# CWE-bench 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-cwe-bench-v2

CWE-bench v2. Every model the catalog carries a published CWE-bench value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Pass@1 |
| Tasks | Audit and patch C/C++, Go, Java, TypeScript/JavaScript, Python, and Rust repositories; 100 public and 150 held-out tasks |
| Difficulty | Frontier agent evaluation |
| Published by | [CWE-bench v2 leaderboard and methodology](https://cwe-bench.com/) |

Defensive vulnerability patching on 250 audit-and-patch tasks spanning 185 weakness types, 100 public and 150 held out.

## CWE-bench ranking

14 models with a published CWE-bench 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 | [Claude Fable 5.2](https://modelscale.dev/models/claude-fable-5-2) | Anthropic | 75.0 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Gemini 4 Hydrogen](https://modelscale.dev/models/gemini-4-hydrogen) | Google | 68.1 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Claude Opus 5.5](https://modelscale.dev/models/claude-opus-5-5) | Anthropic | 67.1 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Muse Wonder](https://modelscale.dev/models/muse-wonder) | Meta | 66.1 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Gemini 4 Argon](https://modelscale.dev/models/gemini-4-argon) | Google | 65.0 | Observed 2026-11-21 · source benchlm:models |
| 6 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 64.2 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Hy4](https://modelscale.dev/models/hy4) | Tencent | 64.1 | Observed 2026-11-21 · source benchlm:models |
| 8 | [DeepSeek V4.1 Flash 1017](https://modelscale.dev/models/deepseek-v4-1-flash) | DeepSeek | 57.6 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Grok 4.7](https://modelscale.dev/models/grok-4-7) | xAI | 54.7 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Hy4 preview](https://modelscale.dev/models/hy4-preview) | Tencent | 47.3 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Mistral Large 4](https://modelscale.dev/models/mistral-large-4) | Mistral | 45.6 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Qwen3.8 Max](https://modelscale.dev/models/qwen3-8-max) | Alibaba | 45.4 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Kimi K3.1 Pro](https://modelscale.dev/models/kimi-3-1-pro) | Moonshot AI | 45.3 | Observed 2026-11-21 · source benchlm:models |
| 14 | [GLM-5.3](https://modelscale.dev/models/glm-5-3) | Z.AI | 42.0 | 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.
