Code Synthesis
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
64.59Accuracy
12
Mar 9, 2026
81.7pass@1
11
May 12, 2026
7OCaml Pass@1
8
Mar 4, 2026
81.2Pass@1
6
Apr 21, 2026
68Success Rate (Lua)
5
Mar 4, 2026
75.7Baseline Score
1
May 12, 2026