ResearchTasksMultimodal Understanding and Question AnsweringMultimodal Understanding and Question AnsweringFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMultimodal Benchmarks MME, OCRBench, DocVQA, RealWorldQA, VLMBlindBATQuant2,386MME Score33Mar 18, 2026LLaVA-NeXT Evaluation Suite (GQA, SQA-IMG, VQA-Text, POPE, MME, MMB-EN, MMB-CN, MMVet) 13B (test)Baseline64.4GQA Score28Jun 26, 2026LLaVA 7B Evaluation Suite (GQA, MMBench, MMBench-CN, MME, POPE, ScienceQA, VQAv2, TextVQA, SEED-Bench, VizWiz) 1.5Vanilla61.9GQA Accuracy22May 28, 2026
Multimodal Benchmarks MME, OCRBench, DocVQA, RealWorldQA, VLMBlindBATQuant2,386MME Score33Mar 18, 2026
LLaVA-NeXT Evaluation Suite (GQA, SQA-IMG, VQA-Text, POPE, MME, MMB-EN, MMB-CN, MMVet) 13B (test)Baseline64.4GQA Score28Jun 26, 2026
LLaVA 7B Evaluation Suite (GQA, MMBench, MMBench-CN, MME, POPE, ScienceQA, VQAv2, TextVQA, SEED-Bench, VizWiz) 1.5Vanilla61.9GQA Accuracy22May 28, 2026