LiveCodeBench
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
LiveCodeBench
87.4Accuracy
102
LiveCodeBench v6
100Accuracy
91
LiveCodeBench
90.7Pass@1
89
LiveCodeBench
95.8Pass@1
86
LiveCodeBench
88.6Accuracy
84
LiveCodeBench
88.1Pass@1
76
LiveCodeBench
55.45pass@1 Accuracy
71
LiveCodeBench
168Average Score
68
LiveCodeBench
7.16Speedup Factor
66
LiveCodeBench
73.2Accuracy
64
LiveCodeBench Python
0.015ECE
60
LiveCodeBench Python
86.7AUROC
60
LiveCodeBench Python
0.067Brier Score
60
LiveCodeBench v6
92Score (%)
51
LiveCodeBench
1,784Pass@1
51
LiveCodeBench Aug 24 – Jan 25
50.9Accuracy
45
LiveCodeBench v6
91.7Score
45
LiveCodeBench V3 V4 (test)
61.4Accuracy
42
LiveCodeBench (test)
53.6Pass@1 Overall
42
LiveCodeBench
70Accuracy
40
LiveCodeBench v5
61.5Pass@1
39
LiveCodeBench (LCB)
91.7Pass@1
37
LiveCodeBench
48Solve Rate
36
LiveCodeBench V5-6
50.8Accuracy
33
LiveCodeBench V1-4
47.1Accuracy
33