List your company

Multi-hop Question Answering on WebQSP

68Pass@1o3-mini
15.27228.96142.6556.339May 16, 2025

Evaluation results

MethodLinks
o3-mini2025.0568
Qwen2.5-72B2025.0565.3
Qwen2.5-32B2025.0562.1
Qwen2.5-32B + cotProtocol=CoT2025.0561.4
QwQ-32B2025.0561.2
Qwen2.5-14B2025.0559.9
Qwen2.5-14B + cotProtocol=CoT2025.0559.2
Qwen2.5-7B2025.0558
Qwen2.5-32B + fs1Protocol=fs12025.0557.6
Qwen2.5-7B + cotProtocol=CoT2025.0556.5
Qwen2.5-32B + rtProtocol=rt2025.0556.3
Qwen2.5-14B + rtProtocol=rt2025.0556.2
Qwen2.5-14B + fs1Protocol=fs12025.0555.8
R1-70B2025.0554.9
Qwen2.5-7B + rtProtocol=rt2025.0551.7
Qwen2.5-7B + fs1Protocol=fs12025.0549.2
Qwen2.5-3B + rtProtocol=rt2025.0548.3
Qwen2.5-3B + cotProtocol=CoT2025.0547.7
Qwen2.5-3B2025.0546.6
SmolLM2-1.7B + rtProtocol=rt2025.0545.4
SmolLM2-1.7B + fs1Protocol=fs12025.0542.6
SmolLM2-1.7B + cotProtocol=CoT2025.0540.9
SmolLM2-1.7B2025.0540.8
Qwen2.5-3B + fs1Protocol=fs12025.0540.6
Qwen2.5-1.5B + cotProtocol=CoT2025.0539.1
Qwen2.5-1.5B2025.0536
Qwen2.5-1.5B + rtProtocol=rt2025.0536
Qwen2.5-1.5B + fs1Protocol=fs12025.0535.6
Qwen2.5-0.5B + fs1Protocol=fs12025.0530.2
SmolLM2-360M + rtProtocol=rt2025.0529.3
Qwen2.5-0.5B + rtProtocol=rt2025.0528.6
SmolLM2-360M + fs1Protocol=fs12025.0526.4
SmolLM2-360M2025.0523.5
Qwen2.5-0.5B + cotProtocol=CoT2025.0523.4
SmolLM2-360M + cotProtocol=CoT2025.0523
Qwen2.5-0.5B2025.0517.3