Question Answering on TabMWP (EM/F1)
37.8EMAdaCAD
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| AdaCADModel=Qwen2.5-7B2026.06 | 37.8 | 40.27 | |
| GreedyModel=Qwen2.5-7B2026.06 | 37.5 | 39.68 | |
| ARRModel=Qwen2.5-7B2026.06 | 37 | 39.54 | |
| COIECDModel=Qwen2.5-7B2026.06 | 36.5 | 39.63 | |
| GreedyModel=Mistral-7B-Inst2026.06 | 34.5 | 39.21 | |
| AdaCADModel=Mistral-7B-Inst2026.06 | 33.9 | 38.29 | |
| COIECDModel=Mistral-7B-Inst2026.06 | 31.5 | 35.8 | |
| CoCoAModel=Mistral-7B-Inst2026.06 | 30.4 | 34.63 | |
| ARRModel=Mistral-7B-Inst2026.06 | 30.4 | 36.59 | |
| ARRModel=Llama3-8B2026.06 | 30 | 35.16 | |
| CoCoAModel=Qwen2.5-7B2026.06 | 29.9 | 33.18 | |
| AdaCADModel=Llama3-8B2026.06 | 29.7 | 35.34 | |
| GreedyModel=Llama3-8B2026.06 | 29.5 | 35.31 | |
| CoCoAModel=Llama3-8B2026.06 | 25.1 | 30.66 | |
| CADModel=Mistral-7B-Inst2026.06 | 21.9 | 28.27 | |
| AdaCADModel=Llama2-13B2026.06 | 21.7 | 24.51 | |
| ARRModel=Llama2-13B2026.06 | 21.2 | 22.88 | |
| GreedyModel=Llama2-13B2026.06 | 21.1 | 23.41 | |
| COIECDModel=Llama3-8B2026.06 | 19.1 | 23.04 | |
| COIECDModel=Llama2-13B2026.06 | 18.7 | 22.12 | |
| CoCoAModel=Llama2-13B2026.06 | 18.5 | 21.55 | |
| ARRModel=Llama3-8B-Inst2026.06 | 16.7 | 21.39 | |
| CADModel=Llama2-13B2026.06 | 14.8 | 17.82 | |
| GreedyModel=Llama3-8B-Inst2026.06 | 14.2 | 19.25 | |
| CADModel=Qwen2.5-7B2026.06 | 13.6 | 15.71 | |
| CADModel=Llama3-8B2026.06 | 12.6 | 16.4 | |
| AdaCADModel=Llama3-8B-Inst2026.06 | 10.6 | 16.24 | |
| COIECDModel=Mistral-7B2026.06 | 10.2 | 12.3 | |
| ARRModel=Llama2-13B-Inst2026.06 | 8.2 | 14.58 | |
| GreedyModel=Mistral-7B2026.06 | 7.9 | 11.18 | |
| CoCoAModel=Qwen2.5-7B-Inst2026.06 | 7.5 | 11.19 | |
| GreedyModel=Llama2-13B-Inst2026.06 | 6.8 | 13.87 | |
| AdaCADModel=Llama2-13B-Inst2026.06 | 6.5 | 12.53 | |
| CoCoAModel=Mistral-7B2026.06 | 6.2 | 8.21 | |
| CoCoAModel=Llama3-8B-Inst2026.06 | 6.2 | 11.35 | |
| ARRModel=Mistral-7B2026.06 | 6.1 | 10.05 | |
| AdaCADModel=Qwen2.5-7B-Inst2026.06 | 5.9 | 9.26 | |
| COIECDModel=Qwen2.5-7B-Inst2026.06 | 5.8 | 9.16 | |
| CADModel=Mistral-7B2026.06 | 5.7 | 7.46 | |
| COIECDModel=Llama3-8B-Inst2026.06 | 4.8 | 11.08 | |
| CADModel=Qwen2.5-7B-Inst2026.06 | 3.8 | 8.21 | |
| AdaCADModel=Mistral-7B2026.06 | 3.7 | 6.4 | |
| COIECDModel=Llama2-13B-Inst2026.06 | 3.6 | 9.53 | |
| CADModel=Llama3-8B-Inst2026.06 | 3.4 | 7.39 | |
| CoCoAModel=Llama2-13B-Inst2026.06 | 3 | 8.16 | |
| CADModel=Llama2-13B-Inst2026.06 | 2.2 | 7.86 | |
| ARRModel=Qwen2.5-7B-Inst2026.06 | 2.1 | 4.24 | |
| GreedyModel=Qwen2.5-7B-Inst2026.06 | 1.5 | 4.43 |