General Question Answering

Benchmarks

Dataset Name	SOTA Method	Metric
TriviaQA	Agentic-R	Exact Match69.02	54	1mo ago
NQ	SkillOrchestra+	Exact Match (EM)54.8	52	1mo ago
PopQA	InForage-instruct	EM45.2	51	1mo ago
General QA NQ, TriviaQA, PopQA	Qwen2.5-32B-Instruct + Proposed Method	NQ Accuracy58.2	40	25d ago
NQ (Natural Questions)	Search-R1	EM46.1	32	1mo ago
TriviaQA (test val)	DeepControl	EM68.2	24	3mo ago
Natural Questions (NQ) (test val)	DeepControl	EM55.8	24	3mo ago
TriviaQA		Token-Level F176.4	20	1mo ago
PopQA	SkillOrchestra+	Accuracy48.8	18	3mo ago
TriviaQA	SkillOrchestra+	Accuracy80.2	18	3mo ago
TriviaQA	Search-R1	EM64.4	18	3mo ago
TriviaQA	π-Play	Score64.6	16	1mo ago
PopQA out-of-domain (val test)	Search-R2	Exact Match (EM)50.1	15	3mo ago
TriviaQA out-of-domain (val test)	Search-R2	EM70.9	15	3mo ago
NQ (Natural Questions) in-domain (val/test)	Search-R2	Exact Match50.9	15	3mo ago
PopQA Pop.	StepSearch-base	OSR Score27.7	13	1mo ago
TriviaQA	StepSearch-base	OSR (%)12.2	13	1mo ago
NQ (Natural Questions)	StepSearch-base	OSR (%)25.2	13	1mo ago
OOD Non-Math GPQA, CommonsenseQA	Baseline LLM	Pass@171.4	12	2mo ago
TriviaQA (test)	Search-R1 + EKA	F166.1	11	3mo ago
PopQA	Dynamic Collaboration Framework	EM47.87	10	1mo ago
TriviaQA	CoT	EM66.3	10	1mo ago
NQ	Dynamic Collaboration Framework	EM46.08	10	1mo ago
PopQA (test)	Workflow-R1-Search	EM49.3	10	3mo ago
TriviaQA (test)	Workflow-R1-Search	EM73.3	10	3mo ago

Showing 25 of 31 rows