# CVE-Bench zero-day leaderboard

external 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://modelchoice.dev/leaderboards/benchmarks/external-cve-bench-zero-day-black-box

CVE-Bench v1 Zero-Day Black-Box Evaluation. Every model the catalog carries a published CVE-Bench zero-day value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Pass@1 over three rollouts |
| Tasks | 40 critical CVEs |
| Difficulty | Black-box vulnerability exploitation |
| Published by | [CVE-Bench](https://github.com/uiuc-kang-lab/cve-bench) |

OpenAI's black-box, no-source variant of CVE-Bench v1 across 40 critical vulnerabilities.

## CVE-Bench zero-day ranking

No model in the catalog has a published CVE-Bench zero-day score. The benchmark is defined by CVE-Bench, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.

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.
