DS-Arena-Code
text
+
+
+
+
About
DS-Arena-Code is a comprehensive coding benchmark developed by DeepSeek to evaluate Large Language Models' programming capabilities across diverse coding challenges. This benchmark tests AI models' ability to generate, complete, and debug code across multiple programming languages and problem domains. DS-Arena-Code measures practical coding skills including algorithm implementation, code optimization, and real-world programming scenarios.
+
+
+
+
Evaluation Stats
Total Models1
Organizations1
Verified Results0
Self-Reported1
+
+
+
+
Benchmark Details
Max Score1
Language
en
+
+
+
+
Performance Overview
Score distribution and top performers
Score Distribution
1 models
Top Score
63.1%
Average Score
63.1%
High Performers (80%+)
0Top Organizations
#1DeepSeek
1 model
63.1%
+
+
+
+
Leaderboard
1 models ranked by performance on DS-Arena-Code
| License | Links | ||||
|---|---|---|---|---|---|
| May 8, 2024 | deepseek | 63.1% |
