Multimodal Understanding on HallusionBench
77.2Accuracy
PRISM + GRPO
Updated 15d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.04 | 77.2 | |
2026.04 | 76.1 | |
2026.04 | 75.8 | |
2026.04 | 74.8 | |
2026.04 | 73.6 | |
2026.04 | 72.9 | |
2026.04 | 72.9 | |
2026.04 | 72.6 | |
2026.04 | 72.3 | |
2026.04 | 72 | |
2026.04 | 71.9 | |
2026.04 | 71.9 | |
2026.04 | 71.6 | |
2026.04 | 71.5 | |
2026.04 | 71.2 | |
2026.04 | 70.1 | |
2026.04 | 69.5 | |
2026.04 | 69.1 | |
2026.04 | 68.2 | |
2026.05 | 63.76 | |
2026.05 | 62.5 | |
2026.05 | 61.77 | |
2026.04 | 61.5 | |
2026.05 | 61.03 | |
2026.05 | 59.87 | |
2026.05 | 59.87 | |
2026.05 | 59.66 | |
2026.05 | 59.35 | |
2026.05 | 57.66 | |
2026.05 | 56.61 | |
2026.05 | 56.3 | |
2026.05 | 55.88 | |
2026.05 | 55.77 | |
2026.05 | 54.62 | |
2026.04 | 53.8 | |
2026.05 | 51.25 | |
2026.05 | 51.15 |