Instruction-based Image Editing on RISEBench 49 (test)
62.8Reasoning
GPT-4o
Updated 25d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.03 | 62.8 | 80.2 | 94.9 | 28.9 | |
2026.03 | 37.64 | 57.86 | 78.73 | 7.2 | |
2026.03 | 36.94 | 57.01 | 70.73 | 7.2 | |
2026.03 | 36.7 | 55.54 | 71.08 | 5.8 | |
2026.03 | 36.67 | 56.59 | 72.09 | 7.2 | |
2026.03 | 36.5 | 53.5 | 73 | 6.1 | |
2026.03 | 36.18 | 59.07 | 72.36 | 7.5 | |
2026.03 | 35.97 | 57.15 | 71.91 | 6.1 | |
2026.03 | 35.83 | 60.2 | 69.91 | 6.9 | |
2026.03 | 35.62 | 56.66 | 72.45 | 6.4 | |
2026.03 | 35.56 | 58.07 | 71.73 | 6.7 | |
2026.03 | 35.42 | 59.07 | 74.27 | 6.4 | |
2026.03 | 31.01 | 40.65 | 88.27 | 2.22 | |
2026.03 | 30.21 | 59.63 | 80 | 3.9 | |
2026.03 | 26.32 | 60.84 | 89.08 | 5 | |
2026.03 | 26.18 | 57.64 | 91.18 | 5.55 | |
2026.03 | 25.25 | 43.06 | 86.64 | 3.33 | |
2026.03 | 25.1 | 41.5 | 73.5 | 1.9 | |
2026.03 | 25.07 | 52.62 | 89.72 | 2.5 | |
2026.03 | 24.65 | 39.8 | 79.18 | 2.5 | |
2026.03 | 24.38 | 22.24 | 81.81 | 0.83 | |
2026.03 | 23.75 | 48.3 | 84.91 | 3.05 | |
2026.03 | 23.26 | 49.29 | 88.09 | 4.17 | |
2026.03 | 22.71 | 56.16 | 90.36 | 3.06 | |
2026.03 | 22.15 | 65.44 | 91.09 | 3.61 | |
2026.03 | 22 | 32.6 | 55.3 | 0.8 | |
2026.03 | 18.33 | 65.79 | 86.63 | 2.22 |