List your company

Multi-hop Question Answering on ExaQT

49.7Pass@1o3-mini
4.04415.89727.7539.603May 16, 2025

Evaluation results

MethodLinks
o3-mini2025.0549.7
R1-70BSize=70B2025.0547.6
Qwen2.5-72BSize=72B2025.0544
QwQ-32BSize=32B2025.0539
Qwen2.5-32B + cotBackbone=Qwen2.5-32B, Protocol=CoT2025.0536.6
Qwen2.5-32B + rtBackbone=Qwen2.5-32B, Protocol=rt2025.0536.6
Qwen2.5-32BBackbone=Qwen2.5-32B2025.0536.2
Qwen2.5-32B + fs1Backbone=Qwen2.5-32B, Protocol=fs12025.0536.1
Qwen2.5-14B + cotBackbone=Qwen2.5-14B, Protocol=CoT2025.0535.6
Qwen2.5-14B + rtBackbone=Qwen2.5-14B, Protocol=rt2025.0535.2
Qwen2.5-14B + fs1Backbone=Qwen2.5-14B, Protocol=fs12025.0533.9
Qwen2.5-14BBackbone=Qwen2.5-14B2025.0533.6
Qwen2.5-7B + rtBackbone=Qwen2.5-7B, Protocol=rt2025.0529.6
Qwen2.5-7B + cotBackbone=Qwen2.5-7B, Protocol=CoT2025.0529.2
Qwen2.5-7BBackbone=Qwen2.5-7B2025.0528.1
Qwen2.5-7B + fs1Backbone=Qwen2.5-7B, Protocol=fs12025.0527.2
Qwen2.5-3B + rtBackbone=Qwen2.5-3B, Protocol=rt2025.0523.5
Qwen2.5-3B + cotBackbone=Qwen2.5-3B, Protocol=CoT2025.0522.2
Qwen2.5-3BBackbone=Qwen2.5-3B2025.0521.4
Qwen2.5-3B + fs1Backbone=Qwen2.5-3B, Protocol=fs12025.0520.5
SmolLM2-1.7B + rtBackbone=SmolLM2-1.7B, Protocol=rt2025.0518.4
Qwen2.5-1.5B + cotBackbone=Qwen2.5-1.5B, Protocol=CoT2025.0517.9
SmolLM2-1.7B + fs1Backbone=SmolLM2-1.7B, Protocol=fs12025.0517.9
SmolLM2-1.7B + cotBackbone=SmolLM2-1.7B, Protocol=CoT2025.0517.7
SmolLM2-1.7BBackbone=SmolLM2-1.7B2025.0517.6
Qwen2.5-1.5B + rtBackbone=Qwen2.5-1.5B, Protocol=rt2025.0517.3
Qwen2.5-1.5BBackbone=Qwen2.5-1.5B2025.0517
Qwen2.5-1.5B + fs1Backbone=Qwen2.5-1.5B, Protocol=fs12025.0516.2
SmolLM2-360M + rtBackbone=SmolLM2-360M, Protocol=rt2025.0511.1
Qwen2.5-0.5B + cotBackbone=Qwen2.5-0.5B, Protocol=CoT2025.0510.4
SmolLM2-360M + cotBackbone=SmolLM2-360M, Protocol=CoT2025.0510.1
Qwen2.5-0.5B + fs1Backbone=Qwen2.5-0.5B, Protocol=fs12025.0510.1
SmolLM2-360M + fs1Backbone=SmolLM2-360M, Protocol=fs12025.059.3
Qwen2.5-0.5B + rtBackbone=Qwen2.5-0.5B, Protocol=rt2025.058.9
SmolLM2-360MBackbone=SmolLM2-360M2025.058.8
Qwen2.5-0.5BBackbone=Qwen2.5-0.5B2025.055.8