List your company

ResearchFormerly WizWand

LiveCodeBench

Benchmarks

TaskDatasetSOTA resultTrendResults

LiveCodeBench v6

90.7Score

14

Competitive Programming

LiveCodeBench (LCB)

82.6Avg@8

14

LiveCodeBench

15.53LCB Score

14

Code Generation

Ag-LiveCodeBench-X

25Lua Pass@1

14

Code Generation

LiveCodeBench V4 (test)

46.3pass@1

14

Competitive Programming

LiveCodeBench v6 (test)

56.7Score

13

Code Generation

LiveCodeBench V6

11,073Response Length (Tokens)

12

Code Generation

LiveCodeBench v6

55.2Pass@16

12

Code Generation

LiveCodeBench

32.9Avg@16

12

LiveCodeBench

22.11Pass@1

12

Correctness Prediction

LiveCodeBench

79.5WP-AUC

12

Code Generation

LiveCodeBench (out-of-distribution)

66Accuracy

12

Code Generation

LiveCodeBench v1-5

30.6pass@1

12

Downstream Accuracy

LiveCodeBench

33.2Accuracy

12

Code Generation

LiveCodeBench

27.78Avg@8

12

Code Generation

LiveCodeBench (LCB)

5.51Speedup

12

Code Generation

LiveCodeBench CPP

28.85Accuracy

11

LiveCodeBench

176.93Total Pass Rate

11

Coding Reasoning

LiveCodeBench V6

58.1Pass@1 (avg@8)

11

LiveCodeBench

88.3Pass@1 Accuracy

11

Code Generation

LiveCodeBench Easy

100Pass@1

11

Competitive Programming

LiveCodeBench

55.19Pass@1

11

Code Generation

LiveCodeBench

94.3AUCOAA

11

Code Generation

LiveCodeBench v6

47.14Avg@4

10

Output Prediction

LiveCodeBench (LCB) output-prediction

51Code Execution Success Rate

10