Multimodal Agent Performance
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
75.3Accuracy
5
Jun 4, 2026
55.1Accuracy
5
Jun 4, 2026
78.2Accuracy
5
Jun 4, 2026
81.9Accuracy
5
Jun 4, 2026
83.7Accuracy
5
Jun 4, 2026
80.6Accuracy
5
Jun 4, 2026