Standard benchmarks
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
standard benchmarks
77.94ASR (%)
18
Standard Benchmarks CIRR, FashionIQ, GeneCIS
38.3Average Performance
10
Standard Benchmarks (ARC-E, ARC-C, BoolQ, HellaSwag, OBQA, PIQA, WinoGrande, MMLU, SciQ) (test)
49.75ARC-E Acc (Norm)
8
Standard text-to-image benchmarks
97.28CLIP Score
6
39 standard benchmarks AIME GSM8K ARC MMLU MMLU-PRO GPQA SuperGPQA
0.741Pearson r
4