List your company

Revision Evaluation on Revision Evaluation unseen (test)

88Relatednesso3-mini
54.7263.367280.64Jan 16, 2026

Evaluation results

MethodLinks
o3-mini2026.01888084
Qwen32026.01867681
Skywork2026.01837780
SciRM2026.01827378
SciRM-Ref2026.01827378
Granite2026.01806874
Qwen2.52026.01806673
Selene2026.01797175
DS-Qwen2026.01776772
Prometheus2026.01767073
DS-GRM2026.01735966
Llama2026.01566158