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.
Agentic benchmark
Anthropic Binary Exploitation Benchmark (formerly OSS-Fuzz), control-flow hijacks. Every model the catalog carries a published Binary Exploitation Benchmark value for, ranked by that value.
Anthropic's unguided vulnerability-discovery and exploitation evaluation: from a single function entry point in an open-source project, the model must find a bug and push it toward a working exploit. This lane counts control-flow hijacks. 4 models in the ModelScale catalog have a published value.
Each point is a model with a published Binary Exploitation Benchmark value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
4 models with a published Binary Exploitation Benchmark 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 | Count of control-flow hijacks |
|---|---|---|---|
| 1 | Anthropic | 148 | |
| 2 | Anthropic | 112 | |
| 3 | Anthropic |
What the benchmark measures and how its value is published, from the source’s own record.
Binary Exploitation Benchmark (Anthropic Binary Exploitation Benchmark (formerly OSS-Fuzz), control-flow hijacks) is an agentic benchmark published by Claude Fable 5.2 and Claude Mythos 5.2 system card. Anthropic's unguided vulnerability-discovery and exploitation evaluation: from a single function entry point in an open-source project, the model must find a bug and push it toward a working exploit. This lane counts control-flow hijacks. Its evaluation set is described by the source as open-source function entry points. The source rates its difficulty as exploit development.
Each model's result is published by Claude Fable 5.2 and Claude Mythos 5.2 system card as count of control-flow hijacks. ModelScale prints that value to 0 decimal places, exactly as published, and never converts or rescales it. This page ranks the 4 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.
| 4 | Anthropic | 48 |
Evidence key: Observed
Rows are ordered by the value Claude Fable 5.2 and Claude Mythos 5.2 system card published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.