Large Language Model Evaluation

Benchmarks

Dataset Name	SOTA Method	Metric
MMLU, GSM8k, HellaSwag, WinoGrande		Average Score78.9	58	3mo ago
10 tasks average		Avg Accuracy70.56	50	3mo ago
HuggingFace Open LLM Leaderboard	SynPO	GSM8K55.37	49	2mo ago
Open PL LLM Leaderboard instruction-tuned		Overall Average Score69.84	44	3mo ago
Open LLM Leaderboard		Average Score74.2	41	1mo ago
Qwen3-0.6B Average (test)	EDGERAZOR	Average Performance47.83	38	27d ago
HuggingFace Open LLM Leaderboard lm-eval-harness default (various)		HellaSwag84.34	36	27d ago
Open LLM Leaderboard v1 (test)		Average Score69.6	34	21d ago
MMLU, GSM8K, GPQA, HUMANEVAL, TRUTHFULQA, IFEVAL	GRPO	MMLU70.7	23	3mo ago
ARC, TruthfulQA, Winogrande, GSM8K, HellaSwag, MMLU	DNPO	ARC Accuracy73.7	16	2mo ago
12-task evaluation suite composite (test)	FineWeb-Edu	Reading Comprehension Score49.6	14	3mo ago
Qwen-32B		MMLU80.81	13	3mo ago
MMLU, GSM8k, HellaSwag, WinoGrande (test)		MMLU Accuracy86.55	13	3mo ago
OpenCompass	Qwen3-30B-A3B	cMMLU84.88	11	3mo ago
Slovene-LLM-Eval		Average Rank3.05	10	3mo ago
GSM8K, TruthfulQA, CommonsenseQA, MMLU, ARC, and TriviaQA (various)	JoBS	Accuracy88	9	3mo ago
NorEval (test)	NorwAI-Mistral-7B	Overall Score0.455	8	3mo ago
SFT Evaluation Suite (AlpacaEval, TruthfulQA, MMLU) (test)	Warmup-Stable-Only (WSO)	AlpacaEval Score78.1	7	2mo ago
LLaMA 3B 3.2		PPL7.81	6	2mo ago
LLaMA 1B 3.2		Perplexity (PPL)9.75	6	2mo ago
LLaMA-3 8B		PPL6.13	6	2mo ago
LLaMA-2 13B		Perplexity4.88	6	2mo ago
LLaMA-2 7B		PPL5.47	6	2mo ago
MT-Bench benign prompts		Average Time Cost41.56	6	3mo ago
Knowledge Specialized Target (test)	CAMEL	Weighted Average Score56.5	4	2mo ago

Showing 25 of 30 rows