List your company

Medical Visual Question Answering on VQA-Med Closed (AUROC)

81.8AUROCHAC-Platt
32.29645.1485870.852Apr 2, 2026

Evaluation results

MethodLinks
HAC-PlattBase Model=InternVL3-38B, Confidence Type=Verbalized2026.0481.8
HAC-GateBase Model=InternVL3-38B, Confidence Type=Verbalized2026.0481.8
Hist. BinningBase Model=InternVL3-2B, Confidence Type=Sampling2026.0479.9
HAC-PlattBase Model=InternVL3-8B, Confidence Type=Sampling2026.0479.3
HAC-GateBase Model=InternVL3-8B, Confidence Type=Sampling2026.0479.3
UncalibratedBase Model=InternVL3-38B, Confidence Type=Verbalized2026.0479.1
Platt ScalingBase Model=InternVL3-38B, Confidence Type=Verbalized2026.0479.1
HAC-PlattBase Model=Qwen3-VL-8B, Confidence Type=Sampling2026.0478.6
HAC-PlattBase Model=Qwen3-VL-8B, Confidence Type=Verbalized2026.0478
Isotonic Regr.Base Model=InternVL3-38B, Confidence Type=Verbalized2026.0477.7
HAC-GateBase Model=Qwen3-VL-8B, Confidence Type=Verbalized2026.0477.3
HAC-GateBase Model=Qwen3-VL-8B, Confidence Type=Sampling2026.0477.1
UncalibratedBase Model=InternVL3-8B, Confidence Type=Sampling2026.0476.2
Platt ScalingBase Model=InternVL3-8B, Confidence Type=Sampling2026.0476.2
Isotonic Regr.Base Model=InternVL3-2B, Confidence Type=Sampling2026.0475.6
UncalibratedBase Model=InternVL3-2B, Confidence Type=Sampling2026.0473.9
Platt ScalingBase Model=InternVL3-2B, Confidence Type=Sampling2026.0473.9
Hist. BinningBase Model=InternVL3-38B, Confidence Type=Verbalized2026.0473.6
HAC-PlattBase Model=InternVL3-2B, Confidence Type=Sampling2026.0473.3
HAC-GateBase Model=InternVL3-2B, Confidence Type=Sampling2026.0473.3
Isotonic Regr.Base Model=InternVL3-8B, Confidence Type=Sampling2026.0472.5
Hist. BinningBase Model=InternVL3-8B, Confidence Type=Sampling2026.0465.3
HAC-PlattBase Model=Qwen3-VL-32B, Confidence Type=Verbalized2026.0464.7
HAC-PlattBase Model=InternVL3-8B, Confidence Type=Verbalized2026.0464.1
HAC-GateBase Model=LLaVA-NeXT-7B, Confidence Type=Verbalized2026.0463.7
HAC-GateBase Model=Qwen3-VL-32B, Confidence Type=Verbalized2026.0463.3
HAC-PlattBase Model=LLaVA-NeXT-7B, Confidence Type=Verbalized2026.0463.1
HAC-GateBase Model=InternVL3-8B, Confidence Type=Verbalized2026.0462.3
UncalibratedBase Model=Qwen3-VL-32B, Confidence Type=Verbalized2026.0460.7
Platt ScalingBase Model=Qwen3-VL-32B, Confidence Type=Verbalized2026.0460.7
UncalibratedBase Model=InternVL3-2B, Confidence Type=Verbalized2026.0458.7
Platt ScalingBase Model=InternVL3-2B, Confidence Type=Verbalized2026.0458.7
HAC-PlattBase Model=InternVL3-2B, Confidence Type=Verbalized2026.0458.7
Hist. BinningBase Model=InternVL3-38B, Confidence Type=Sampling2026.0458.7
HAC-GateBase Model=InternVL3-2B, Confidence Type=Verbalized2026.0457.4
HAC-GateBase Model=LLaVA-NeXT-34B, Confidence Type=Sampling2026.0457.1
UncalibratedBase Model=LLaVA-NeXT-34B, Confidence Type=Sampling2026.0456.9
Platt ScalingBase Model=LLaVA-NeXT-34B, Confidence Type=Sampling2026.0456.9
UncalibratedBase Model=Qwen3-VL-2B, Confidence Type=Sampling2026.0456.7
Platt ScalingBase Model=Qwen3-VL-2B, Confidence Type=Sampling2026.0456.7
Isotonic Regr.Base Model=Qwen3-VL-2B, Confidence Type=Sampling2026.0456.7
UncalibratedBase Model=LLaVA-NeXT-7B, Confidence Type=Verbalized2026.0456.5
Platt ScalingBase Model=LLaVA-NeXT-7B, Confidence Type=Verbalized2026.0456.5
Hist. BinningBase Model=Qwen3-VL-2B, Confidence Type=Sampling2026.0456.4
Isotonic Regr.Base Model=Qwen3-VL-32B, Confidence Type=Verbalized2026.0456.1
Isotonic Regr.Base Model=Qwen3-VL-2B, Confidence Type=Verbalized2026.0456
Isotonic Regr.Base Model=LLaVA-NeXT-7B, Confidence Type=Sampling2026.0456
HAC-GateBase Model=LLaVA-NeXT-7B, Confidence Type=Sampling2026.0455.9
HAC-PlattBase Model=Qwen3-VL-2B, Confidence Type=Verbalized2026.0455.7
UncalibratedBase Model=LLaVA-NeXT-7B, Confidence Type=Sampling2026.0455.6
Platt ScalingBase Model=LLaVA-NeXT-7B, Confidence Type=Sampling2026.0455.6
UncalibratedBase Model=Qwen3-VL-2B, Confidence Type=Verbalized2026.0454.9
Platt ScalingBase Model=Qwen3-VL-2B, Confidence Type=Verbalized2026.0454.9
UncalibratedBase Model=Qwen3-VL-8B, Confidence Type=Sampling2026.0454.9
Platt ScalingBase Model=Qwen3-VL-8B, Confidence Type=Sampling2026.0454.9
Hist. BinningBase Model=InternVL3-2B, Confidence Type=Verbalized2026.0454.7
Isotonic Regr.Base Model=LLaVA-NeXT-34B, Confidence Type=Verbalized2026.0453.6
Hist. BinningBase Model=LLaVA-NeXT-7B, Confidence Type=Sampling2026.0453
UncalibratedBase Model=LLaVA-NeXT-34B, Confidence Type=Verbalized2026.0452.5
Platt ScalingBase Model=LLaVA-NeXT-34B, Confidence Type=Verbalized2026.0452.5
Hist. BinningBase Model=LLaVA-NeXT-34B, Confidence Type=Verbalized2026.0452.5
Isotonic Regr.Base Model=InternVL3-2B, Confidence Type=Verbalized2026.0452.4
HAC-PlattBase Model=LLaVA-NeXT-7B, Confidence Type=Sampling2026.0452.4
UncalibratedBase Model=Qwen3-VL-8B, Confidence Type=Verbalized2026.0451.8
Platt ScalingBase Model=Qwen3-VL-8B, Confidence Type=Verbalized2026.0451.8
Hist. BinningBase Model=LLaVA-NeXT-34B, Confidence Type=Sampling2026.0451.8
Isotonic Regr.Base Model=Qwen3-VL-8B, Confidence Type=Sampling2026.0451.6
Hist. BinningBase Model=Qwen3-VL-2B, Confidence Type=Verbalized2026.0451.1
Hist. BinningBase Model=InternVL3-8B, Confidence Type=Verbalized2026.0450.9
Isotonic Regr.Base Model=LLaVA-NeXT-7B, Confidence Type=Verbalized2026.0450.7
UncalibratedBase Model=Qwen3-VL-32B, Confidence Type=Sampling2026.0450
Platt ScalingBase Model=Qwen3-VL-32B, Confidence Type=Sampling2026.0450
Isotonic Regr.Base Model=Qwen3-VL-32B, Confidence Type=Sampling2026.0450
Hist. BinningBase Model=Qwen3-VL-32B, Confidence Type=Sampling2026.0450
Isotonic Regr.Base Model=InternVL3-8B, Confidence Type=Verbalized2026.0450
HAC-PlattBase Model=Qwen3-VL-2B, Confidence Type=Sampling2026.0449.8
HAC-GateBase Model=Qwen3-VL-2B, Confidence Type=Sampling2026.0449.8
Hist. BinningBase Model=Qwen3-VL-8B, Confidence Type=Sampling2026.0449.7
UncalibratedBase Model=InternVL3-8B, Confidence Type=Verbalized2026.0449.1
Platt ScalingBase Model=InternVL3-8B, Confidence Type=Verbalized2026.0449.1
HAC-GateBase Model=Qwen3-VL-2B, Confidence Type=Verbalized2026.0448.6
Isotonic Regr.Base Model=LLaVA-NeXT-34B, Confidence Type=Sampling2026.0448.1
Hist. BinningBase Model=LLaVA-NeXT-7B, Confidence Type=Verbalized2026.0447.1
UncalibratedBase Model=InternVL3-38B, Confidence Type=Sampling2026.0446.3
Platt ScalingBase Model=InternVL3-38B, Confidence Type=Sampling2026.0446.3
HAC-GateBase Model=InternVL3-38B, Confidence Type=Sampling2026.0446.3
HAC-PlattBase Model=LLaVA-NeXT-34B, Confidence Type=Sampling2026.0446.1
HAC-GateBase Model=LLaVA-NeXT-34B, Confidence Type=Verbalized2026.0445.8
Isotonic Regr.Base Model=InternVL3-38B, Confidence Type=Sampling2026.0444.4
HAC-PlattBase Model=LLaVA-NeXT-34B, Confidence Type=Verbalized2026.0443.1
Isotonic Regr.Base Model=Qwen3-VL-8B, Confidence Type=Verbalized2026.0443
HAC-PlattBase Model=InternVL3-38B, Confidence Type=Sampling2026.0442.3
HAC-PlattBase Model=Qwen3-VL-32B, Confidence Type=Sampling2026.0442.2
HAC-GateBase Model=Qwen3-VL-32B, Confidence Type=Sampling2026.0442.2
Hist. BinningBase Model=Qwen3-VL-32B, Confidence Type=Verbalized2026.0440.2
Hist. BinningBase Model=Qwen3-VL-8B, Confidence Type=Verbalized2026.0434.2