List your company

Spatiotemporal reasoning on ST-Bench 2026

55.3Exact Match (EM)STAR
25.55633.2784148.722May 11, 2026

Evaluation results

MethodLinks
STARBackbone=Qwen3-8B, Query Eligibility=EM-eligible queries2026.0555.3
LLM-only (CoT)Backbone=Qwen3-8B, Query Eligibility=EM-eligible queries2026.0545
Graph-of-ThoughtBackbone=Qwen3-8B, Query Eligibility=EM-eligible queries2026.0542.5
ReflexionBackbone=Qwen3-8B, Query Eligibility=EM-eligible queries2026.0540
Tree-of-ThoughtBackbone=Qwen3-8B, Query Eligibility=EM-eligible queries2026.0540
LLM-onlyBackbone=Qwen3-8B, Query Eligibility=EM-eligible queries2026.0537.5
Function-callingBackbone=Qwen3-8B, Query Eligibility=EM-eligible queries2026.0533.3
ReActBackbone=Qwen3-8B, Query Eligibility=EM-eligible queries2026.0526.7