SecCodeBench
Progress Over Time
Interactive timeline showing model performance evolution on SecCodeBench
State-of-the-art frontier
Open
Proprietary
SecCodeBench Leaderboard
1 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Alibaba Cloud / Qwen Team | 397B | — | — |
Notice missing or incorrect data?
What is SecCodeBench?
SecCodeBench evaluates LLM coding agents on secure code generation and vulnerability detection, testing the ability to produce code that is both functional and free from security vulnerabilities.
SecCodeBench is a text benchmark evaluating models on coding tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–1 scale. The current average is 0.7, with the leader at 0.7.
Compare leaders on the best AI for coding leaderboards.
Current leaders
Qwen3.5-397B-A17B from Alibaba Cloud / Qwen Team currently leads the SecCodeBench leaderboard with a score of 0.683 across 1 evaluated AI models.
FAQ
Common questions about the SecCodeBench benchmark and leaderboard.