instruct2026.0531.9
Uniform-Cut MHModel=Phi-3.5-mini-instruct2026.0531.8
StandardModel=Qwen3-8B-Base2026.0531.7
TMCModel=Phi-3.5-mini-instruct2026.0531.5
SMCModel=Phi-3.5-mini-instruct2026.0531
StandardModel=Phi-4-mini-instruct2026.0530.7
Entropy-Cut MHModel=Qwen2.5-7B2026.0530.2
InternVL 3.0 2BNumber of Parameters=2B, Input Modality=Text-Only2026.0329.8
Low-TemperatureModel=Qwen2.5-7B2026.0529.5
StandardModel=Qwen2.5-7B2026.0529.4
Uniform-Cut MHModel=Qwen2.5-7B2026.0529.4
StandardModel=Qwen2.5-Math-7B2026.0529
SMCModel=Qwen2.5-7B2026.0528.8
StandardModel=Phi-3.5-mini-instruct2026.0527.8
TMCModel=Qwen2.5-7B2026.0527.5