Visual Question Answering on RSHR-Bench
49.5COL
GPT-4o
Updated 3d ago
Evaluation Results
| Method | Links | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2026.04 | 49.5 | 23 | 15 | 35.5 | 30.5 | 28 | 27.1 | 22.5 | 41 | 68 | 56 | 30.5 | 32 | 64 | 30.2 | 50.1 | 37.3 | |
2026.04 | 46.5 | 32 | 38 | 12.5 | 38.5 | 24 | 17.1 | 17 | 37 | 44 | 34 | 65 | 32 | 50 | 29.2 | 45 | 34.8 | |
2026.04 | 41.5 | 16 | 29 | 31.5 | 31.5 | 32 | 28.6 | 19.5 | 32 | 54 | 54 | 31.5 | 48 | 54 | 29.1 | 48.3 | 36 | |
2026.04 | 41 | 22 | 21 | 30 | 32.5 | 30.5 | 27.1 | 18 | 31 | 42 | 30 | 29.5 | 32 | 52 | 28.1 | 37.1 | 31.3 | |
2026.04 | 40 | 22 | 22 | 37 | 35.5 | 26 | 21.4 | 24.5 | 24 | 58 | 30 | 55 | 32 | 58 | 28 | 46.6 | 34.6 | |
2026.04 | 32.5 | 22 | 24 | 29.5 | 40 | 25 | 22.9 | 22.5 | 29 | 30 | 24 | 25.5 | 30 | 32 | 25.9 | 28.3 | 26.8 | |
2026.04 | 29.5 | 25 | 22 | 28 | 25 | 24.5 | 24.3 | 26.5 | 22 | 26 | 28 | 25 | 10 | 20 | 25.2 | 21.8 | 24 | |
2026.04 | 29 | 10 | 23 | 23 | 37 | 24.5 | 31.4 | 20 | 23 | 74 | 58 | 35 | 34 | 66 | 24.5 | 53.4 | 34.8 | |
2026.04 | 25.5 | 22 | 26 | 26 | 22.5 | 24.5 | 30 | 22.5 | 20 | 26 | 20 | 22.5 | 34 | 20 | 24.3 | 24.5 | 24.4 | |
2026.04 | 25.5 | 25 | 26 | 26.5 | 55 | 25 | 22.9 | 25 | 25 | 26 | 24 | 26.5 | 34 | 28 | 25.7 | 27.7 | 26.4 | |
2026.04 | 25 | 24 | 25 | 25 | 23.5 | 25 | 22.9 | 25 | 25 | 24 | 22 | 23.5 | 30 | 22 | 24.5 | 24.3 | 24.4 | |
2026.04 | 25 | 24 | 25 | 25 | 25 | 25 | 21.4 | 25 | 25 | 24 | 0 | 0 | 34 | 22 | 24.5 | 16 | 21.5 | |
2026.04 | 22.5 | 22 | 21 | 25 | 20.5 | 26 | 28.6 | 20.5 | 22 | 22 | 28 | 50 | 32 | 20 | 23.1 | 30.4 | 25.7 | |
2026.04 | 21.5 | 28 | 18 | 21.5 | 29 | 28.5 | 30 | 26.5 | 25 | 20 | 16 | 29 | 34 | 26 | 25.3 | 25 | 25.2 | |
2026.04 | 21.5 | 28 | 30 | 24 | 19.5 | 29.5 | 34.3 | 22 | 29 | 26 | 30 | 35 | 32 | 30 | 27.4 | 30.6 | 28.5 |