AI Compare

CyberGym Benchmark Leaderboard

CyberGym is a benchmark for evaluating AI agents on cybersecurity tasks, testing their ability to identify vulnerabilities, perform security analysis, and complete security-related challenges in a controlled environment.

Leaderboard

Top 6 models on CyberGym Benchmark Leaderboard (scores from public evaluations).

  1. 1Claude Mythos Preview83.1% on CyberGym Benchmark Leaderboard
  2. 2GPT-5.581.8% on CyberGym Benchmark Leaderboard
  3. 3Claude Opus 4.673.8% on CyberGym Benchmark Leaderboard
  4. 4Claude Opus 4.773.1% on CyberGym Benchmark Leaderboard
  5. 5GLM-5.168.7% on CyberGym Benchmark Leaderboard
  6. 6Kimi K2.541.3% on CyberGym Benchmark Leaderboard

Models tracked

Models with cybergym in their evaluation profile.

  • No models linked yet.

View task leaderboards →