# CWE-Bench-AA leaderboard

Agentic benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/agentic-aa-cwe-bench

Artificial Analysis CWE-Bench-AA. Every model the catalog carries a published CWE-Bench-AA value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Pass@1 |
| Tasks | Real-world vulnerability patching tasks |
| Difficulty | Automated vulnerability remediation |
| Published by | [CWE-Bench-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/cwe-bench-aa) |

Artificial Analysis' implementation of Collinear AI's CWE-bench, testing whether agents can patch real-world software vulnerabilities. One of the three components of the AA Cyber Index.

## CWE-Bench-AA ranking

21 models with a published CWE-Bench-AA value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Pass@1 | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [DeepSeek V4.1 Flash 1017](https://modelscale.dev/models/deepseek-v4-1-flash) | DeepSeek | 68.3 | Observed 2026-11-21 · source benchlm:models |
| 1 | [Grok 4.7](https://modelscale.dev/models/grok-4-7) | xAI | 68.3 | Observed 2026-11-21 · source benchlm:models |
| 3 | [GPT-6.2 Astra](https://modelscale.dev/models/gpt-6-2-astra) | OpenAI | 65.0 | Observed 2026-11-21 · source benchlm:models |
| 4 | [GPT-6 Sol](https://modelscale.dev/models/gpt-6-sol) | OpenAI | 64.2 | Observed 2026-11-21 · source benchlm:models |
| 5 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 63.3 | Observed 2026-11-21 · source benchlm:models |
| 5 | [MiMo-V2.6-Pro](https://modelscale.dev/models/mimo-v2-6-pro) | Xiaomi | 63.3 | Observed 2026-11-21 · source benchlm:models |
| 7 | [GPT-6.2 Sol](https://modelscale.dev/models/gpt-6-2-sol) | OpenAI | 61.7 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Kimi K3.1 Pro](https://modelscale.dev/models/kimi-3-1-pro) | Moonshot AI | 60.8 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Claude Opus 5.5](https://modelscale.dev/models/claude-opus-5-5) | Anthropic | 58.3 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Mistral Large 4](https://modelscale.dev/models/mistral-large-4) | Mistral | 58.3 | Observed 2026-11-21 · source benchlm:models |
| 11 | [GPT-6 Luna](https://modelscale.dev/models/gpt-6-luna) | OpenAI | 56.7 | Observed 2026-11-21 · source benchlm:models |
| 12 | [GLM-5.3](https://modelscale.dev/models/glm-5-3) | Z.AI | 55.8 | Observed 2026-11-21 · source benchlm:models |
| 12 | [GLM-5.3-Flash](https://modelscale.dev/models/glm-5-3-flash) | Z.AI | 55.8 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Kimi K3](https://modelscale.dev/models/kimi-3) | Moonshot AI | 53.3 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Gemini 3.8 Flash](https://modelscale.dev/models/gemini-3-8-flash) | Google | 52.5 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Step 5 Preview](https://modelscale.dev/models/step-5-preview) | StepFun | 52.5 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Claude Fable 5.1](https://modelscale.dev/models/claude-fable-5-1) | Anthropic | 50.8 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Beam 1.0 501B-A23B](https://modelscale.dev/models/reflection-beam) | Reflection AI | 49.2 | Observed 2026-11-21 · source benchlm:models |
| 19 | [MiniMax M3](https://modelscale.dev/models/minimax-m3) | MiniMax | 41.7 | Observed 2026-11-21 · source benchlm:models |
| 20 | [Nemotron 3 Ultra](https://modelscale.dev/models/nemotron-3-ultra-500b) | NVIDIA | 27.5 | Observed 2026-11-21 · source benchlm:models |
| 21 | [Qwen3.8-27B](https://modelscale.dev/models/qwen3-8-27b) | Alibaba | 26.7 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
