LLM-as-a-Judge

Benchmarks

Dataset Name	SOTA Method	Metric
MTbench (test)		StdDev2.24	45	1mo ago
PreferenceBench	CalibraEval	Rstd0.69	36	1mo ago
RewardBench 1.0 (test)	CC	Rstd0.54	36	1mo ago
JudgeBench		Accuracy84.19	29	25d ago
PreferenceBench	PA-GRPO	Accuracy90.2	21	25d ago
MT-Bench	PA-GRPO	Accuracy81.4	21	25d ago
ARENA	EpiPersona-A	Accuracy66.07	20	18d ago
PRISM	EpiPersona-A	Accuracy59.38	20	18d ago
PRISM (test)	SynthesizeMe	Accuracy58.9	14	1mo ago
Chatbot Arena (test)	Gemini-2.5-Pro	Accuracy68.13	14	1mo ago
FairJudge Benchmark 1K (test)	FairJudge-8B	Agreement71.5	13	1mo ago
JudgeLM (test)		Agreement79.59	13	1mo ago
PandaLM Human Annotations (test)	FairJudge-8B	Agreement0.7683	13	1mo ago
Preference Bench (test)	CalibraEval	Std Dev2.82	9	1mo ago
RewardBench (test)	CalibraEval	Std Dev (Reward)2.72	9	1mo ago
JudgeBench (Merged GPT Claude)		Direct Baseline Score87.38	8	11d ago
RewardBench	Qwen3-Next-80B-A3B-Thinking	Accuracy92.9	8	1mo ago
KD-DTI (test)	GPT-4o-Mini	EM Change53.41	8	1mo ago
DDI (test)	GPT-4o-Mini	EM (Δ)59.03	8	1mo ago
BC5CDR (test)	GPT-4o-Mini	EM48.35	8	1mo ago
BigGen-Bench (test)	LLaDA (FS)	Pearson Correlation0.312	4	11d ago

Showing 21 of 21 rows