List your company

Open-ended Question Answering on HotpotQA (test)

88AccuracyRouteGoT
58.8866.447481.56Mar 6, 2026

Evaluation results

MethodLinks
RouteGoTBackbone={Qwen3-4B, 8B, 30B}2026.0388592
GoT*Backbone=Qwen3-30B2026.0387812
CoTBackbone=Qwen3-30B2026.0386431
RouteLLMBackbone={Qwen3-4B, 8B, 30B}2026.0383555
IOBackbone=Qwen3-30B2026.038111
KNNBackbone={Qwen3-4B, 8B, 30B}2026.0379627
RTRBackbone={Qwen3-4B, 8B, 30B}2026.0379554
RandomBackbone={Qwen3-4B, 8B, 30B}2026.03771,685
EmbedLLMBackbone={Qwen3-4B, 8B, 30B}2026.03772,040
AGoTBackbone=Qwen3-30B2026.03722,583
ToTBackbone=Qwen3-30B2026.03603,748