List your company

Multi-hop Question Answering on Mintaka

77.4Pass@1o3-mini
10.52827.88945.2562.611May 16, 2025

Evaluation results

MethodLinks
o3-mini2025.0577.4
R1-70B2025.0575.5
Qwen2.5-72B2025.0573.6
QwQ-32B2025.0570.8
Qwen2.5-32B + cotProtocol=CoT2025.0569.6
Qwen2.5-32B + fs1Protocol=fs12025.0568.2
Qwen2.5-32B + rtProtocol=rt2025.0568
Qwen2.5-14B + rtProtocol=rt2025.0567.8
Qwen2.5-32B2025.0567.4
Qwen2.5-14B + cotProtocol=CoT2025.0566.4
Qwen2.5-14B + fs1Protocol=fs12025.0565.4
Qwen2.5-14B2025.0562.4
Qwen2.5-7B + cotProtocol=CoT2025.0558
Qwen2.5-7B + rtProtocol=rt2025.0557.6
Qwen2.5-7B + fs1Protocol=fs12025.0555.1
Qwen2.5-7B2025.0554.8
Qwen2.5-3B + rtProtocol=rt2025.0549.5
Qwen2.5-3B + fs1Protocol=fs12025.0544.4
Qwen2.5-3B + cotProtocol=CoT2025.0543.1
Qwen2.5-3B2025.0539.6
SmolLM2-1.7B + rtProtocol=rt2025.0536.6
SmolLM2-1.7B + fs1Protocol=fs12025.0534.1
Qwen2.5-1.5B + cotProtocol=CoT2025.0531.8
Qwen2.5-1.5B2025.0531.6
Qwen2.5-1.5B + fs1Protocol=fs12025.0530.1
SmolLM2-1.7B + cotProtocol=CoT2025.0529.5
Qwen2.5-1.5B + rtProtocol=rt2025.0529.4
SmolLM2-1.7B2025.0529.3
Qwen2.5-0.5B + cotProtocol=CoT2025.0521.4
SmolLM2-360M + rtProtocol=rt2025.0520.2
Qwen2.5-0.5B + fs1Protocol=fs12025.0520.2
SmolLM2-360M + fs1Protocol=fs12025.0519.7
SmolLM2-360M + cotProtocol=CoT2025.0518.8
Qwen2.5-0.5B + rtProtocol=rt2025.0517.8
SmolLM2-360M2025.0517.5
Qwen2.5-0.5B2025.0513.1