Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

LiveCodeBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Code GenerationLiveCodeBench
Pass@190.7
89
Code GenerationLiveCodeBench
Pass@195.8
86
Code GenerationLiveCodeBench
Average Score168
68
Code ReasoningLiveCodeBench
Accuracy87.4
46
Code GenerationLiveCodeBench (test)
Pass@1 Overall53.6
38
Code GenerationLiveCodeBench
Pass@11,784
37
Code GenerationLiveCodeBench
Accuracy57.29
32
Code VerificationLiveCodeBench
Pass@139.31
32
ReasoningLiveCodeBench
LiveCodeBench Score54.25
27
Code GenerationLiveCodeBench v3
Score90.2
26
Code GenerationLiveCodeBench
Speedup3.52
24
Code generationLiveCodeBench Jan-Apr 2025
Accuracy (pass@1)47.25
24
Code GenerationLiveCodeBench Medium
Accuracy96.79
23
CodingLiveCodeBench
Task Accuracy79
23
Code GenerationLiveCodeBench v6
Accuracy83.93
23
Competitive ProgrammingLiveCodeBench v5
Score82.8
22
Code GenerationLiveCodeBench Hard
Pass@163.9
21
LLM InferenceLiveCodeBench
Speedup2.81
21
Competitive ProgrammingLiveCodeBench 2408 - 2505 v6
Score80.2
19
Code ReasoningLiveCodeBench 1.0 (test)
Accuracy47.2
18
Code GenerationLiveCodeBench pass@1 v5
pass@130.7
18
Code GenerationLiveCodeBench lite v6 (test)
Accuracy56.57
18
Code GenerationLiveCodeBench lite v5 (test)
Accuracy64.07
18
CodingLiveCodeBench v5
Accuracy75.9
18
Code GenerationLiveCodeBench (LCB)
% Avg@432.4
17
Showing 25 of 82 rows