Multimodal Open-ended Utility Evaluation on MM-Vet v2 (test)
66.3Utility Score
No Steering
Updated 6d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.04 | 66.3 | |
2026.04 | 63.7 | |
2026.04 | 63 | |
2026.04 | 61.1 | |
2026.04 | 58.5 |
No Steering
| Method | Links | |
|---|---|---|
2026.04 | 66.3 | |
2026.04 | 63.7 | |
2026.04 | 63 | |
2026.04 | 61.1 | |
2026.04 | 58.5 |