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
CyScenarioBench Average Success Rate. Every model the catalog carries a published CyScenarioBench success value for, ranked by that value.
Average success rate across realistic, long-horizon cybersecurity scenarios. 6 models in the ModelScale catalog have a published value.
Each point is a model with a published CyScenarioBench success value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
6 models with a published CyScenarioBench success 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 | Average success rate |
|---|---|---|---|
| 1 | Anthropic | 76 | |
| 2 | Anthropic | 68 | |
| 3 | OpenAI | 63 |
What the benchmark measures and how its value is published, from the source’s own record.
CyScenarioBench success (CyScenarioBench Average Success Rate) is an external benchmark published by Assessing GPT-5.6 Sol. Average success rate across realistic, long-horizon cybersecurity scenarios. Its evaluation set is described by the source as 11 cyber scenarios. The source rates its difficulty as long-horizon cybersecurity.
Each model's result is published by Assessing GPT-5.6 Sol as average success rate. ModelScale prints that value to 0 decimal places, exactly as published, and never converts or rescales it. This page ranks the 6 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 | 62 |
| 5 | OpenAI | 59 |
| 6 | OpenAI | 28 |
Evidence key: Observed
Rows are ordered by the value Assessing GPT-5.6 Sol 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.