Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
external benchmark
Every model the catalog carries a published Aikido Arena value for, ranked by that value.
Aikido Security's live benchmark of how well AI models rediscover real vulnerabilities. Each model runs three times on 32 recently disclosed CVEs in open-source repositories, and the score is the share it finds in at least one run (pass@3 recall). 0 models in the ModelScale catalog have a published value.
The benchmark is defined by Aikido Arena: AI model benchmarks for cybersecurity, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.
What the benchmark measures and how its value is published, from the source’s own record.
Aikido Arena is an external benchmark published by Aikido Arena: AI model benchmarks for cybersecurity. Aikido Security's live benchmark of how well AI models rediscover real vulnerabilities. Each model runs three times on 32 recently disclosed CVEs in open-source repositories, and the score is the share it finds in at least one run (pass@3 recall). Its evaluation set is described by the source as 32 recently disclosed CVEs in real open-source repositories. The source rates its difficulty as rediscovering real vulnerabilities from source, including missing checks and long call chains.
Each model's result is published by Aikido Arena: AI model benchmarks for cybersecurity as three runs per model in Aikido's code-analysis harness (30 turns, no internet). ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 0 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.