Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

LLM-as-a-Judge Evaluation using 10-fold Cross-Validation

88CG Accuracy

Qwen3-14B

22.4839.4956.573.51Jun 4, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
888082.9
2026.06
837280.8
2026.06
837853
2026.06
797457.5
2026.06
776786.2
2026.06
646264.4
2026.06
505012
2026.06
252527