VL-RewardBench
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multimodal Reward Modeling | VL-RewardBench | Accuracy77.5 | 76 | |
| Reward Modeling | VL-RewardBench | Accuracy86.45 | 13 |
Showing 2 of 2 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multimodal Reward Modeling | VL-RewardBench | Accuracy77.5 | 76 | |
| Reward Modeling | VL-RewardBench | Accuracy86.45 | 13 |