Multimodal Understanding and Question Answering on LLaVA-NeXT Evaluation Suite 13B (test)
64.4GQA Score
Baseline
Updated 29d ago
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
2026.06 | 64.4 | 73.1 | 63.2 | 85.3 | 1,539.5 | 68.5 | 61.2 | 45 | 67.2 | 100 | |
2026.06 | 64.1 | 72.8 | 62.5 | 86.7 | 1,560.8 | 69 | 63.4 | 44.4 | 67.6 | 100.6 | |
2026.06 | 63.7 | 71.7 | 62.4 | 86.5 | 1,573.1 | 67.6 | 63.2 | 40.9 | 66.8 | 99.4 | |
2026.06 | 63.5 | 72.2 | 59.2 | 86.5 | 1,526.1 | 67.5 | 62.9 | 39 | 65.9 | 98.1 | |
2026.06 | 63.2 | 71.5 | 61.1 | 85.9 | 1,569.7 | 67.6 | 63 | 42.2 | 66.6 | 99.1 | |
2026.06 | 63.1 | 71.2 | 57.6 | 87.3 | 1,554.6 | 68.7 | 61.2 | 42.3 | 66.1 | 98.4 | |
2026.06 | 62.9 | 70.8 | 62.1 | 85.8 | 1,549.2 | 68.1 | 62.6 | 46.8 | 67.1 | 99.9 | |
2026.06 | 62.8 | 71.7 | 62.1 | 84.4 | 1,559.1 | 66.6 | 60.8 | 39.7 | 65.8 | 97.9 | |
2026.06 | 62.8 | 70.6 | 56.2 | 83.7 | 1,497.3 | 67.4 | 61.9 | 39.4 | 64.6 | 96.1 | |
2026.06 | 62.7 | 72.5 | 62.8 | 85.6 | 1,562.7 | 68.8 | 64 | 41.3 | 67 | 99.7 | |
2026.06 | 62.7 | 71 | 61.3 | 85.2 | 1,542.4 | 67.6 | 61.9 | 45.5 | 66.5 | 99 | |
2026.06 | 62.7 | 71 | 60.8 | 85.2 | 1,509.3 | 66.6 | 63.1 | 42.8 | 66 | 98.2 | |
2026.06 | 61.8 | 72.3 | 57.6 | 85.2 | 1,473 | 65.9 | 61.9 | 39.2 | 64.7 | 96.3 | |
2026.06 | 61.3 | 69.9 | 52.8 | 87.2 | 1,476.6 | 67.3 | 57.4 | 33.1 | 62.9 | 93.6 | |
2026.06 | 61.2 | 71.2 | 59.2 | 82.7 | 1,473.7 | 66.2 | 62.9 | 37.8 | 64.4 | 95.8 | |
2026.06 | 61.1 | 70.7 | 55.9 | 79.1 | 1,426.5 | 66.6 | 60.6 | 36.5 | 62.7 | 93.3 | |
2026.06 | 61.1 | 70.6 | 59.7 | 83.9 | 1,480.9 | 66.6 | 62.8 | 40.4 | 64.9 | 96.6 | |
2026.06 | 60.9 | 71.7 | 60.7 | 80.2 | 1,516.7 | 65.5 | 59.9 | 43.8 | 64.8 | 96.4 | |
2026.06 | 60.9 | 70.9 | 60 | 81.5 | 1,491.6 | 68 | 63.5 | 39.3 | 64.8 | 96.4 | |
2026.06 | 60.9 | 69.8 | 59.7 | 81.1 | 1,457.4 | 65.9 | 61.9 | 41.4 | 64.2 | 95.5 | |
2026.06 | 60.7 | 70.2 | 60.7 | 82.3 | 1,487.3 | 66.5 | 62.3 | 41.1 | 64.8 | 96.4 | |
2026.06 | 60 | 71.4 | 56.3 | 81.9 | 1,436.7 | 65.1 | 60.9 | 37.4 | 63.1 | 93.9 | |
2026.06 | 58.9 | 69.1 | 49.2 | 87 | 1,392.3 | 65.7 | 51.6 | 27.8 | 59.9 | 89.1 | |
2026.06 | 58.7 | 70.1 | 57.2 | 75.7 | 1,389.3 | 64.6 | 60.8 | 35 | 61.4 | 91.4 | |
2026.06 | 57.9 | 70.1 | 52.8 | 72.1 | 1,345.9 | 63.2 | 57.1 | 30.6 | 58.9 | 87.6 | |
2026.06 | 57.8 | 69.7 | 58.6 | 76.8 | 1,393.9 | 64.8 | 60 | 35.9 | 61.7 | 91.8 | |
2026.06 | 57.7 | 72.1 | 56.2 | 74.6 | 1,386.3 | 62.8 | 55.3 | 29.5 | 59.7 | 88.8 | |
2026.06 | 54.6 | 70.5 | 55.4 | 63.6 | 1,279 | 59.8 | 54.4 | 30.2 | 56.6 | 84.2 |