List your company

Selective Prediction on A-OKVQA 60 (test)

0.972AUROCRidge LTSA Chart
0.449920.585460.7210.85654Jun 8, 2026

Evaluation results

MethodLinks
Ridge LTSA ChartModel=Idefics3-8B-Llama3, Variant=PR-dim/Ridge Proximity, Baseline=true2026.060.9720.1320.8640.108
Ridge LTSA ChartModel=SmolVLM-Instruct, Variant=PR-dim/Ridge Proximity2026.060.9510.2450.750.182
logP(x)Model=Idefics3-8B-Llama3, Variant=Sequence logP(x)2026.060.7950.2440.7520.152
logP(x)Model=SmolVLM-Instruct, Variant=Sequence logP(x)2026.060.7910.3440.6510.221
Topology LID-MLEModel=Idefics3-8B-Llama3, Variant=Neg LID-MLE2026.060.7250.2520.7440.169
Topology LID-MLEModel=SmolVLM-Instruct, Variant=Neg LID-MLE2026.060.470.5930.4020.299