List your company

Medical Visual Question Answering on SLAKE Open 1.0 (test)

2.6ECEHist. Binning
0.88412.46724.0535.633Apr 2, 2026

Evaluation results

MethodLinks
Hist. BinningBackbone=Qwen3-VL-2B, Confidence Source=Verbalized, 5-fold CV=true2026.042.6
Isotonic Regr.Backbone=InternVL3-8B, Confidence Source=Verbalized, 5-fold CV=true2026.042.7
Isotonic Regr.Backbone=Qwen3-VL-2B, Confidence Source=Verbalized, 5-fold CV=true2026.043
Hist. BinningBackbone=InternVL3-8B, Confidence Source=Verbalized, 5-fold CV=true2026.043
Platt ScalingBackbone=Qwen3-VL-2B, Confidence Source=Verbalized, 5-fold CV=true2026.043.1
Isotonic Regr.Backbone=InternVL3-2B, Confidence Source=Verbalized, 5-fold CV=true2026.043.4
Hist. BinningBackbone=InternVL3-2B, Confidence Source=Verbalized, 5-fold CV=true2026.043.6
Hist. BinningBackbone=Qwen3-VL-32B, Confidence Source=Verbalized, 5-fold CV=true2026.043.7
Hist. BinningBackbone=InternVL3-38B, Confidence Source=Verbalized, 5-fold CV=true2026.044
Isotonic Regr.Backbone=Qwen3-VL-32B, Confidence Source=Sampling, 5-fold CV=true2026.044.1
Isotonic Regr.Backbone=Qwen3-VL-8B, Confidence Source=Sampling, 5-fold CV=true2026.044.2
Hist. BinningBackbone=Qwen3-VL-8B, Confidence Source=Verbalized, 5-fold CV=true2026.044.2
Isotonic Regr.Backbone=LLaVA-NeXT-7B, Confidence Source=Verbalized, 5-fold CV=true2026.044.3
Isotonic Regr.Backbone=InternVL3-38B, Confidence Source=Verbalized, 5-fold CV=true2026.044.4
Hist. BinningBackbone=LLaVA-NeXT-7B, Confidence Source=Verbalized, 5-fold CV=true2026.044.4
Isotonic Regr.Backbone=Qwen3-VL-8B, Confidence Source=Verbalized, 5-fold CV=true2026.044.5
Isotonic Regr.Backbone=Qwen3-VL-32B, Confidence Source=Verbalized, 5-fold CV=true2026.045
Hist. BinningBackbone=Qwen3-VL-32B, Confidence Source=Sampling, 5-fold CV=true2026.045.1
Platt ScalingBackbone=Qwen3-VL-32B, Confidence Source=Sampling, 5-fold CV=true2026.045.2
Hist. BinningBackbone=Qwen3-VL-8B, Confidence Source=Sampling, 5-fold CV=true2026.045.5
Platt ScalingBackbone=LLaVA-NeXT-7B, Confidence Source=Verbalized, 5-fold CV=true2026.045.5
Platt ScalingBackbone=Qwen3-VL-8B, Confidence Source=Verbalized, 5-fold CV=true2026.045.6
Platt ScalingBackbone=Qwen3-VL-8B, Confidence Source=Sampling, 5-fold CV=true2026.045.7
Isotonic Regr.Backbone=Qwen3-VL-2B, Confidence Source=Sampling, 5-fold CV=true2026.045.8
Platt ScalingBackbone=InternVL3-8B, Confidence Source=Verbalized, 5-fold CV=true2026.045.8
Platt ScalingBackbone=InternVL3-38B, Confidence Source=Verbalized, 5-fold CV=true2026.046.2
Platt ScalingBackbone=InternVL3-2B, Confidence Source=Verbalized, 5-fold CV=true2026.046.3
Isotonic Regr.Backbone=InternVL3-38B, Confidence Source=Sampling, 5-fold CV=true2026.046.5
Hist. BinningBackbone=LLaVA-NeXT-34B, Confidence Source=Verbalized, 5-fold CV=true2026.046.6
Isotonic Regr.Backbone=LLaVA-NeXT-34B, Confidence Source=Verbalized, 5-fold CV=true2026.046.7
Hist. BinningBackbone=InternVL3-2B, Confidence Source=Sampling, 5-fold CV=true2026.046.9
Platt ScalingBackbone=LLaVA-NeXT-34B, Confidence Source=Verbalized, 5-fold CV=true2026.046.9
HAC-GateBackbone=Qwen3-VL-32B, Confidence Source=Verbalized, 5-fold CV=true2026.047
Hist. BinningBackbone=InternVL3-38B, Confidence Source=Sampling, 5-fold CV=true2026.047
Hist. BinningBackbone=Qwen3-VL-2B, Confidence Source=Sampling, 5-fold CV=true2026.047.1
Platt ScalingBackbone=Qwen3-VL-32B, Confidence Source=Verbalized, 5-fold CV=true2026.047.5
Isotonic Regr.Backbone=InternVL3-8B, Confidence Source=Sampling, 5-fold CV=true2026.047.5
Hist. BinningBackbone=InternVL3-8B, Confidence Source=Sampling, 5-fold CV=true2026.047.5
HAC-GateBackbone=InternVL3-8B, Confidence Source=Sampling, 5-fold CV=true2026.047.6
Isotonic Regr.Backbone=LLaVA-NeXT-7B, Confidence Source=Sampling, 5-fold CV=true2026.047.7
HAC-GateBackbone=InternVL3-8B, Confidence Source=Verbalized, 5-fold CV=true2026.047.8
HAC-GateBackbone=Qwen3-VL-8B, Confidence Source=Sampling, 5-fold CV=true2026.047.9
Isotonic Regr.Backbone=InternVL3-2B, Confidence Source=Sampling, 5-fold CV=true2026.047.9
HAC-GateBackbone=Qwen3-VL-8B, Confidence Source=Verbalized, 5-fold CV=true2026.048.2
Platt ScalingBackbone=InternVL3-8B, Confidence Source=Sampling, 5-fold CV=true2026.048.2
HAC-PlattBackbone=InternVL3-8B, Confidence Source=Verbalized, 5-fold CV=true2026.048.2
HAC-GateBackbone=Qwen3-VL-32B, Confidence Source=Sampling, 5-fold CV=true2026.048.3
Hist. BinningBackbone=LLaVA-NeXT-7B, Confidence Source=Sampling, 5-fold CV=true2026.048.4
HAC-GateBackbone=InternVL3-38B, Confidence Source=Verbalized, 5-fold CV=true2026.048.5
Platt ScalingBackbone=LLaVA-NeXT-7B, Confidence Source=Sampling, 5-fold CV=true2026.048.5
HAC-PlattBackbone=Qwen3-VL-8B, Confidence Source=Sampling, 5-fold CV=true2026.048.8
HAC-PlattBackbone=Qwen3-VL-32B, Confidence Source=Verbalized, 5-fold CV=true2026.048.8
Platt ScalingBackbone=InternVL3-2B, Confidence Source=Sampling, 5-fold CV=true2026.048.9
HAC-PlattBackbone=InternVL3-38B, Confidence Source=Sampling, 5-fold CV=true2026.048.9
Platt ScalingBackbone=Qwen3-VL-2B, Confidence Source=Sampling, 5-fold CV=true2026.049.1
HAC-GateBackbone=Qwen3-VL-2B, Confidence Source=Verbalized, 5-fold CV=true2026.049.1
HAC-PlattBackbone=Qwen3-VL-8B, Confidence Source=Verbalized, 5-fold CV=true2026.049.3
HAC-PlattBackbone=Qwen3-VL-2B, Confidence Source=Verbalized, 5-fold CV=true2026.049.5
HAC-PlattBackbone=Qwen3-VL-32B, Confidence Source=Sampling, 5-fold CV=true2026.049.5
HAC-PlattBackbone=InternVL3-8B, Confidence Source=Sampling, 5-fold CV=true2026.049.5
Platt ScalingBackbone=InternVL3-38B, Confidence Source=Sampling, 5-fold CV=true2026.049.5
HAC-GateBackbone=InternVL3-38B, Confidence Source=Sampling, 5-fold CV=true2026.049.7
HAC-PlattBackbone=Qwen3-VL-2B, Confidence Source=Sampling, 5-fold CV=true2026.0410.1
HAC-GateBackbone=InternVL3-2B, Confidence Source=Sampling, 5-fold CV=true2026.0410.1
HAC-GateBackbone=LLaVA-NeXT-7B, Confidence Source=Sampling, 5-fold CV=true2026.0410.4
HAC-PlattBackbone=LLaVA-NeXT-7B, Confidence Source=Verbalized, 5-fold CV=true2026.0410.6
HAC-PlattBackbone=InternVL3-2B, Confidence Source=Verbalized, 5-fold CV=true2026.0410.7
HAC-PlattBackbone=InternVL3-38B, Confidence Source=Verbalized, 5-fold CV=true2026.0410.7
HAC-GateBackbone=LLaVA-NeXT-7B, Confidence Source=Verbalized, 5-fold CV=true2026.0410.7
HAC-GateBackbone=InternVL3-2B, Confidence Source=Verbalized, 5-fold CV=true2026.0410.8
HAC-PlattBackbone=LLaVA-NeXT-7B, Confidence Source=Sampling, 5-fold CV=true2026.0410.8
HAC-PlattBackbone=InternVL3-2B, Confidence Source=Sampling, 5-fold CV=true2026.0411
HAC-GateBackbone=Qwen3-VL-2B, Confidence Source=Sampling, 5-fold CV=true2026.0411.7
HAC-GateBackbone=LLaVA-NeXT-34B, Confidence Source=Verbalized, 5-fold CV=true2026.0412.4
Isotonic Regr.Backbone=LLaVA-NeXT-34B, Confidence Source=Sampling, 5-fold CV=true2026.0413.4
HAC-PlattBackbone=LLaVA-NeXT-34B, Confidence Source=Verbalized, 5-fold CV=true2026.0414.6
Hist. BinningBackbone=LLaVA-NeXT-34B, Confidence Source=Sampling, 5-fold CV=true2026.0414.8
HAC-GateBackbone=LLaVA-NeXT-34B, Confidence Source=Sampling, 5-fold CV=true2026.0416.1
HAC-PlattBackbone=LLaVA-NeXT-34B, Confidence Source=Sampling, 5-fold CV=true2026.0416.2
Platt ScalingBackbone=LLaVA-NeXT-34B, Confidence Source=Sampling, 5-fold CV=true2026.0417.2
UncalibratedBackbone=InternVL3-8B, Confidence Source=Sampling, 5-fold CV=true2026.0422.9
UncalibratedBackbone=InternVL3-2B, Confidence Source=Sampling, 5-fold CV=true2026.0423
UncalibratedBackbone=InternVL3-38B, Confidence Source=Sampling, 5-fold CV=true2026.0423.8
UncalibratedBackbone=LLaVA-NeXT-7B, Confidence Source=Sampling, 5-fold CV=true2026.0425
UncalibratedBackbone=Qwen3-VL-32B, Confidence Source=Verbalized, 5-fold CV=true2026.0425.7
UncalibratedBackbone=InternVL3-8B, Confidence Source=Verbalized, 5-fold CV=true2026.0426.4
UncalibratedBackbone=Qwen3-VL-32B, Confidence Source=Sampling, 5-fold CV=true2026.0427.2
UncalibratedBackbone=LLaVA-NeXT-34B, Confidence Source=Sampling, 5-fold CV=true2026.0428.9
UncalibratedBackbone=Qwen3-VL-2B, Confidence Source=Sampling, 5-fold CV=true2026.0429.8
UncalibratedBackbone=Qwen3-VL-8B, Confidence Source=Verbalized, 5-fold CV=true2026.0429.9
UncalibratedBackbone=Qwen3-VL-8B, Confidence Source=Sampling, 5-fold CV=true2026.0433.9
UncalibratedBackbone=InternVL3-2B, Confidence Source=Verbalized, 5-fold CV=true2026.0434
UncalibratedBackbone=Qwen3-VL-2B, Confidence Source=Verbalized, 5-fold CV=true2026.0434.6
UncalibratedBackbone=InternVL3-38B, Confidence Source=Verbalized, 5-fold CV=true2026.0435.3
UncalibratedBackbone=LLaVA-NeXT-7B, Confidence Source=Verbalized, 5-fold CV=true2026.0445
UncalibratedBackbone=LLaVA-NeXT-34B, Confidence Source=Verbalized, 5-fold CV=true2026.0445.5