ResearchBenchmarksMultimodal Reasoning on OOD TextFollow64Average NMV2.837618.716334.59550.4737Jul 2, 2026Evaluation ResultsMethodMethodLinksAverage NSaved TimesAccuracyMVModel=Qwen2.5VL-2.5-7B...Model=Qwen2.5VL-2.5-7B-Instruct, Stopping criteria=N=642026.0764178.1ACModel=Qwen2.5VL-2.5-7B...Model=Qwen2.5VL-2.5-7B-Instruct, Stopping criteria=Adaptive2026.0712.874.9778.1CASModel=Qwen2.5VL-2.5-7B...Model=Qwen2.5VL-2.5-7B-Instruct, Stopping criteria=Confidence-based Adaptive2026.075.1912.3378.2