List your company

Question Answering on GPQA-D (Acc, Len)

52.53AccuracyLCPO
26.259633.079839.946.7202Aug 13, 2025

Evaluation results

MethodLinks
LCPOBackbone=DeepSeek-R1-Distill-Qwen-7B2025.0852.534,301
OriginalBackbone=DeepSeek-R1-Distill-Qwen-7B2025.0848.999,237
CoDBackbone=DeepSeek-R1-Distill-Qwen-7B2025.0847.985,834
DASTBackbone=DeepSeek-R1-Distill-Qwen-7B2025.0847.9810,819
L1-MaxBackbone=DeepSeek-R1-Distill-Qwen-7B2025.0846.972,039
L1-ExactBackbone=DeepSeek-R1-Distill-Qwen-7B2025.0846.463,235
TrEffBackbone=DeepSeek-R1-Distill-Qwen-7B2025.0844.956,470
LCPOBackbone=DeepSeek-R1-Distill-Qwen-1.5B2025.0839.394,340
OriginalBackbone=DeepSeek-R1-Distill-Qwen-1.5B2025.0834.8510,312
CoDBackbone=DeepSeek-R1-Distill-Qwen-1.5B2025.0833.337,328
L1-MaxBackbone=DeepSeek-R1-Distill-Qwen-1.5B2025.0831.822,839
L1-ExactBackbone=DeepSeek-R1-Distill-Qwen-1.5B2025.0831.313,253
TrEffBackbone=DeepSeek-R1-Distill-Qwen-1.5B2025.0827.276,914