List your company

Question Answering on OpenBookQA (OpQA)

47OpQA ScoreSTL
37.6440.0742.544.93Feb 10, 2026

Evaluation results

MethodLinks
STLBase Model=Qwen2.5-7B2026.0247
STL-augBase Model=Qwen2.5-7B2026.0247
SurgicalBase Model=Qwen2.5-7B2026.0247
STLBase Model=LLaMA-3-8B2026.0245
STL-augBase Model=LLaMA-3-8B2026.0245
SurgicalBase Model=LLaMA-3-8B2026.0245
SCANSBase Model=Qwen2.5-7B2026.0244
DCRBase Model=Qwen2.5-7B2026.0244
SCANSBase Model=LLaMA-3-8B2026.0244
STLBase Model=Qwen2.5-1.5B2026.0241
STL-augBase Model=Qwen2.5-1.5B2026.0241
SurgicalBase Model=Qwen2.5-1.5B2026.0240
SCANSBase Model=Qwen2.5-1.5B2026.0239
DCRBase Model=LLaMA-3-8B2026.0239
DCRBase Model=Qwen2.5-1.5B2026.0238