Multimodal Document Question Answering on DocBench
80.16Accuracy (Academia)
AutothinkRAG
Updated 1mo ago
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
2026.03 | 80.16 | 75.4 | 85.71 | 87.09 | 92.5 | 86.43 | 77.31 | 81.25 | 82.13 | |
2026.03 | 77.34 | 73.46 | 80.59 | 85.29 | 88.78 | 84.08 | 76.12 | 77.84 | 79.37 | |
2026.03 | 77.03 | 74 | 81.54 | 84.39 | 89.26 | 85.32 | 75.09 | 76.42 | 79.47 | |
2026.03 | 76.34 | 72.93 | 79.77 | 84.07 | 84.52 | 84.65 | 74.47 | 75.83 | 78.02 | |
2026.03 | 74.9 | 70.68 | 77.41 | 83.06 | 81.67 | 84.21 | 76.36 | 52.8 | 75.47 | |
2025.07 | 60.7 | 64.1 | 62.6 | 64.9 | 76.2 | 80 | 86.4 | 75 | 77.5 | |
2025.07 | 60.5 | 65.8 | 66.5 | 70.4 | 77.1 | 81.2 | 88.7 | 71.9 | 76.8 | |
2025.07 | 51.8 | 59.4 | 62.8 | 60.7 | 77.9 | 79.1 | 77.8 | 70.2 | 74 | |
2025.07 | 51.8 | 62.9 | 66.9 | 68.6 | 76.2 | 82.4 | 81.1 | 67.7 | 75.2 | |
2025.07 | 43.9 | 13.5 | 53.4 | 44.5 | 79.7 | 52.9 | 18.8 | 81.5 | 44.7 | |
2025.07 | 43.6 | 38.2 | 66.2 | 64.9 | 80.2 | 79.9 | 32.1 | 70.2 | 61 | |
2025.07 | 43.6 | 34.4 | 62.8 | 65.4 | 75 | 81.6 | 30.5 | 67.7 | 59.5 | |
2025.07 | 41.3 | 16.3 | 50.7 | 49.7 | 77.3 | 53.9 | 20.1 | 75.8 | 44.8 | |
2025.07 | 40.6 | 27.1 | 56.8 | 59.7 | 75 | 73.5 | 24.4 | 76.6 | 54.7 | |
2025.07 | 39.6 | 25.7 | 52.5 | 49.7 | 74.5 | 71.7 | 26 | 67.5 | 52.3 | |
2025.07 | 19.8 | 16.3 | 28.4 | 31.4 | 46.5 | 35.7 | 15.9 | 39.5 | 27.7 | |
2025.07 | 17.5 | 14.9 | 25 | 34.6 | 48.8 | 34 | 8.4 | 40.3 | 25.4 |