Question Answering on OpenBookQA (OpQA)
47OpQA ScoreSTL
Evaluation Results
| Method | Links | |
|---|---|---|
| STLBase Model=Qwen2.5-7B2026.02 | 47 | |
| STL-augBase Model=Qwen2.5-7B2026.02 | 47 | |
| SurgicalBase Model=Qwen2.5-7B2026.02 | 47 | |
| STLBase Model=LLaMA-3-8B2026.02 | 45 | |
| STL-augBase Model=LLaMA-3-8B2026.02 | 45 | |
| SurgicalBase Model=LLaMA-3-8B2026.02 | 45 | |
| SCANSBase Model=Qwen2.5-7B2026.02 | 44 | |
| DCRBase Model=Qwen2.5-7B2026.02 | 44 | |
| SCANSBase Model=LLaMA-3-8B2026.02 | 44 | |
| STLBase Model=Qwen2.5-1.5B2026.02 | 41 | |
| STL-augBase Model=Qwen2.5-1.5B2026.02 | 41 | |
| SurgicalBase Model=Qwen2.5-1.5B2026.02 | 40 | |
| SCANSBase Model=Qwen2.5-1.5B2026.02 | 39 | |
| DCRBase Model=LLaMA-3-8B2026.02 | 39 | |
| DCRBase Model=Qwen2.5-1.5B2026.02 | 38 |