Knowledge

Benchmarks

Dataset Name	SOTA Method	Metric
MMLU	DictaLM 3.0 24B-Think	Accuracy85.93	71	2d ago
GPQA	DeepSeek-R1-Distill-Qwen-32B (Reasoning)	Accuracy59.39	34	2d ago
ARC Easy	DeepSeek-R1-Distill-Qwen-32B (Reasoning)	ARC-E Score99.54	31	2d ago
ARC Challenge	ReasonAny	ARC-C Score96.43	31	2d ago
MMLU-Pro	Ling-flash-2.0	Score77.55	30	4d ago
MMB	TAIA	Accuracy61.98	21	4d ago
CommonSenseQA CoQA		Score66.91	20	4d ago
GPQA	Ling-flash-2.0	Score69.16	17	4d ago
C-EVAL		Score88.12	12	4d ago
OpenBookQA (test)	Qwen3-Omni-Instruct	Accuracy92.31	11	4d ago
MMSU (test)	Qwen3-Omni-Instruct	Performance77	11	4d ago
TriviaQA	LLaDA2.1-flash	Score72.93	10	4d ago
PHYBench	LLaDA2.0-flash	Score30.06	10	4d ago
GPQA	ReasonAny	GPQA Score57.5	9	2d ago
Knowledge Suite	Task Arithmetic	ARC-C84.07	9	2d ago
CLIcK	DeepSeek-V3.1	Score80.9	7	4d ago
KMMLU-Pro		Score70.9	7	4d ago
CMMLU	MiniCPM-4.1	Knowledge Score84.72	6	4d ago
C-Eval	Qwen3-1.7B-ALLMEM	C-Eval Knowledge Accuracy0.589	4	4d ago
PopQA	DictaLM 3.0 24B-Think	Accuracy30.59	3	2d ago
KMMLU Redux	DeepSeek-V3.1	Score75.9	3	4d ago
KMMLU	DeepSeek-V3.1	Score0.787	3	4d ago
OpenThaiEval	Typhoon-S-8B	Score67.06	2	4d ago
MMLU EN	Qwen3-8B	Knowledge Score42.18	2	4d ago
GPQA EN	Qwen3-8B	Score41.41	2	4d ago

Showing 25 of 25 rows