List your company

ResearchFormerly WizWand

LiveCodeBench

Benchmarks

TaskDatasetSOTA resultTrendResults

LiveCodeBench

38.9Accuracy (Acc)

5

LiveCodeBench Out-of-Distribution

47.7Initial F1

5

LiveCodeBench In-Distribution

47.4Initial F1 Score

5

Code Generation

LiveCodeBench v6

37.14Accuracy

5

Competitive Code

LiveCodeBench

70.86Score

5

Code Generation

LiveCodeBench (OOD)

19.2Accuracy

5

LiveCodeBench (LCB)

56.7Pass@1

5

LiveCodeBenchPro Easy 25Q2

89.3Pass@1

5

LiveCodeBench 2408-2505 v6

88.4Pass@1

5

Code Understanding and Reasoning

LiveCodeBench v6

42.5Accuracy (avg@1)

5

Code Generation

LiveCodeBench

85Performance

5

Code Generation

LiveCodeBench Hard v5

64.5Pass@1

5

LiveCodeBench v1

35.7Score

5

LiveCodeBench v6

35Accuracy

4

Code Generation

LiveCodeBench v5

62.2Avg@8 Accuracy

4

Code execution output prediction

LiveCodeBench

90.92Accuracy

4

LiveCodeBench

4.36Acceptance Length

4

Code Generation

LiveCodeBench v6

7.8Avg@4

4

LiveCodeBench v6

17.06Average Performance

4

LiveCodeBench v6

48.41Avg@4

4

LiveCodeBench 24.08-25.02

65.9Pass@1

4

LiveCodeBench v6

93Pass@3

4

Code Generation

LiveCodeBench v6

33.71Accuracy

4

LiveCodeBench (LCB) 24.08-25.05

79.74Mean@4

4

LiveCodeBench Pro Medium 25Q2

3.5Score

4