Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MLLM-CTBENCH

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multimodal Continual Instruction TuningMLLM-CTBench
Math QA Accuracy49.52
12
Multimodal Continual LearningMLLM-CTBENCH
Accuracy (Math QA)55.17
12
Showing 2 of 2 rows