all the models — AI benchmark observatory
← Benchmarks

Capture-the-Flag Challenges (Internal)

Capture-the-Flag Challenges is OpenAI's internal expansion of competitive, professional-level cybersecurity capture-the-flag tasks used to evaluate vulnerability identification and exploitation capability under the Preparedness Framework.

id capture-the-flag-challenges · max 1 · 3 models reported

#ModelScore
1GPT-5.6 Sol
OpenAI
0.97
2GPT-5.6 Terra
OpenAI
0.92
3GPT-5.6 Luna
OpenAI
0.85
Capture-the-Flag Challenges (Internal) Leaderboard · all the models