Code Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
3,511Response Length (Tokens)
12
Jun 17, 2026
57.2Accuracy
12
Jun 16, 2026
54.9Accuracy
12
Jun 16, 2026
31.1Accuracy
12
Jun 11, 2026
100Accuracy (%)
12
Jun 11, 2026
55.2Pass@16
12
Jun 9, 2026
32.9Avg@16
12
Jun 9, 2026
56.7Accuracy
12
Jun 9, 2026
60Accuracy (%)
12
Jun 9, 2026
77.44Accuracy
12
Jun 8, 2026
80.7Pass@1
12
Jun 8, 2026
82.3Pass@1
12
Jun 8, 2026
93.1Pass@10
12
Jun 4, 2026
52.67Performance Score
12
Jun 2, 2026
4.78Speedup
12
Jun 2, 2026
5.86Speedup
12
Jun 2, 2026
3.7Speedup
12
Jun 2, 2026
3.57Speedup
12
Jun 2, 2026
1.7Latency (s)
12
May 29, 2026
2Latency (s)
12
May 29, 2026
20.3Pass@1
12
May 28, 2026
93.2Pass@1
12
May 28, 2026
48.4Precision@1
12
May 28, 2026
83.2Pass@4
12
May 27, 2026
71.9Performance (%)
12
May 27, 2026