List your company

LLM Evaluation on Shared (evaluation)

78Tie-aware AccuracyGrowLoop
11.4428.724663.28May 26, 2026

Evaluation results

MethodLinks
GrowLoopCategory=Ours2026.0578870.78
ICAICategory=Training-free rubric2026.0558850.75
OpenJudgeCategory=Training-free rubric2026.0558700.62
ICL (k=3)Category=No rubric2026.0537570.09
Arena-Hard PromptCategory=Manual rubric2026.052743-0.17
Zero-shotCategory=No rubric2026.052542-0.21
MT-Bench PromptCategory=Manual rubric2026.052338-0.31
Skywork-Reward-V2Category=Reward Model2026.052239-0.2
RM-R1Category=Reward Model2026.051525-0.5
OpenRubric-JudgeCategory=Training-based rubric2026.051424-0.49