LiveCodeBench
text
+
+
+
+
About
LiveCodeBench is a holistic and contamination-free code evaluation benchmark that continuously collects new programming problems from competitive coding platforms. This dynamic benchmark tests AI models' programming capabilities through fresh problems that evolve over time, preventing memorization and ensuring genuine coding skills assessment across algorithm implementation, problem-solving, and code generation tasks.
+
+
+
+
Evaluation Stats
Total Models48
Organizations10
Verified Results0
Self-Reported48
+
+
+
+
Benchmark Details
Max Score1
Language
en
+
+
+
+
Performance Overview
Score distribution and top performers
Score Distribution
48 models
Top Score
80.4%
Average Score
46.5%
High Performers (80%+)
1Top Organizations
#1xAI
4 models
79.6%
#2Zhipu AI
2 models
71.8%
#3NVIDIA
1 model
66.3%
#4Moonshot AI
1 model
53.7%
#5Microsoft
2 models
53.4%
+
+
+
+
Leaderboard
48 models ranked by performance on LiveCodeBench
| License | Links | ||||
|---|---|---|---|---|---|
| Feb 17, 2025 | Proprietary | 80.4% | |||
| Jul 9, 2025 | Proprietary | 79.4% | |||
| Feb 17, 2025 | Proprietary | 79.4% | |||
| Jul 9, 2025 | Proprietary | 79.0% | |||
| Sep 29, 2025 | MIT | 74.1% | |||
| May 28, 2025 | MIT | 73.3% | |||
| Jul 28, 2025 | MIT | 72.9% | |||
| Apr 29, 2025 | Apache 2.0 | 70.7% | |||
| Jul 28, 2025 | MIT | 70.7% | |||
| Jun 5, 2025 | Proprietary | 69.0% |
Showing 1 to 10 of 48 models
...