# CWE-bench v1 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-v1

Every model the catalog carries a published CWE-bench v1 value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Pass@1 |
| Tasks | Audit and patch held-out C/C++, Go, Java, TypeScript/JavaScript, Python, and Rust repositories |
| Difficulty | Frontier agent evaluation |
| Published by | [CWE-bench v1 leaderboard and methodology](https://cwe-bench.com/) |

Defensive vulnerability patching on 120 held-out tasks spanning 73 weakness types.

## CWE-bench v1 ranking

11 models with a published CWE-bench v1 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 | [Gemini 4 Argon](https://modelscale.dev/models/gemini-4-argon) | Google | 68.0 | Observed 2026-10-23 · source benchlm:models |
| 1 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 68.0 | Observed 2026-10-23 · source benchlm:models |
| 1 | [Grok 4.7](https://modelscale.dev/models/grok-4-7) | xAI | 68.0 | Observed 2026-10-23 · source benchlm:models |
| 4 | [Claude Opus 5.5](https://modelscale.dev/models/claude-opus-5-5) | Anthropic | 67.0 | Observed 2026-10-23 · source benchlm:models |
| 5 | [Claude Fable 5.1](https://modelscale.dev/models/claude-fable-5-1) | Anthropic | 58.0 | Observed 2026-10-23 · source benchlm:models |
| 6 | [Grok 4.6](https://modelscale.dev/models/grok-4-6) | xAI | 57.0 | Observed 2026-10-23 · source benchlm:models |
| 7 | [DeepSeek V4.1 Flash 1017](https://modelscale.dev/models/deepseek-v4-1-flash) | DeepSeek | 55.0 | Observed 2026-10-23 · source benchlm:models |
| 7 | [Muse Spark 1.3](https://modelscale.dev/models/muse-spark-1-3) | Meta | 55.0 | Observed 2026-10-23 · source benchlm:models |
| 9 | [Hy4 preview](https://modelscale.dev/models/hy4-preview) | Tencent | 53.0 | Observed 2026-10-23 · source benchlm:models |
| 10 | [GPT-6 Sol](https://modelscale.dev/models/gpt-6-sol) | OpenAI | 52.0 | Observed 2026-10-23 · source benchlm:models |
| 11 | [Inkling](https://modelscale.dev/models/inkling) | Thinking Machines Lab | 37.0 | Observed 2026-10-23 · 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.