Visual Question Answering on VQA-Med Open
0.825AUROCHAC-Gate
Evaluation Results
| Method | Links | |
|---|---|---|
| HAC-GateBase Model=InternVL3-8B, Confidence Type=Sampling2026.04 | 0.825 | |
| HAC-GateBase Model=InternVL3-2B, Confidence Type=Sampling2026.04 | 0.821 | |
| HAC-PlattBase Model=InternVL3-8B, Confidence Type=Sampling2026.04 | 0.821 | |
| HAC-PlattBase Model=InternVL3-2B, Confidence Type=Sampling2026.04 | 0.818 | |
| UncalibratedBase Model=InternVL3-2B, Confidence Type=Sampling2026.04 | 0.812 | |
| Platt ScalingBase Model=InternVL3-2B, Confidence Type=Sampling2026.04 | 0.812 | |
| Isotonic Regr.Base Model=InternVL3-2B, Confidence Type=Sampling2026.04 | 0.804 | |
| UncalibratedBase Model=InternVL3-8B, Confidence Type=Sampling2026.04 | 0.801 | |
| Platt ScalingBase Model=InternVL3-8B, Confidence Type=Sampling2026.04 | 0.801 | |
| Isotonic Regr.Base Model=InternVL3-8B, Confidence Type=Sampling2026.04 | 0.801 | |
| Hist. BinningBase Model=InternVL3-2B, Confidence Type=Sampling2026.04 | 0.798 | |
| HAC-PlattBase Model=Qwen3-VL-8B, Confidence Type=Verbalized2026.04 | 0.793 | |
| Hist. BinningBase Model=InternVL3-8B, Confidence Type=Sampling2026.04 | 0.785 | |
| HAC-PlattBase Model=Qwen3-VL-32B, Confidence Type=Sampling2026.04 | 0.784 | |
| HAC-GateBase Model=Qwen3-VL-32B, Confidence Type=Sampling2026.04 | 0.784 | |
| HAC-GateBase Model=Qwen3-VL-8B, Confidence Type=Verbalized2026.04 | 0.768 | |
| HAC-PlattBase Model=InternVL3-2B, Confidence Type=Verbalized2026.04 | 0.762 | |
| HAC-PlattBase Model=Qwen3-VL-8B, Confidence Type=Sampling2026.04 | 0.76 | |
| HAC-GateBase Model=InternVL3-8B, Confidence Type=Verbalized2026.04 | 0.76 | |
| HAC-GateBase Model=Qwen3-VL-8B, Confidence Type=Sampling2026.04 | 0.759 | |
| HAC-PlattBase Model=InternVL3-8B, Confidence Type=Verbalized2026.04 | 0.757 | |
| HAC-GateBase Model=InternVL3-2B, Confidence Type=Verbalized2026.04 | 0.753 | |
| HAC-GateBase Model=InternVL3-38B, Confidence Type=Sampling2026.04 | 0.752 | |
| HAC-PlattBase Model=InternVL3-38B, Confidence Type=Sampling2026.04 | 0.751 | |
| HAC-GateBase Model=Qwen3-VL-32B, Confidence Type=Verbalized2026.04 | 0.741 | |
| UncalibratedBase Model=Qwen3-VL-8B, Confidence Type=Verbalized2026.04 | 0.737 | |
| Platt ScalingBase Model=Qwen3-VL-8B, Confidence Type=Verbalized2026.04 | 0.737 | |
| Isotonic Regr.Base Model=Qwen3-VL-8B, Confidence Type=Verbalized2026.04 | 0.737 | |
| HAC-PlattBase Model=Qwen3-VL-32B, Confidence Type=Verbalized2026.04 | 0.736 | |
| HAC-GateBase Model=LLaVA-NeXT-34B, Confidence Type=Verbalized2026.04 | 0.725 | |
| HAC-GateBase Model=InternVL3-38B, Confidence Type=Verbalized2026.04 | 0.72 | |
| HAC-PlattBase Model=LLaVA-NeXT-34B, Confidence Type=Verbalized2026.04 | 0.719 | |
| UncalibratedBase Model=Qwen3-VL-2B, Confidence Type=Sampling2026.04 | 0.704 | |
| Platt ScalingBase Model=Qwen3-VL-2B, Confidence Type=Sampling2026.04 | 0.704 | |
| UncalibratedBase Model=Qwen3-VL-32B, Confidence Type=Sampling2026.04 | 0.704 | |
| Platt ScalingBase Model=Qwen3-VL-32B, Confidence Type=Sampling2026.04 | 0.704 | |
| Isotonic Regr.Base Model=Qwen3-VL-32B, Confidence Type=Sampling2026.04 | 0.702 | |
| HAC-PlattBase Model=Qwen3-VL-2B, Confidence Type=Verbalized2026.04 | 0.696 | |
| HAC-GateBase Model=Qwen3-VL-2B, Confidence Type=Verbalized2026.04 | 0.696 | |
| HAC-PlattBase Model=InternVL3-38B, Confidence Type=Verbalized2026.04 | 0.696 | |
| Isotonic Regr.Base Model=Qwen3-VL-2B, Confidence Type=Sampling2026.04 | 0.693 | |
| Isotonic Regr.Base Model=Qwen3-VL-32B, Confidence Type=Verbalized2026.04 | 0.69 | |
| HAC-GateBase Model=Qwen3-VL-2B, Confidence Type=Sampling2026.04 | 0.689 | |
| Hist. BinningBase Model=Qwen3-VL-32B, Confidence Type=Sampling2026.04 | 0.689 | |
| HAC-PlattBase Model=Qwen3-VL-2B, Confidence Type=Sampling2026.04 | 0.688 | |
| Hist. BinningBase Model=LLaVA-NeXT-7B, Confidence Type=Sampling2026.04 | 0.688 | |
| UncalibratedBase Model=InternVL3-38B, Confidence Type=Sampling2026.04 | 0.68 | |
| Platt ScalingBase Model=InternVL3-38B, Confidence Type=Sampling2026.04 | 0.68 | |
| HAC-GateBase Model=LLaVA-NeXT-7B, Confidence Type=Verbalized2026.04 | 0.678 | |
| Hist. BinningBase Model=Qwen3-VL-32B, Confidence Type=Verbalized2026.04 | 0.677 | |
| Isotonic Regr.Base Model=InternVL3-38B, Confidence Type=Verbalized2026.04 | 0.677 | |
| Isotonic Regr.Base Model=InternVL3-38B, Confidence Type=Sampling2026.04 | 0.676 | |
| Hist. BinningBase Model=Qwen3-VL-8B, Confidence Type=Verbalized2026.04 | 0.675 | |
| UncalibratedBase Model=Qwen3-VL-32B, Confidence Type=Verbalized2026.04 | 0.675 | |
| Platt ScalingBase Model=Qwen3-VL-32B, Confidence Type=Verbalized2026.04 | 0.675 | |
| HAC-PlattBase Model=LLaVA-NeXT-7B, Confidence Type=Verbalized2026.04 | 0.675 | |
| Hist. BinningBase Model=Qwen3-VL-2B, Confidence Type=Sampling2026.04 | 0.671 | |
| Hist. BinningBase Model=InternVL3-38B, Confidence Type=Verbalized2026.04 | 0.668 | |
| HAC-PlattBase Model=LLaVA-NeXT-34B, Confidence Type=Sampling2026.04 | 0.659 | |
| UncalibratedBase Model=Qwen3-VL-8B, Confidence Type=Sampling2026.04 | 0.657 | |
| Platt ScalingBase Model=Qwen3-VL-8B, Confidence Type=Sampling2026.04 | 0.657 | |
| Isotonic Regr.Base Model=Qwen3-VL-8B, Confidence Type=Sampling2026.04 | 0.657 | |
| Isotonic Regr.Base Model=LLaVA-NeXT-7B, Confidence Type=Sampling2026.04 | 0.654 | |
| Hist. BinningBase Model=Qwen3-VL-8B, Confidence Type=Sampling2026.04 | 0.65 | |
| HAC-PlattBase Model=LLaVA-NeXT-7B, Confidence Type=Sampling2026.04 | 0.648 | |
| Hist. BinningBase Model=InternVL3-38B, Confidence Type=Sampling2026.04 | 0.647 | |
| Isotonic Regr.Base Model=InternVL3-8B, Confidence Type=Verbalized2026.04 | 0.635 | |
| Hist. BinningBase Model=InternVL3-8B, Confidence Type=Verbalized2026.04 | 0.635 | |
| UncalibratedBase Model=InternVL3-8B, Confidence Type=Verbalized2026.04 | 0.633 | |
| Platt ScalingBase Model=InternVL3-8B, Confidence Type=Verbalized2026.04 | 0.633 | |
| HAC-GateBase Model=LLaVA-NeXT-34B, Confidence Type=Sampling2026.04 | 0.633 | |
| UncalibratedBase Model=InternVL3-38B, Confidence Type=Verbalized2026.04 | 0.629 | |
| Platt ScalingBase Model=InternVL3-38B, Confidence Type=Verbalized2026.04 | 0.629 | |
| UncalibratedBase Model=LLaVA-NeXT-7B, Confidence Type=Sampling2026.04 | 0.625 | |
| Platt ScalingBase Model=LLaVA-NeXT-7B, Confidence Type=Sampling2026.04 | 0.625 | |
| HAC-GateBase Model=LLaVA-NeXT-7B, Confidence Type=Sampling2026.04 | 0.625 | |
| UncalibratedBase Model=LLaVA-NeXT-34B, Confidence Type=Sampling2026.04 | 0.607 | |
| Platt ScalingBase Model=LLaVA-NeXT-34B, Confidence Type=Sampling2026.04 | 0.607 | |
| UncalibratedBase Model=LLaVA-NeXT-34B, Confidence Type=Verbalized2026.04 | 0.606 | |
| Platt ScalingBase Model=LLaVA-NeXT-34B, Confidence Type=Verbalized2026.04 | 0.606 | |
| Isotonic Regr.Base Model=LLaVA-NeXT-34B, Confidence Type=Verbalized2026.04 | 0.606 | |
| Hist. BinningBase Model=LLaVA-NeXT-34B, Confidence Type=Verbalized2026.04 | 0.606 | |
| Isotonic Regr.Base Model=LLaVA-NeXT-34B, Confidence Type=Sampling2026.04 | 0.588 | |
| UncalibratedBase Model=Qwen3-VL-2B, Confidence Type=Verbalized2026.04 | 0.577 | |
| Platt ScalingBase Model=Qwen3-VL-2B, Confidence Type=Verbalized2026.04 | 0.577 | |
| Isotonic Regr.Base Model=Qwen3-VL-2B, Confidence Type=Verbalized2026.04 | 0.577 | |
| UncalibratedBase Model=LLaVA-NeXT-7B, Confidence Type=Verbalized2026.04 | 0.565 | |
| Platt ScalingBase Model=LLaVA-NeXT-7B, Confidence Type=Verbalized2026.04 | 0.565 | |
| Hist. BinningBase Model=LLaVA-NeXT-7B, Confidence Type=Verbalized2026.04 | 0.565 | |
| Hist. BinningBase Model=Qwen3-VL-2B, Confidence Type=Verbalized2026.04 | 0.554 | |
| Hist. BinningBase Model=LLaVA-NeXT-34B, Confidence Type=Sampling2026.04 | 0.553 | |
| Isotonic Regr.Base Model=LLaVA-NeXT-7B, Confidence Type=Verbalized2026.04 | 0.55 | |
| Isotonic Regr.Base Model=InternVL3-2B, Confidence Type=Verbalized2026.04 | 0.532 | |
| Hist. BinningBase Model=InternVL3-2B, Confidence Type=Verbalized2026.04 | 0.528 | |
| UncalibratedBase Model=InternVL3-2B, Confidence Type=Verbalized2026.04 | 0.447 | |
| Platt ScalingBase Model=InternVL3-2B, Confidence Type=Verbalized2026.04 | 0.447 |