List your company

Explorative Reasoning on Game of 24 (test)

80AccuracyRTR
17.633.85066.2Mar 6, 2026

Evaluation results

MethodLinks
RTRBackbone={Qwen3-4B, 8B, 30B}2026.03804,623
RouteGoTBackbone={Qwen3-4B, 8B, 30B}2026.03803,648
RouteLLMBackbone={Qwen3-4B, 8B, 30B}2026.03794,849
AGoTBackbone=Qwen3-30B2026.037418,406
GoT*Backbone=Qwen3-30B2026.037217,396
KNNBackbone={Qwen3-4B, 8B, 30B}2026.03714,542
RandomBackbone={Qwen3-4B, 8B, 30B}2026.03627,899
CoTBackbone=Qwen3-30B2026.03581,948
EmbedLLMBackbone={Qwen3-4B, 8B, 30B}2026.03589,668
IOBackbone=Qwen3-30B2026.0327380
ToTBackbone=Qwen3-30B2026.03202,855