# AI Coding Agent Security Benchmark

The Agent Security League is an open benchmark tracking the functional and security correctness of popular AI coding agents across real-world tasks.

[Download paper](/content/learn/agent-security-league-evaluating-the-security-of-ai-coded-software/index.html)

87.2%
highest functional correctness score (Claude Code with Claude Fable 5.1)

32
agent + model combos independently benchmarked

37.4%
highest security correctness score (Claude Code with Claude Fable 5.1)

## Agent Security League

Updated as new commercial agents and models ship. Sorted by security correctness.

### Harness:

AllClaude CodeCodexCursorSWE-Agent

### Model:

All ModelsClaude Fable 5.1GPT-6 AstraGPT-6.1 SolClaude Opus 5.5Claude Opus 5Claude Fable 5GPT-6 SolGPT-5.5GPT 5.6 SolGPT-5.4Claude Opus 4.8Claude Sonnet 5Claude Opus 4.7Gemini 3.5 FlashGemini 3.1 ProGPT-5.3Composer 2.5Claude Sonnet 4.6GLM 5.2Claude Opus 4.6Gemini 3 ProClaude Opus 4.5Claude Sonnet 4Gemini 2.5 Pro

| Harness | Model                | Functional (%)\* | Secure (%)† | Date       |
|---------|---------------------|-------------------|---------------|------------|
| 01      | Claude Code         | 87.2              | 37.4          | 2026-09-04 |
| 02      | Codex               | GPT-6 Astra       | 82.1          | 34.6       | 2026-09-09 |
| 03      | Codex               | GPT-6.1 Sol      | 77.7          | 34.1       | 2026-10-01 |
| 04      | Claude Code         | Claude Opus 5.5  | 68.7          | 33.5       | 2026-09-24 |
| 05      | Claude Code         | Claude Opus 5    | 73.7          | 32.4       | 2026-07-31 |
| 06      | Cursor              | Claude Fable 5   | 72.6          | 29.0       | 2026-06-12 |
| 07      | Codex               | GPT-6 Sol        | 72.1          | 25.1       | 2026-09-29 |
| 08      | Cursor              | GPT-5.5          | 84.9          | 24.0       | 2026-04-25 |
| 09      | Codex               | GPT 5.6 Sol      | 70.9          | 23.5       | 2026-07-17 |
| 10      | Codex               | GPT-5.5          | 62.6          | 22.4       | 2026-04-25 |
| 11      | Codex               | GPT-5.4          | 63.1          | 21.8       | 2026-03-18 |
| 12      | Cursor              | Claude Opus 4.8  | 75.4          | 20.7       | 2026-05-30 |
| 13      | Claude Code         | Claude Sonnet 5   | 83.2          | 19.6       | 2026-07-02 |
| 14      | Claude Code         | Claude Fable 5    | 59.8          | 19.0       | 2026-06-10 |
| 15      | Cursor              | Claude Opus 4.7  | 79.9          | 18.4       | 2026-04-17 |
| 16      | Cursor              | Gemini 3.5 Flash | 79.3          | 17.9       | 2026-05-20 |
| 17      | Claude Code         | Claude Opus 4.7  | 76.5          | 16.8       | 2026-04-16 |
| 18      | Cursor              | Gemini 3.1 Pro   | 73.2          | 15.1       | 2026-03-24 |
| 19      | Claude Code         | Claude Opus 4.8  | 73.7          | 14.5       | 2026-05-29 |
| 20      | Cursor              | GPT-5.3          | 48.0          | 14.5       | 2026-02-27 |
| 21      | Cursor              | Composer 2.5     | 75.4          | 14.0       | 2026-05-19 |
| 22      | Claude Code         | Claude Sonnet 4.6 | 69.8          | 12.3       | 2026-02-20 |
| 23      | Cursor              | GLM 5.2          | 82.5          | 12.0       | 2026-07-09 |
| 24      | Cursor              | Claude Opus 4.6  | 84.9          | 11.2       | 2026-03-19 |
| 25      | Claude Code         | Claude Opus 4.6  | 78.2          | 10.6       | 2026-03-16 |
| 26      | Claude Code         | Gemini 3 Pro     | 44.1          | 9.5        | 2026-02-23 |
| 27      | Claude Code         | Claude Opus 4.5  | 68.7          | 8.4        | 2026-02-25 |
| 28      | Cursor              | Gemini 3 Pro     | 27.9          | 5.6        | 2026-02-24 |
| 29      | Claude Code         | Claude Sonnet 4  | 45.3          | 6.1        | 2026-02-11 |
| 30      | Claude Code         | Gemini 2.5 Pro   | 19.6          | 5.0        | 2026-02-11 |
| 31      | SWE-Agent           | Claude Sonnet 4  | 55.3          | 7.8        | 2026-02-19 |
| 32      | SWE-Agent           | Gemini 2.5 Pro   | 20.7          | 4.5        | 2026-02-19 |

\*Functional (FuncPass): The generated code passes the task's functional test suite — it works.

†Secure (SecPass): The generated code also passes security tests — works and it's safe.

## Methodology

### Peer-reviewed research

The Agent Security League extends [SusVibes](https://arxiv.org/pdf/2512.03262), a foundational benchmark developed at Carnegie Mellon University.

### Real-world tasks

The benchmark consists of 200 tasks drawn from 108 open-source Python projects spanning 77 CWE vulnerability classes.

### Anti-cheating safeguards

Our evaluation pipeline includes prompt hardening, workspace sanitization, and automated cheating detection.

## Resources

.webp)\
\
Research\
\
How AI coding agents cheat benchmarks\
\
Read More](/content/learn/recall-not-reasoning-how-ai-coding-agents-cheat-security-benchmarks/index.html)

.webp)\
\
Whitepaper\
\
Evaluating the Security of AI Coding Agents\
\
Read More](/content/learn/agent-security-league-evaluating-the-security-of-ai-coded-software/index.html)

\
\
Blog Post\
\
Introducing the Agent Code Security Leaderboard\
\
Read More](/content/learn/is-ai-coding-safe-introducing-the-agent-security-league/index.html)

## Security in every line, so you can code without compromise.

AI coding agents can write code, but they lack security context. AURI is the security harness your coding agent is missing.

Always free for developers.

[Start Now](/content/platform/developer/index.html) [Book a Demo](/content/demo-request/index.html)