List your company

Graduate-level Reasoning on GPQA-D (Score)

61.1ScoreMTI
20.64431.14741.6552.153Oct 15, 2025

Evaluation results

MethodLinks
MTIModel=Qwen3-8B, τ=1.52025.1061.1
MTIModel=Qwen3-8B, τ=0.52025.1060.6
MTIModel=Qwen3-8B, τ=1.02025.1060.1
CGRSModel=Qwen3-8B, τ=-2025.1059.8
DEERModel=Qwen3-8B, τ=-2025.1059.3
TALEModel=Qwen3-8B, τ=-2025.1059.1
DynasorModel=Qwen3-8B, τ=-2025.1057.7
NoThinkingModel=Qwen3-8B, τ=-2025.1054.2
MTIModel=DeepSeek-R1-7B, τ=0.52025.1051.52
MTIModel=DeepSeek-R1-7B, τ=1.02025.1048.5
MTIModel=DeepSeek-R1-7B, τ=1.52025.1040.9
NoThinkingModel=DeepSeek-R1-7B, τ=-2025.1037.9
TALEModel=DeepSeek-R1-7B, τ=-2025.1036.2
DEERModel=DeepSeek-R1-7B, τ=-2025.1033.1
CGRSModel=DeepSeek-R1-7B, τ=-2025.1032.8
DynasorModel=DeepSeek-R1-7B, τ=-2025.1022.2