Coding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
98.4Accuracy
175
Jun 18, 2026
98.17Pass@1
168
May 27, 2026
95.12Pass@1
164
Jun 9, 2026
97.88Pass@1
117
May 28, 2026
95.62Accuracy
84
Jun 15, 2026
95.33Pass@1 Accuracy
78
May 7, 2026
92Score (%)
51
Jun 23, 2026
87.1Eval+ Score
47
Jun 16, 2026
37.9Accuracy
45
Jun 18, 2026
50.9Accuracy
45
Jun 18, 2026
98.3Pass@1
42
Feb 26, 2026
74.4Test Accuracy
40
Jun 9, 2026
70Accuracy
40
Jun 9, 2026
81Overall Average Score
37
Jun 2, 2026
50.2HumanEval Score
35
Jun 1, 2026
77.6Accuracy
33
Jun 26, 2026
36.8Score
32
Jun 16, 2026
87.1Score
32
Jun 16, 2026
0.97HumanEval Mean Score
32
Mar 18, 2026
41.2LiveCode Score
31
Jun 16, 2026
87.9Score
31
May 26, 2026
63.92Original Accuracy
30
Jun 19, 2026
42Accuracy
30
Jun 18, 2026
74.2Acc (avg@32)
29
May 11, 2026
79.9HumanEval
28
May 22, 2026