XLRS-Bench
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
XLRS-Bench L-3 Capability (test)
61.7OC
33
XLRS-Bench
52.78Accuracy
20
XLRS-Bench
53.1Average Score (Avg.)
19
XLRS-Bench
60.4PASS@1
18
XLRS-Bench
0.542Average Score
17
XLRS-Bench vqa
21.6F1 Score
10
XLRS-Bench caption
40.4GEval Score
10
XLRS-Bench Lite
51.12Score
9
XLRS-Bench macro
54.6Pass@1
7
XLRS-Bench
52.8Score
5