Physical Reasoning and Instruction Following on WorldModelBench (test)
2.52Instruction Adherence Score
Veo3
Updated 1mo ago
Evaluation Results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
2026.06 | 2.52 | 98 | 95 | 1.93 | 100 | 89 | 99 | 91 | 100 | 4.8 | 9.25 | |
2026.06 | 2.5 | 99 | 95 | 1.94 | 100 | 89 | 99 | 94 | 100 | 4.83 | 9.27 | |
2026.06 | 2.33 | 87 | 85 | 1.72 | 100 | 100 | 100 | 94 | 100 | 4.94 | 8.99 | |
2026.06 | 2.21 | 96 | 93 | 1.88 | 100 | 91 | 99 | 95 | 100 | 4.84 | 8.93 | |
2026.06 | 2.14 | 100 | 94 | 1.94 | 100 | 92 | 100 | 94 | 100 | 4.86 | 8.94 | |
2026.06 | 2.13 | 59 | 46 | 1.05 | 100 | 48 | 99 | 69 | 98 | 4.13 | 7.31 | |
2026.06 | 2.05 | 76 | 65 | 1.41 | 100 | 65 | 99 | 81 | 100 | 4.45 | 7.91 | |
2026.06 | 2.01 | 89 | 91 | 1.8 | 100 | 93 | 99 | 95 | 100 | 4.87 | 8.67 | |
2026.06 | 1.97 | 69 | 62 | 1.32 | 99 | 60 | 100 | 73 | 100 | 4.32 | 7.61 | |
2026.06 | 1.62 | 54 | 45 | 0.99 | 100 | 56 | 100 | 85 | 100 | 4.4 | 7.01 | |
2026.06 | 1.59 | 97 | 100 | 1.97 | 100 | 100 | 100 | 100 | 100 | 5 | 8.55 |