# CyScenarioBench Average Success Rate (CyScenarioBench success)

> Average success rate across realistic, long-horizon cybersecurity scenarios.

Canonical page: https://benchlm.ai/benchmarks/cyscenariobenchaveragesuccess

- Category: [Agentic](/agentic)
- Last updated: September 27, 2026

## About CyScenarioBench success

- Year: 2026
- Tasks: 11 cyber scenarios
- Format: Average success rate
- Difficulty: Long-horizon cybersecurity
- Paper: [Assessing GPT-5.6 Sol](https://www.irregular.com/research/assessing-gpt-5.6-sol)

Irregular evaluates models repeatedly across CyScenarioBench challenges and averages success equally across scenarios. BenchLM keeps this independent result display only.

CyScenarioBench success is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (2 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [GPT-6 Astra](/models/gpt-6-astra) | OpenAI | 59% |
| 2 | [GPT-5.6 Sol](/models/gpt-5-6-sol) | OpenAI | 28% |

## FAQ

### What does CyScenarioBench success measure?

Average success rate across realistic, long-horizon cybersecurity scenarios.

### Which model scores highest on CyScenarioBench success?

GPT-6 Astra by OpenAI currently leads with a score of 59% on CyScenarioBench success.

### How many models are evaluated on CyScenarioBench success?

2 AI models have been evaluated on CyScenarioBench success on BenchLM.

### Does CyScenarioBench success affect BenchLM's overall score?

Not directly. CyScenarioBench success is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on CyScenarioBench success

- [GPT-6 Astra vs GPT-5.6 Sol](/compare/gpt-5-6-sol-vs-gpt-6-astra)