# CVE Rediscovery 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-cve-rediscovery

Anthropic CVE Rediscovery. Every model the catalog carries a published CVE Rediscovery value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Share of advisories rediscovered |
| Tasks | 1,829 CVE advisories |
| Difficulty | Vulnerability discovery |
| Published by | [Claude Fable 5.2 and Claude Mythos 5.2 system card](https://assets.claude.com/27d60918d218125e7504bc7354c4b4626ec56b11.pdf) |

Anthropic's internal evaluation of whether a model can independently rediscover known vulnerabilities from 1,829 CVE advisories, given only the affected source code.

## CVE Rediscovery ranking

3 models with a published CVE Rediscovery 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 | Share of advisories rediscovered | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Mythos 5.2](https://modelscale.dev/models/claude-mythos-5-2) | Anthropic | 89.6 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Claude Opus 5.5](https://modelscale.dev/models/claude-opus-5-5) | Anthropic | 81.3 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Claude Mythos 5.1](https://modelscale.dev/models/claude-mythos-5-1) | Anthropic | 78.3 | 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.
