Share your thoughts, 1 month free Claude Pro on usSee more

General Language Understanding

Benchmarks

Dataset Name	SOTA Method	Metric
tinyBenchmark		Accuracy (ARC)77.51	91	1mo ago
GLUE		Accuracy92.5	75	2mo ago
LAMBADA, ARC-C, HellaSwag, BoolQ, MMLU, GSM8K Average		Accuracy74.35	56	1mo ago
GLUE v1 (test dev)	BOMF (Ours)	MNLI87.86	40	4mo ago
MMLU		MMLU Score73.59	39	3mo ago
Standard Downstream Tasks Suite (SciQ, PIQA, WinoGrande, ARC-E, ARC-C, HellaSwag, LogiQA, BoolQ, LAMBADA, MMLU)	ConceptLM	Average Accuracy48.3	32	4mo ago
NLU Suite (MMLU, SST-2, AGNews, 20News, MNLI, SNLI)	ReLoRA	Average Accuracy89.9	31	1mo ago
MMLU	Qwen3-4B	MMLU Accuracy72.45	29	1mo ago
Average	EMoE	Average Accuracy72.93	26	2mo ago
General LLM Benchmarks (ARC-C, CSQA, HellaSwag, LAMBADA, MMLU, OpenBookQA, PIQA, Winogrande) (test)		ARC-C Accuracy59.5	22	4mo ago
CMMLU, CEval	A-CHORD	Chinese Score (CMMLU/CEval)71.66	20	1mo ago
MMLU, MMLU-Pro, GPQA-Diamond	A-CHORD	English Score55.46	20	1mo ago
General Ability Suite (MMLU, PIQA, ARC-E, ARC-C, BoolQ, WinoGrande, HellaSwag, TruthfulQA)	LRC	MMLU Accuracy65	20	1mo ago
12-task evaluation suite (test)	Efficient-DLM 8B	Average Score71.62	20	4mo ago
MMLU	LP-SFT	5-shot Accuracy78.82	18	18d ago
C-Eval (val)	Qwen-1.5 14B (Teacher)	Accuracy78.68	18	4mo ago
Held-out capability suite (test)		AIME-2024 Accuracy62.9	16	2mo ago
Overall LLM Evaluation Suite PiQA, ARC, HellaSwag, WinoGrande, MMLU v1	LLaMA-3-8B-Lizard	Overall Accuracy74.6	16	3mo ago
General Downstream Tasks Aggregate	PonderLM-2-Pythia-1.4B	Average Accuracy59.5	16	26d ago
General Ability Suite (C-QA, T-QA, LAM, MMLU, L-Code)		Average Score48.1	16	4mo ago
KMMLU	Solar Open	Overall Score73	16	1mo ago
10-benchmark suite average		Average Accuracy73.81	15	1mo ago
10 Benchmarks Average (test)	Base	Accuracy (Average)67.4	15	2mo ago
8 Sub-Tasks (test)	LoRA	Performance on 8 Sub-Tasks62.3	14	4mo ago
NLP Evaluation Suite (SciQ, PIQA, WG, ARC, HellaSwag, LogiQA, BoolQ, LAMBADA)	MOUE L48	SciQ Accuracy58.3	14	4mo ago

Showing 25 of 70 rows