Multi-turn Visual Question Answering on MT-GQA balanced (test-dev)
65.45Acc1
Base
Updated 2mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.03 | 65.45 | 67.32 | 69.12 | 67.3 | |
2026.03 | 63.83 | 66.68 | 67.94 | 66.15 | |
2026.03 | 62.47 | 65.21 | 67.22 | 64.97 | |
2026.03 | 61.76 | 64.07 | 65.35 | 63.73 | |
2026.03 | 60.78 | 63.41 | 65.16 | 63.12 | |
2026.03 | 60.21 | 63.38 | 65.01 | 62.87 | |
2026.03 | 59.69 | 62.28 | 63.88 | 61.95 | |
2026.03 | 59.61 | 61.86 | 63.43 | 61.63 | |
2026.03 | 59.43 | 63.49 | 65.19 | 62.7 | |
2026.03 | 58.6 | 61.04 | 63 | 60.88 | |
2026.03 | 58.46 | 61.39 | 63.24 | 61.03 | |
2026.03 | 57.02 | 59.26 | 62.16 | 59.48 | |
2026.03 | 55.99 | 58.49 | 61.55 | 58.68 | |
2026.03 | 55.95 | 58.71 | 60.64 | 58.43 | |
2026.03 | 55.7 | 57.94 | 60.7 | 58.11 | |
2026.03 | 55.41 | 58.53 | 60.26 | 58.07 | |
2026.03 | 55.26 | 57.23 | 60.13 | 57.54 | |
2026.03 | 55.06 | 57.89 | 59.74 | 57.56 | |
2026.03 | 54.84 | 57.33 | 58.83 | 57 | |
2026.03 | 54.63 | 57.87 | 60.23 | 57.58 | |
2026.03 | 54.6 | 57.07 | 59.31 | 56.99 | |
2026.03 | 52.94 | 57.2 | 59.69 | 56.61 | |
2026.03 | 52.52 | 57.01 | 60.67 | 56.73 | |
2026.03 | 49.08 | 53.34 | 56.14 | 52.85 | |
2026.03 | 47.23 | 51.34 | 53.36 | 50.64 | |
2026.03 | 46.42 | 50.55 | 53.95 | 50.31 | |
2026.03 | 40.98 | 46.71 | 49.3 | 45.66 |