SOTA Knowledge Reasoning benchmarks and papers with code

Benchmarks

Dataset Name	SOTA Method	Metric
MMLU-Pro	SIGMA	Accuracy91.43	120	5d ago
MMLU	SIGMA	MMLU Knowledge Reasoning Accuracy92.16	73	14d ago
Knowledge Reasoning Benchmarks (MATH, GPQA, MMLU, GSM8K) (test)	PDA-GAM (3∆)	MATH Accuracy89.6	24	1d ago
K-Cross (test)	CMA	Accuracy41.5	22	5d ago
K-Cross (val)	PSO-Merging	Accuracy43	22	5d ago
GPQA	LLaDA-2.1-flash	Accuracy67.3	18	1mo ago
GPQA Diamond	TRICE-30B	Accuracy (avg@8)75.4	16	26d ago
GPQA Diamond	General Teacher	Accuracy62.5	12	7d ago
Tobacco Pest and Disease Control (test)	GraphRAG + ChatGLM	Accuracy90.1	8	3mo ago
GPQA Diamond		pass@182.8	7	3mo ago
Super GPQA	Qwen2.5-32B-Instruct + Bootcamp-SFT-RL	Accuracy51	6	13d ago
MMLU 57 subjects (test)	UTS-guided system	Accuracy74.3	6	3mo ago
MMLU		Pass@189.9	6	3mo ago
BLINK	InterSketch	Accuracy63	5	7d ago
MMLU Pro (test)	MiMo-VL-Miloco-7B	EM68.5	5	3mo ago
MMMU	InterSketch	Accuracy68.6	4	7d ago
MMLU c	1B Model (Multilingual classifier)	Normalized Accuracy29.87	3	1mo ago
Include c	1B Model (Multilingual classifier)	Normalized Accuracy35.41	3	1mo ago
GMMLU c	1B Model (Multilingual classifier)	Normalized Accuracy32	3	1mo ago
CMMLU c	1B Model (Multilingual classifier)	Accuracy (Normalized)36.08	3	1mo ago
GPQA Diamond	ExpertWeaver	Score37.3	3	3mo ago

Showing 21 of 21 rows