Few-shot task expansion
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
71.58SR
5
Feb 26, 2026
71.88Success Rate
5
Feb 26, 2026
71.28Success Rate (SR)
5
Feb 26, 2026
82.59SR
5
Feb 26, 2026
83.61Success Rate
5
Feb 26, 2026
81.56SR
5
Feb 26, 2026