Aggregate Benchmarks
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Aggregate Benchmarks
93.9Average Score
37
Aggregate Benchmarks
100Relative Score
22
Aggregate Benchmarks
1.06Harmful Score
21
Aggregate Benchmarks
100Average Score
16
Aggregate Benchmarks
66.9Average Accuracy
13
Aggregate Benchmarks Code Math
56.2Code Component Average
12
Aggregate Benchmarks
100Relative Performance
10
Aggregate Benchmarks Table 6
100Relative Performance (%)
10
Aggregate Benchmarks Average
33.76PSNR
9
Aggregate Benchmarks (DAVIS, MeViS-U, REVOS)
41Overall Score
6