List your company

Visual Question Answering on VQA-Med Open

0.825AUROCHAC-Gate
0.431880.533940.6360.73806Apr 2, 2026

Evaluation results

MethodLinks
HAC-GateBase Model=InternVL3-8B, Confidence Type=Sampling2026.040.825
HAC-GateBase Model=InternVL3-2B, Confidence Type=Sampling2026.040.821
HAC-PlattBase Model=InternVL3-8B, Confidence Type=Sampling2026.040.821
HAC-PlattBase Model=InternVL3-2B, Confidence Type=Sampling2026.040.818
UncalibratedBase Model=InternVL3-2B, Confidence Type=Sampling2026.040.812
Platt ScalingBase Model=InternVL3-2B, Confidence Type=Sampling2026.040.812
Isotonic Regr.Base Model=InternVL3-2B, Confidence Type=Sampling2026.040.804
UncalibratedBase Model=InternVL3-8B, Confidence Type=Sampling2026.040.801
Platt ScalingBase Model=InternVL3-8B, Confidence Type=Sampling2026.040.801
Isotonic Regr.Base Model=InternVL3-8B, Confidence Type=Sampling2026.040.801
Hist. BinningBase Model=InternVL3-2B, Confidence Type=Sampling2026.040.798
HAC-PlattBase Model=Qwen3-VL-8B, Confidence Type=Verbalized2026.040.793
Hist. BinningBase Model=InternVL3-8B, Confidence Type=Sampling2026.040.785
HAC-PlattBase Model=Qwen3-VL-32B, Confidence Type=Sampling2026.040.784
HAC-GateBase Model=Qwen3-VL-32B, Confidence Type=Sampling2026.040.784
HAC-GateBase Model=Qwen3-VL-8B, Confidence Type=Verbalized2026.040.768
HAC-PlattBase Model=InternVL3-2B, Confidence Type=Verbalized2026.040.762
HAC-PlattBase Model=Qwen3-VL-8B, Confidence Type=Sampling2026.040.76
HAC-GateBase Model=InternVL3-8B, Confidence Type=Verbalized2026.040.76
HAC-GateBase Model=Qwen3-VL-8B, Confidence Type=Sampling2026.040.759
HAC-PlattBase Model=InternVL3-8B, Confidence Type=Verbalized2026.040.757
HAC-GateBase Model=InternVL3-2B, Confidence Type=Verbalized2026.040.753
HAC-GateBase Model=InternVL3-38B, Confidence Type=Sampling2026.040.752
HAC-PlattBase Model=InternVL3-38B, Confidence Type=Sampling2026.040.751
HAC-GateBase Model=Qwen3-VL-32B, Confidence Type=Verbalized2026.040.741
UncalibratedBase Model=Qwen3-VL-8B, Confidence Type=Verbalized2026.040.737
Platt ScalingBase Model=Qwen3-VL-8B, Confidence Type=Verbalized2026.040.737
Isotonic Regr.Base Model=Qwen3-VL-8B, Confidence Type=Verbalized2026.040.737
HAC-PlattBase Model=Qwen3-VL-32B, Confidence Type=Verbalized2026.040.736
HAC-GateBase Model=LLaVA-NeXT-34B, Confidence Type=Verbalized2026.040.725
HAC-GateBase Model=InternVL3-38B, Confidence Type=Verbalized2026.040.72
HAC-PlattBase Model=LLaVA-NeXT-34B, Confidence Type=Verbalized2026.040.719
UncalibratedBase Model=Qwen3-VL-2B, Confidence Type=Sampling2026.040.704
Platt ScalingBase Model=Qwen3-VL-2B, Confidence Type=Sampling2026.040.704
UncalibratedBase Model=Qwen3-VL-32B, Confidence Type=Sampling2026.040.704
Platt ScalingBase Model=Qwen3-VL-32B, Confidence Type=Sampling2026.040.704
Isotonic Regr.Base Model=Qwen3-VL-32B, Confidence Type=Sampling2026.040.702
HAC-PlattBase Model=Qwen3-VL-2B, Confidence Type=Verbalized2026.040.696
HAC-GateBase Model=Qwen3-VL-2B, Confidence Type=Verbalized2026.040.696
HAC-PlattBase Model=InternVL3-38B, Confidence Type=Verbalized2026.040.696
Isotonic Regr.Base Model=Qwen3-VL-2B, Confidence Type=Sampling2026.040.693
Isotonic Regr.Base Model=Qwen3-VL-32B, Confidence Type=Verbalized2026.040.69
HAC-GateBase Model=Qwen3-VL-2B, Confidence Type=Sampling2026.040.689
Hist. BinningBase Model=Qwen3-VL-32B, Confidence Type=Sampling2026.040.689
HAC-PlattBase Model=Qwen3-VL-2B, Confidence Type=Sampling2026.040.688
Hist. BinningBase Model=LLaVA-NeXT-7B, Confidence Type=Sampling2026.040.688
UncalibratedBase Model=InternVL3-38B, Confidence Type=Sampling2026.040.68
Platt ScalingBase Model=InternVL3-38B, Confidence Type=Sampling2026.040.68
HAC-GateBase Model=LLaVA-NeXT-7B, Confidence Type=Verbalized2026.040.678
Hist. BinningBase Model=Qwen3-VL-32B, Confidence Type=Verbalized2026.040.677
Isotonic Regr.Base Model=InternVL3-38B, Confidence Type=Verbalized2026.040.677
Isotonic Regr.Base Model=InternVL3-38B, Confidence Type=Sampling2026.040.676
Hist. BinningBase Model=Qwen3-VL-8B, Confidence Type=Verbalized2026.040.675
UncalibratedBase Model=Qwen3-VL-32B, Confidence Type=Verbalized2026.040.675
Platt ScalingBase Model=Qwen3-VL-32B, Confidence Type=Verbalized2026.040.675
HAC-PlattBase Model=LLaVA-NeXT-7B, Confidence Type=Verbalized2026.040.675
Hist. BinningBase Model=Qwen3-VL-2B, Confidence Type=Sampling2026.040.671
Hist. BinningBase Model=InternVL3-38B, Confidence Type=Verbalized2026.040.668
HAC-PlattBase Model=LLaVA-NeXT-34B, Confidence Type=Sampling2026.040.659
UncalibratedBase Model=Qwen3-VL-8B, Confidence Type=Sampling2026.040.657
Platt ScalingBase Model=Qwen3-VL-8B, Confidence Type=Sampling2026.040.657
Isotonic Regr.Base Model=Qwen3-VL-8B, Confidence Type=Sampling2026.040.657
Isotonic Regr.Base Model=LLaVA-NeXT-7B, Confidence Type=Sampling2026.040.654
Hist. BinningBase Model=Qwen3-VL-8B, Confidence Type=Sampling2026.040.65
HAC-PlattBase Model=LLaVA-NeXT-7B, Confidence Type=Sampling2026.040.648
Hist. BinningBase Model=InternVL3-38B, Confidence Type=Sampling2026.040.647
Isotonic Regr.Base Model=InternVL3-8B, Confidence Type=Verbalized2026.040.635
Hist. BinningBase Model=InternVL3-8B, Confidence Type=Verbalized2026.040.635
UncalibratedBase Model=InternVL3-8B, Confidence Type=Verbalized2026.040.633
Platt ScalingBase Model=InternVL3-8B, Confidence Type=Verbalized2026.040.633
HAC-GateBase Model=LLaVA-NeXT-34B, Confidence Type=Sampling2026.040.633
UncalibratedBase Model=InternVL3-38B, Confidence Type=Verbalized2026.040.629
Platt ScalingBase Model=InternVL3-38B, Confidence Type=Verbalized2026.040.629
UncalibratedBase Model=LLaVA-NeXT-7B, Confidence Type=Sampling2026.040.625
Platt ScalingBase Model=LLaVA-NeXT-7B, Confidence Type=Sampling2026.040.625
HAC-GateBase Model=LLaVA-NeXT-7B, Confidence Type=Sampling2026.040.625
UncalibratedBase Model=LLaVA-NeXT-34B, Confidence Type=Sampling2026.040.607
Platt ScalingBase Model=LLaVA-NeXT-34B, Confidence Type=Sampling2026.040.607
UncalibratedBase Model=LLaVA-NeXT-34B, Confidence Type=Verbalized2026.040.606
Platt ScalingBase Model=LLaVA-NeXT-34B, Confidence Type=Verbalized2026.040.606
Isotonic Regr.Base Model=LLaVA-NeXT-34B, Confidence Type=Verbalized2026.040.606
Hist. BinningBase Model=LLaVA-NeXT-34B, Confidence Type=Verbalized2026.040.606
Isotonic Regr.Base Model=LLaVA-NeXT-34B, Confidence Type=Sampling2026.040.588
UncalibratedBase Model=Qwen3-VL-2B, Confidence Type=Verbalized2026.040.577
Platt ScalingBase Model=Qwen3-VL-2B, Confidence Type=Verbalized2026.040.577
Isotonic Regr.Base Model=Qwen3-VL-2B, Confidence Type=Verbalized2026.040.577
UncalibratedBase Model=LLaVA-NeXT-7B, Confidence Type=Verbalized2026.040.565
Platt ScalingBase Model=LLaVA-NeXT-7B, Confidence Type=Verbalized2026.040.565
Hist. BinningBase Model=LLaVA-NeXT-7B, Confidence Type=Verbalized2026.040.565
Hist. BinningBase Model=Qwen3-VL-2B, Confidence Type=Verbalized2026.040.554
Hist. BinningBase Model=LLaVA-NeXT-34B, Confidence Type=Sampling2026.040.553
Isotonic Regr.Base Model=LLaVA-NeXT-7B, Confidence Type=Verbalized2026.040.55
Isotonic Regr.Base Model=InternVL3-2B, Confidence Type=Verbalized2026.040.532
Hist. BinningBase Model=InternVL3-2B, Confidence Type=Verbalized2026.040.528
UncalibratedBase Model=InternVL3-2B, Confidence Type=Verbalized2026.040.447
Platt ScalingBase Model=InternVL3-2B, Confidence Type=Verbalized2026.040.447