Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Risk-of-bias assessment in medical systematic reviews on COCHRANEFOREST (test)
Loading...
0.895
Coherence
Qwen2.5-7B-GRPO-VPRM
0.34068
0.48459
0.6285
0.77241
Jan 23, 2026
Coherence
CA
Updated 5mo ago
Evaluation Results
Method
Method
Links
Coherence
CA
Qwen2.5-7B-GRPO-VPRM
Training Algorithm=GRP...
2026.01
0.895
0.75
Qwen2.5-7B-DAPO-VPRM
Training Algorithm=DAP...
2026.01
0.801
0.694
Llama-3.1-405B
Model Type=Pretrained LLM
2026.01
0.507
0.271
Qwen2.5-72B
Model Type=Pretrained LLM
2026.01
0.443
0.249
GPT-OSS-120B
Model Type=Pretrained LLM
2026.01
0.362
0.285
Feedback
Search any
task
Search any
task