Coding Agent Capacity
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
74Score
13
Jul 2, 2026
82.3Score
8
Jul 2, 2026
63Score
8
Jul 2, 2026
71.1Score
8
Jul 2, 2026
94.2Score
8
Jul 2, 2026
27.1Score
8
Jul 2, 2026
57.7Score
8
Jul 2, 2026
55.6Score
8
Jul 2, 2026
56.1Score
8
Jul 2, 2026