List your company

Multi-hop Question Answering on SimpleQA

18.8Pass@1R1-70B
1.5366.01810.514.982May 16, 2025

Evaluation results

MethodLinks
R1-70B2025.0518.8
o3-mini2025.0513.8
Qwen2.5-72B2025.0511.7
Qwen2.5-32B + cotProtocol=CoT2025.059.9
QwQ-32B2025.059.7
Qwen2.5-32B + rtProtocol=rt2025.059.4
Qwen2.5-32B2025.058.7
Qwen2.5-14B + rtProtocol=rt2025.058.2
Qwen2.5-14B + cotProtocol=CoT2025.058
Qwen2.5-14B + fs1Protocol=fs12025.057.9
Qwen2.5-32B + fs1Protocol=fs12025.057.8
Qwen2.5-7B2025.057
Qwen2.5-14B2025.056.8
Qwen2.5-7B + rtProtocol=rt2025.056.7
Qwen2.5-7B + cotProtocol=CoT2025.056.2
Qwen2.5-3B + rtProtocol=rt2025.055.3
Qwen2.5-7B + fs1Protocol=fs12025.055.3
Qwen2.5-3B + cotProtocol=CoT2025.054.8
Qwen2.5-3B + fs1Protocol=fs12025.054.5
Qwen2.5-3B2025.054.4
Qwen2.5-1.5B + cotProtocol=CoT2025.054.1
Qwen2.5-1.5B + rtProtocol=rt2025.053.8
SmolLM2-1.7B + rtProtocol=rt2025.053.8
SmolLM2-1.7B + fs1Protocol=fs12025.053.6
Qwen2.5-0.5B + fs1Protocol=fs12025.053.5
Qwen2.5-1.5B + fs1Protocol=fs12025.053.5
SmolLM2-1.7B2025.053.2
SmolLM2-1.7B + cotProtocol=CoT2025.053.2
Qwen2.5-0.5B + cotProtocol=CoT2025.053.1
Qwen2.5-1.5B2025.053.1
SmolLM2-360M + rtProtocol=rt2025.052.9
SmolLM2-360M + fs1Protocol=fs12025.052.7
SmolLM2-360M + cotProtocol=CoT2025.052.5
SmolLM2-360M2025.052.4
Qwen2.5-0.5B2025.052.3
Qwen2.5-0.5B + rtProtocol=rt2025.052.2