MMHal
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Hallucination Evaluation | MMHal | Score4.2 | 37 | |
| VQA Hallucination | MMHal | Score3.87 | 21 | |
| Pointwise Scoring | MMHal pointwise | Kendall's Tau0.949 | 9 | |
| Hallucination Evaluation | MMHal v1.0 (test) | Score2.23 | 6 |
Showing 4 of 4 rows