Language Model Evaluation

Benchmarks

Dataset Name	SOTA Method	Metric
BenchPress short-context (test)	Qwen3-8B	Accuracy68.84	131	22d ago
Winogrande, ARC-C, ARC-E, Lambada, PIQA, Hellaswag, MMLU, IFEval, and GSM8K-CoT (Mixed standard 10-shot prompt)	IF4	Accuracy80.39	88	21d ago
Open LLM Leaderboard v2 (test)		BBH60.84	47	22d ago
ArxivRollBench 2026a		Valid Accuracy70.8	42	8d ago
Qwen3-0.6B Evaluation Suite average	EDGERAZOR	Average Performance47.8	24	27d ago
Pooled tasks Table 5 Llama-3.1 3.3 (various)	Llama-3.3 70B Instruct	Pooled Accuracy Estimate (γ̂)57.15	21	3mo ago
AdaptEval	SCALENET (Layer-wise)	ROUGE-Lsum0.2733	14	3mo ago
DCLM Core	Composer (2Mb-M-3A)	DCLM Core Score49.3	12	16d ago
lm-eval-harness (test)		MMLU74.22	9	27d ago
Downstream Tasks Evaluation Suite Math, Code, Law, Know., Reason., MMLU		Math Accuracy4.92	9	3mo ago
DATE-LM MMLU, GSM8K, BBH		MMLU Accuracy62.07	7	2d ago
Quality, Factuality, and Safety Evaluation Suite (test)	Self-Improving Pretraining	Generation Quality Score86.3	7	3mo ago
NLP Evaluation Suite (WG, PIQA, BoolQ, ARC-C, ARC-E, OBQA, HS, SciQ, LM, RTE)	QK sharing	WG60.14	6	3mo ago
Open LeaderBoard v2	AgentSociety	AS0.6547	5	7d ago
1.3B LLM Leaderboard	QA+C4-85B	ARC36.4	5	3mo ago
MMLU-Pro	AgentSociety	AS77.54	1	7d ago

Showing 16 of 16 rows