Reliability Prediction on LLaVA-Bench (eval)
0.971AUROCQwen2-VL-7B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2-VL-7BReliability source=Probe2026.06 | 0.971 | |
| LLaVA-1.5-7BReliability source=Probe2026.06 | 0.956 | |
| PaliGemma-3BReliability source=Probe2026.06 | 0.738 |
Loading the SOTA2 catalog…