LLM-as-a-Judge Evaluation using 10-fold Cross-Validation benchmark leaderboard · SOTA2 Research

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

88CG AccuracyQwen3-14B

Evaluation Results

Method	Links
Qwen3-14B2026.06		88	80	82.9
Gemini-2-Flash2026.06		83	72	80.8
GPT-OSS 20B2026.06		83	78	53
Gemini-2-Flash2026.06		79	74	57.5
GPT-OSS 20B2026.06		77	67	86.2
Qwen3-14B2026.06		64	62	64.4
Random Baseline2026.06		50	50	12
Random Baseline2026.06		25	25	27