New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
CyberGym benchmark
AI model leaderboard for the CyberGym benchmark. Compare how large language models score on CyberGym, see the full ranking, and understand what this AI benchmark measures. GPT-5.5-Cyber currently leads with 85.6%. Benchmark for AI agents on real-world cybersecurity tasks.
Leaderboard
| # | Model | Organization | Score | Variant | Source |
|---|---|---|---|---|---|
| #1 | GPT-5.5-Cyber | OpenAI | 85.6% | official ↗ |
Frequently asked questions about CyberGym
What is the CyberGym benchmark?
Benchmark for AI agents on real-world cybersecurity tasks.
How is the CyberGym benchmark scored?
CyberGym is scored using the success rate (%) metric, where a higher score is better. The maximum achievable score is 100.000. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.
Which AI model scores highest on CyberGym?
As of the latest reported scores on GenAIList, GPT-5.5-Cyber achieves the highest result on CyberGym with a score of 85.6%.
Is a higher CyberGym score better?
Yes. On CyberGym a higher score indicates better performance, so models near the top of the leaderboard are the strongest.