List your company

Multi-Hop Question Answering on MuSiQue (Score)

37.8ScoreToolForge
0.1529.92619.729.474Apr 15, 2026

Evaluation results

MethodLinks
ToolForgeBase Model=Qwen3-8B2026.0437.8
Dr.ZeroBase Model=Qwen3-4B-Instruct-25072026.0414.4
π-PlayBase Model=Qwen3-4B-Instruct-25072026.0413.4
Dr.ZeroBase Model=Qwen3-8B2026.0413.1
Search-R1Base Model=Qwen3-4B-Instruct-25072026.0412.9
π-PlayBase Model=Qwen3-8B2026.0412.4
π-PlayBase Model=Qwen3-4B2026.0411.2
SQLM*Base Model=Qwen3-4B2026.0410.8
Search-R1Base Model=Qwen3-4B2026.0410.5
SQLM*Base Model=Qwen3-4B-Instruct-25072026.0410.2
SQLM*Base Model=Qwen3-8B2026.049.9
Search-R1Base Model=Qwen3-8B2026.049.8
Dr.ZeroBase Model=Qwen3-4B2026.047.8
ReActBase Model=Qwen3-8B2026.047.4
ReActBase Model=Qwen3-4B-Instruct-25072026.046.3
ReActBase Model=Qwen3-4B2026.041.6