List your company

Question Answering on NQ, TriviaQA, PopQA, HotpotQA, 2WikiMQA, MuSiQue, Bamboogle

280.3Total Scoreπ-Play
59.924117.137174.35231.563Apr 15, 2026

Evaluation results

MethodLinks
π-PlayBase Model=Qwen3-8B2026.04280.3
π-PlayBase Model=Qwen3-4B-Instruct-25072026.04277.2
Dr.ZeroBase Model=Qwen3-8B2026.04274.9
Dr.ZeroBase Model=Qwen3-4B-Instruct-25072026.04266.3
Search-R1Base Model=Qwen3-4B-Instruct-25072026.04266
π-PlayBase Model=Qwen3-4B2026.04250
SQLM*Base Model=Qwen3-4B-Instruct-25072026.04249.9
SQLM*Base Model=Qwen3-8B2026.04248.8
SQLM*Base Model=Qwen3-4B2026.04246.6
Dr.ZeroBase Model=Qwen3-4B2026.04245.2
Search-R1Base Model=Qwen3-8B2026.04242.8
Search-R1Base Model=Qwen3-4B2026.04239.7
ReActBase Model=Qwen3-4B-Instruct-25072026.04166.6
ReActBase Model=Qwen3-8B2026.04149.1
ReActBase Model=Qwen3-4B2026.0468.4