Creative Writing

Benchmarks

Dataset Name	SOTA Method	Metric
WildBench		WildBench Score83.9	45	29d ago
Creative Writing	Min-k	Win Rate58.6	36	4d ago
CreativeWriting v3	SPARD	LLM Judge73.95	26	8d ago
Arena-Hard Creative Writing v2	Gemini-2.5-Pro	Score90.8	25	1mo ago
Creative writing (test)		Creativity90.38	20	4d ago
Overall Average Poem, Joke, Story	VS-Standard	Semantic Diversity0.3603	20	29d ago
Story	VS-Standard	Semantic Diversity38.6	20	29d ago
Poem		Semantic Diversity31.22	20	29d ago
Blessing short-text		Score94.6	18	10d ago
Arena Hard	Online DPO with WILDREWARD	Win Rate63.5	18	8d ago
Creative Writing	Self-Refine	Solved Rate51.98	16	23d ago
WildBench (test)		WildBench Score64.4	15	29d ago
ArenaHard creative writing v2.0	DPWriter	WR Score29	13	1mo ago
Creative Writing EQ-Bench v3	DPWriter	ELO829.05	13	1mo ago
WritingBench	DPWriter	Score6.43	13	1mo ago
Creative Writing	SFT+DPO+GRPO	Discovery Score45.2	12	1mo ago
Creative Writing v3	QwQ-32B	Overall Rubric Score52.8	10	1mo ago
Creative Writing Human Evaluation	Min-k	Human Preference Count75	9	4d ago
HelloBench	Qwen3-30B-A3B-Thinking	Accuracy80.4	6	12d ago
Konkani Kannada script	Qwen2.5 14B	LLM Judge Score3.6	6	23d ago
Konkani Devanagari script	Llama 8B	LLM Judge Score3.7	6	23d ago
Konkani Romi script	Llama 8B	LLM Judge Score4.2	6	23d ago
Creative Writing	Info-Gain Sampler	Win Rate vs Confidence70.1	6	1mo ago
Creative Writing Alpaca-Eval 100 problems 2.0	ICRL prompting	Length-Controlled Win Rate93.81	4	23d ago
GRAFITE Sample Dataset Creative	Llama-3.1-8B-Instruct	Pass Rate100	4	29d ago

Showing 25 of 25 rows