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

Combined MLLM Evaluation Suite

Benchmarks

Task NameDataset NameSOTA ResultTrend
Overall Multi-benchmark PerformanceCombined MLLM Evaluation Suite AI2D, ChartQA, POPE, MME, MMBench
Average Performance100
13
Showing 1 of 1 rows