List your company

Medical Visual Question Answering on VQA-Med Open

0.006ECEInternVL3-2B
0.000560.037280.0740.11072Apr 2, 2026

Evaluation results

MethodLinks
InternVL3-2BCalibration Strategy=Platt Scaling, Confidence Mode=Verbalized2026.040.006
Qwen3-VL-2BCalibration Strategy=Hist. Binning, Confidence Mode=Verbalized2026.040.012
Qwen3-VL-2BCalibration Strategy=Isotonic Regr., Confidence Mode=Verbalized2026.040.02
InternVL3-8BCalibration Strategy=Isotonic Regr., Confidence Mode=Verbalized2026.040.024
InternVL3-8BCalibration Strategy=Hist. Binning, Confidence Mode=Verbalized2026.040.024
InternVL3-38BCalibration Strategy=Isotonic Regr., Confidence Mode=Verbalized2026.040.026
LLaVA-NeXT-7BCalibration Strategy=Isotonic Regr., Confidence Mode=Verbalized2026.040.026
LLaVA-NeXT-7BCalibration Strategy=Hist. Binning, Confidence Mode=Verbalized2026.040.026
InternVL3-8BCalibration Strategy=Platt Scaling, Confidence Mode=Verbalized2026.040.028
LLaVA-NeXT-7BCalibration Strategy=Platt Scaling, Confidence Mode=Verbalized2026.040.028
InternVL3-38BCalibration Strategy=Hist. Binning, Confidence Mode=Verbalized2026.040.029
Qwen3-VL-32BCalibration Strategy=Isotonic Regr., Confidence Mode=Sampling2026.040.031
Qwen3-VL-2BCalibration Strategy=Platt Scaling, Confidence Mode=Verbalized2026.040.032
InternVL3-2BCalibration Strategy=Isotonic Regr., Confidence Mode=Verbalized2026.040.033
InternVL3-2BCalibration Strategy=Hist. Binning, Confidence Mode=Verbalized2026.040.034
Qwen3-VL-32BCalibration Strategy=Hist. Binning, Confidence Mode=Verbalized2026.040.035
Qwen3-VL-32BCalibration Strategy=Isotonic Regr., Confidence Mode=Verbalized2026.040.036
Qwen3-VL-32BCalibration Strategy=Hist. Binning, Confidence Mode=Sampling2026.040.041
Qwen3-VL-8BCalibration Strategy=Hist. Binning, Confidence Mode=Sampling2026.040.042
Qwen3-VL-8BCalibration Strategy=Hist. Binning, Confidence Mode=Verbalized2026.040.042
Qwen3-VL-8BCalibration Strategy=Isotonic Regr., Confidence Mode=Sampling2026.040.044
LLaVA-NeXT-34BCalibration Strategy=Isotonic Regr., Confidence Mode=Sampling2026.040.047
LLaVA-NeXT-34BCalibration Strategy=Isotonic Regr., Confidence Mode=Verbalized2026.040.047
LLaVA-NeXT-34BCalibration Strategy=Hist. Binning, Confidence Mode=Verbalized2026.040.047
LLaVA-NeXT-7BCalibration Strategy=Isotonic Regr., Confidence Mode=Sampling2026.040.049
Qwen3-VL-8BCalibration Strategy=Platt Scaling, Confidence Mode=Sampling2026.040.051
Qwen3-VL-32BCalibration Strategy=Platt Scaling, Confidence Mode=Sampling2026.040.055
InternVL3-38BCalibration Strategy=Isotonic Regr., Confidence Mode=Sampling2026.040.055
Qwen3-VL-2BCalibration Strategy=Isotonic Regr., Confidence Mode=Sampling2026.040.059
LLaVA-NeXT-34BCalibration Strategy=Platt Scaling, Confidence Mode=Verbalized2026.040.064
InternVL3-38BCalibration Strategy=Platt Scaling, Confidence Mode=Sampling2026.040.065
Qwen3-VL-2BCalibration Strategy=Platt Scaling, Confidence Mode=Sampling2026.040.067
InternVL3-38BCalibration Strategy=Hist. Binning, Confidence Mode=Sampling2026.040.067
LLaVA-NeXT-34BCalibration Strategy=Platt Scaling, Confidence Mode=Sampling2026.040.072
Qwen3-VL-2BCalibration Strategy=HAC-Platt, Confidence Mode=Sampling2026.040.076
Qwen3-VL-2BCalibration Strategy=Hist. Binning, Confidence Mode=Sampling2026.040.077
InternVL3-8BCalibration Strategy=Isotonic Regr., Confidence Mode=Sampling2026.040.078
LLaVA-NeXT-7BCalibration Strategy=Hist. Binning, Confidence Mode=Sampling2026.040.079
Qwen3-VL-8BCalibration Strategy=Platt Scaling, Confidence Mode=Verbalized2026.040.083
Qwen3-VL-8BCalibration Strategy=Isotonic Regr., Confidence Mode=Verbalized2026.040.085
InternVL3-38BCalibration Strategy=HAC-Platt, Confidence Mode=Sampling2026.040.085
InternVL3-38BCalibration Strategy=HAC-Gate, Confidence Mode=Sampling2026.040.087
LLaVA-NeXT-34BCalibration Strategy=HAC-Gate, Confidence Mode=Sampling2026.040.089
LLaVA-NeXT-7BCalibration Strategy=HAC-Platt, Confidence Mode=Verbalized2026.040.09
LLaVA-NeXT-34BCalibration Strategy=Hist. Binning, Confidence Mode=Sampling2026.040.091
Qwen3-VL-2BCalibration Strategy=HAC-Gate, Confidence Mode=Sampling2026.040.093
InternVL3-8BCalibration Strategy=Hist. Binning, Confidence Mode=Sampling2026.040.098
LLaVA-NeXT-7BCalibration Strategy=HAC-Gate, Confidence Mode=Sampling2026.040.098
LLaVA-NeXT-7BCalibration Strategy=HAC-Gate, Confidence Mode=Verbalized2026.040.098
LLaVA-NeXT-34BCalibration Strategy=HAC-Platt, Confidence Mode=Sampling2026.040.099
InternVL3-2BCalibration Strategy=HAC-Platt, Confidence Mode=Sampling2026.040.104
Hist. BinningBackbone=InternVL3-38B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.106
InternVL3-2BCalibration Strategy=HAC-Gate, Confidence Mode=Sampling2026.040.107
Qwen3-VL-32BCalibration Strategy=Platt Scaling, Confidence Mode=Verbalized2026.040.108
Qwen3-VL-2BCalibration Strategy=HAC-Gate, Confidence Mode=Verbalized2026.040.112
InternVL3-2BCalibration Strategy=Hist. Binning, Confidence Mode=Sampling2026.040.113
InternVL3-2BCalibration Strategy=Isotonic Regr., Confidence Mode=Sampling2026.040.114
Hist. BinningBackbone=LLaVA-NeXT-7B, Confidence Type=Verbalized, Protocol=5-fold CV2026.040.114
Qwen3-VL-32BCalibration Strategy=HAC-Gate, Confidence Mode=Sampling2026.040.116
LLaVA-NeXT-7BCalibration Strategy=Platt Scaling, Confidence Mode=Sampling2026.040.116
Isotonic Regr.Backbone=InternVL3-38B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.116
Qwen3-VL-32BCalibration Strategy=HAC-Platt, Confidence Mode=Sampling2026.040.117
Platt ScalingBackbone=InternVL3-38B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.117
Qwen3-VL-8BCalibration Strategy=HAC-Gate, Confidence Mode=Verbalized2026.040.118
HAC-PlattBackbone=InternVL3-38B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.118
HAC-GateBackbone=InternVL3-38B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.118
InternVL3-2BCalibration Strategy=Platt Scaling, Confidence Mode=Sampling2026.040.119
Qwen3-VL-2BCalibration Strategy=HAC-Platt, Confidence Mode=Verbalized2026.040.121
HAC-GateBackbone=InternVL3-2B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.122
Hist. BinningBackbone=LLaVA-NeXT-7B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.122
Isotonic Regr.Backbone=LLaVA-NeXT-7B, Confidence Type=Verbalized, Protocol=5-fold CV2026.040.124
Isotonic Regr.Backbone=Qwen3-VL-2B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.125
Platt ScalingBackbone=LLaVA-NeXT-7B, Confidence Type=Verbalized, Protocol=5-fold CV2026.040.125
Qwen3-VL-8BCalibration Strategy=HAC-Platt, Confidence Mode=Sampling2026.040.127
Platt ScalingBackbone=Qwen3-VL-8B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.127
Isotonic Regr.Backbone=LLaVA-NeXT-7B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.128
LLaVA-NeXT-34BCalibration Strategy=HAC-Gate, Confidence Mode=Verbalized2026.040.129
Platt ScalingBackbone=InternVL3-2B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.13
HAC-PlattBackbone=InternVL3-2B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.13
Qwen3-VL-32BCalibration Strategy=HAC-Gate, Confidence Mode=Verbalized2026.040.131
Qwen3-VL-8BCalibration Strategy=HAC-Platt, Confidence Mode=Verbalized2026.040.132
Platt ScalingBackbone=Qwen3-VL-2B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.132
InternVL3-8BCalibration Strategy=Platt Scaling, Confidence Mode=Sampling2026.040.133
Isotonic Regr.Backbone=LLaVA-NeXT-34B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.133
Isotonic Regr.Backbone=Qwen3-VL-8B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.134
Isotonic Regr.Backbone=LLaVA-NeXT-34B, Confidence Type=Verbalized, Protocol=5-fold CV2026.040.134
Hist. BinningBackbone=LLaVA-NeXT-34B, Confidence Type=Verbalized, Protocol=5-fold CV2026.040.134
Qwen3-VL-8BCalibration Strategy=HAC-Gate, Confidence Mode=Sampling2026.040.135
HAC-PlattBackbone=Qwen3-VL-2B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.135
Isotonic Regr.Backbone=InternVL3-2B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.135
Qwen3-VL-32BCalibration Strategy=HAC-Platt, Confidence Mode=Verbalized2026.040.137
HAC-PlattBackbone=Qwen3-VL-8B, Confidence Type=Verbalized, Protocol=5-fold CV2026.040.137
Isotonic Regr.Backbone=InternVL3-8B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.139
HAC-PlattBackbone=LLaVA-NeXT-7B, Confidence Type=Verbalized, Protocol=5-fold CV2026.040.139
HAC-GateBackbone=LLaVA-NeXT-34B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.14
InternVL3-8BCalibration Strategy=HAC-Platt, Confidence Mode=Verbalized2026.040.141
InternVL3-38BCalibration Strategy=Platt Scaling, Confidence Mode=Verbalized2026.040.141
LLaVA-NeXT-34BCalibration Strategy=HAC-Platt, Confidence Mode=Verbalized2026.040.141
HAC-GateBackbone=LLaVA-NeXT-7B, Confidence Type=Sampling, Protocol=5-fold CV2026.040.141
LLaVA-NeXT-7BCalibration Strategy=HAC-Platt, Confidence Mode=Sampling2026.040.142