Combined Suite
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Combined Suite General Reasoning Perception Text
76.3Text Average
13
Combined Suite Setup 3
54.38Average Percentage Score
9
Combined Suite (MME, MMStar, SQA, RealWorldQA, MMMU, MMMU-P, VisuLogic, LogicVista, CRPE, POPE, HallBench)
43.94Average Score
4
Combined Suite (HS, PIQA, SIQA, Wino, MMLU, NQ, TQA, ARC-C, ARC-E, OBQA, BoolQ, DROP, BBH-LB, GSM8K)
57.8Accuracy
4
Combined Suite TriviaQA, NQ open, WebQS, HumanEval, MBPP
21.91Average Score
4