List your company

Medical Visual Question Answering on VQA-RAD (Closed)

1.3ECEQwen3-VL-2B
-0.0769.21218.527.788Apr 2, 2026

Evaluation results

MethodLinks
Qwen3-VL-2BCalibration Method=Platt Scaling, Confidence Type=Verbalized, 5-fold CV=true2026.041.3
Qwen3-VL-2BCalibration Method=Hist. Binning, Confidence Type=Verbalized, 5-fold CV=true2026.041.3
Qwen3-VL-2BCalibration Method=Isotonic Regr., Confidence Type=Verbalized, 5-fold CV=true2026.041.4
LLaVA-NeXT-34BCalibration Method=Platt Scaling, Confidence Type=Verbalized, 5-fold CV=true2026.041.9
InternVL3-8BCalibration Method=Platt Scaling, Confidence Type=Verbalized, 5-fold CV=true2026.042.3
InternVL3-8BCalibration Method=Isotonic Regr., Confidence Type=Verbalized, 5-fold CV=true2026.042.8
LLaVA-NeXT-7BCalibration Method=Platt Scaling, Confidence Type=Verbalized, 5-fold CV=true2026.042.9
LLaVA-NeXT-34BCalibration Method=HAC-Platt, Confidence Type=Verbalized, 5-fold CV=true2026.043
Qwen3-VL-2BCalibration Method=HAC-Gate, Confidence Type=Verbalized, 5-fold CV=true2026.043.2
InternVL3-8BCalibration Method=HAC-Platt, Confidence Type=Verbalized, 5-fold CV=true2026.043.3
InternVL3-8BCalibration Method=HAC-Gate, Confidence Type=Verbalized, 5-fold CV=true2026.043.5
Qwen3-VL-8BCalibration Method=Isotonic Regr., Confidence Type=Sampling, 5-fold CV=true2026.043.7
InternVL3-38BCalibration Method=HAC-Gate, Confidence Type=Verbalized, 5-fold CV=true2026.043.7
LLaVA-NeXT-7BCalibration Method=HAC-Platt, Confidence Type=Verbalized, 5-fold CV=true2026.043.8
LLaVA-NeXT-34BCalibration Method=Hist. Binning, Confidence Type=Verbalized, 5-fold CV=true2026.043.8
Qwen3-VL-8BCalibration Method=Hist. Binning, Confidence Type=Sampling, 5-fold CV=true2026.044.4
InternVL3-8BCalibration Method=Hist. Binning, Confidence Type=Verbalized, 5-fold CV=true2026.044.4
LLaVA-NeXT-34BCalibration Method=Isotonic Regr., Confidence Type=Verbalized, 5-fold CV=true2026.044.4
Qwen3-VL-32BCalibration Method=Isotonic Regr., Confidence Type=Verbalized, 5-fold CV=true2026.044.5
Qwen3-VL-32BCalibration Method=Isotonic Regr., Confidence Type=Sampling, 5-fold CV=true2026.044.6
Qwen3-VL-2BCalibration Method=HAC-Platt, Confidence Type=Verbalized, 5-fold CV=true2026.044.7
Qwen3-VL-8BCalibration Method=HAC-Platt, Confidence Type=Verbalized, 5-fold CV=true2026.044.8
Qwen3-VL-32BCalibration Method=Hist. Binning, Confidence Type=Verbalized, 5-fold CV=true2026.044.8
LLaVA-NeXT-7BCalibration Method=Isotonic Regr., Confidence Type=Verbalized, 5-fold CV=true2026.044.8
Qwen3-VL-8BCalibration Method=HAC-Gate, Confidence Type=Sampling, 5-fold CV=true2026.044.9
LLaVA-NeXT-34BCalibration Method=HAC-Gate, Confidence Type=Verbalized, 5-fold CV=true2026.044.9
Qwen3-VL-32BCalibration Method=HAC-Gate, Confidence Type=Verbalized, 5-fold CV=true2026.045.1
InternVL3-2BCalibration Method=Isotonic Regr., Confidence Type=Verbalized, 5-fold CV=true2026.045.2
Qwen3-VL-32BCalibration Method=HAC-Gate, Confidence Type=Sampling, 5-fold CV=true2026.045.4
Qwen3-VL-8BCalibration Method=Isotonic Regr., Confidence Type=Verbalized, 5-fold CV=true2026.045.5
Qwen3-VL-8BCalibration Method=HAC-Platt, Confidence Type=Sampling, 5-fold CV=true2026.045.5
InternVL3-2BCalibration Method=Platt Scaling, Confidence Type=Verbalized, 5-fold CV=true2026.045.5
Qwen3-VL-8BCalibration Method=Platt Scaling, Confidence Type=Sampling, 5-fold CV=true2026.045.7
Qwen3-VL-32BCalibration Method=HAC-Platt, Confidence Type=Sampling, 5-fold CV=true2026.045.7
Qwen3-VL-32BCalibration Method=HAC-Platt, Confidence Type=Verbalized, 5-fold CV=true2026.045.7
InternVL3-38BCalibration Method=Hist. Binning, Confidence Type=Verbalized, 5-fold CV=true2026.045.7
Qwen3-VL-32BCalibration Method=Hist. Binning, Confidence Type=Sampling, 5-fold CV=true2026.045.8
Qwen3-VL-8BCalibration Method=Platt Scaling, Confidence Type=Verbalized, 5-fold CV=true2026.045.9
Qwen3-VL-32BCalibration Method=Platt Scaling, Confidence Type=Sampling, 5-fold CV=true2026.046
Qwen3-VL-32BCalibration Method=Platt Scaling, Confidence Type=Verbalized, 5-fold CV=true2026.046.1
InternVL3-38BCalibration Method=Isotonic Regr., Confidence Type=Verbalized, 5-fold CV=true2026.046.1
InternVL3-2BCalibration Method=Hist. Binning, Confidence Type=Verbalized, 5-fold CV=true2026.046.2
Qwen3-VL-8BCalibration Method=HAC-Gate, Confidence Type=Verbalized, 5-fold CV=true2026.046.4
Qwen3-VL-8BCalibration Method=Hist. Binning, Confidence Type=Verbalized, 5-fold CV=true2026.046.7
InternVL3-38BCalibration Method=Isotonic Regr., Confidence Type=Sampling, 5-fold CV=true2026.047.1
InternVL3-2BCalibration Method=HAC-Gate, Confidence Type=Verbalized, 5-fold CV=true2026.047.8
LLaVA-NeXT-7BCalibration Method=Hist. Binning, Confidence Type=Verbalized, 5-fold CV=true2026.047.8
InternVL3-38BCalibration Method=Platt Scaling, Confidence Type=Verbalized, 5-fold CV=true2026.048.3
InternVL3-38BCalibration Method=HAC-Platt, Confidence Type=Verbalized, 5-fold CV=true2026.048.3
InternVL3-2BCalibration Method=HAC-Platt, Confidence Type=Verbalized, 5-fold CV=true2026.048.5
Qwen3-VL-2BCalibration Method=Isotonic Regr., Confidence Type=Sampling, 5-fold CV=true2026.048.6
InternVL3-2BCalibration Method=Isotonic Regr., Confidence Type=Sampling, 5-fold CV=true2026.049.9
InternVL3-38BCalibration Method=Hist. Binning, Confidence Type=Sampling, 5-fold CV=true2026.0410.3
LLaVA-NeXT-7BCalibration Method=Platt Scaling, Confidence Type=Sampling, 5-fold CV=true2026.0410.4
LLaVA-NeXT-7BCalibration Method=HAC-Platt, Confidence Type=Sampling, 5-fold CV=true2026.0410.4
LLaVA-NeXT-7BCalibration Method=Isotonic Regr., Confidence Type=Sampling, 5-fold CV=true2026.0410.7
InternVL3-38BCalibration Method=Platt Scaling, Confidence Type=Sampling, 5-fold CV=true2026.0410.8
InternVL3-38BCalibration Method=HAC-Platt, Confidence Type=Sampling, 5-fold CV=true2026.0410.8
Qwen3-VL-2BCalibration Method=HAC-Gate, Confidence Type=Sampling, 5-fold CV=true2026.0411
LLaVA-NeXT-7BCalibration Method=HAC-Gate, Confidence Type=Verbalized, 5-fold CV=true2026.0411.2
Qwen3-VL-2BCalibration Method=Platt Scaling, Confidence Type=Sampling, 5-fold CV=true2026.0411.5
Qwen3-VL-2BCalibration Method=Hist. Binning, Confidence Type=Sampling, 5-fold CV=true2026.0411.7
LLaVA-NeXT-34BCalibration Method=Hist. Binning, Confidence Type=Sampling, 5-fold CV=true2026.0411.7
Qwen3-VL-2BCalibration Method=HAC-Platt, Confidence Type=Sampling, 5-fold CV=true2026.0411.8
LLaVA-NeXT-7BCalibration Method=HAC-Gate, Confidence Type=Sampling, 5-fold CV=true2026.0411.8
InternVL3-38BCalibration Method=HAC-Gate, Confidence Type=Sampling, 5-fold CV=true2026.0411.9
LLaVA-NeXT-7BCalibration Method=Hist. Binning, Confidence Type=Sampling, 5-fold CV=true2026.0412
InternVL3-8BCalibration Method=Hist. Binning, Confidence Type=Sampling, 5-fold CV=true2026.0412.1
LLaVA-NeXT-34BCalibration Method=Platt Scaling, Confidence Type=Sampling, 5-fold CV=true2026.0412.3
LLaVA-NeXT-34BCalibration Method=HAC-Platt, Confidence Type=Sampling, 5-fold CV=true2026.0412.3
InternVL3-38BCalibration Method=Uncalibrated, Confidence Type=Sampling, 5-fold CV=true2026.0412.4
InternVL3-8BCalibration Method=Platt Scaling, Confidence Type=Sampling, 5-fold CV=true2026.0412.8
InternVL3-8BCalibration Method=HAC-Platt, Confidence Type=Sampling, 5-fold CV=true2026.0412.9
LLaVA-NeXT-34BCalibration Method=HAC-Gate, Confidence Type=Sampling, 5-fold CV=true2026.0412.9
LLaVA-NeXT-34BCalibration Method=Isotonic Regr., Confidence Type=Sampling, 5-fold CV=true2026.0413
InternVL3-2BCalibration Method=HAC-Gate, Confidence Type=Sampling, 5-fold CV=true2026.0413.1
InternVL3-8BCalibration Method=Isotonic Regr., Confidence Type=Sampling, 5-fold CV=true2026.0413.3
LLaVA-NeXT-7BCalibration Method=Uncalibrated, Confidence Type=Sampling, 5-fold CV=true2026.0413.3
InternVL3-2BCalibration Method=HAC-Platt, Confidence Type=Sampling, 5-fold CV=true2026.0414.6
InternVL3-2BCalibration Method=Platt Scaling, Confidence Type=Sampling, 5-fold CV=true2026.0414.7
InternVL3-8BCalibration Method=HAC-Gate, Confidence Type=Sampling, 5-fold CV=true2026.0414.9
InternVL3-2BCalibration Method=Hist. Binning, Confidence Type=Sampling, 5-fold CV=true2026.0415.6
Qwen3-VL-32BCalibration Method=Uncalibrated, Confidence Type=Verbalized, 5-fold CV=true2026.0417.4
InternVL3-38BCalibration Method=Uncalibrated, Confidence Type=Verbalized, 5-fold CV=true2026.0418.3
InternVL3-8BCalibration Method=Uncalibrated, Confidence Type=Sampling, 5-fold CV=true2026.0418.8
InternVL3-8BCalibration Method=Uncalibrated, Confidence Type=Verbalized, 5-fold CV=true2026.0420.3
LLaVA-NeXT-34BCalibration Method=Uncalibrated, Confidence Type=Sampling, 5-fold CV=true2026.0421.2
Qwen3-VL-8BCalibration Method=Uncalibrated, Confidence Type=Verbalized, 5-fold CV=true2026.0423
Qwen3-VL-32BCalibration Method=Uncalibrated, Confidence Type=Sampling, 5-fold CV=true2026.0423
InternVL3-2BCalibration Method=Uncalibrated, Confidence Type=Sampling, 5-fold CV=true2026.0423.2
InternVL3-2BCalibration Method=Uncalibrated, Confidence Type=Verbalized, 5-fold CV=true2026.0423.2
Qwen3-VL-2BCalibration Method=Uncalibrated, Confidence Type=Verbalized, 5-fold CV=true2026.0424.5
Qwen3-VL-8BCalibration Method=Uncalibrated, Confidence Type=Sampling, 5-fold CV=true2026.0424.7
LLaVA-NeXT-34BCalibration Method=Uncalibrated, Confidence Type=Verbalized, 5-fold CV=true2026.0427
Qwen3-VL-2BCalibration Method=Uncalibrated, Confidence Type=Sampling, 5-fold CV=true2026.0428.8
LLaVA-NeXT-7BCalibration Method=Uncalibrated, Confidence Type=Verbalized, 5-fold CV=true2026.0435.7