# Aikido Arena v1 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://modelscale.dev/leaderboards/benchmarks/external-aikido-arena-v1

Aikido known-CVE benchmark (July 2026). Every model the catalog carries a published Aikido Arena v1 value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Three runs per model and reasoning level in Aikido's code-analysis harness |
| Tasks | 26 known CVEs from the GitHub advisory database |
| Difficulty | Rediscovering known vulnerabilities with the investigator pointed at the vulnerable code |
| Published by | [Benchmarking 13 AI models on rediscovering known CVEs](https://www.aikido.dev/blog/benchmarking-ai-models-known-cves) |

The first version of Aikido Security's model benchmark: 13 models at two reasoning levels, three runs each on 26 known CVEs from the GitHub advisory database, scored by pass@3 recall.

## Aikido Arena v1 ranking

No model in the catalog has a published Aikido Arena v1 score. The benchmark is defined by Benchmarking 13 AI models on rediscovering known CVEs, 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.
