GDM InterCode CTF: leaderboard
Google DeepMind InterCode-CTF evaluates terminal-based capture-the-flag problem solving with interactive tools.
Metric: Accuracy (%). Source: github.com. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude 3.7 Sonnet (20250219) | 87.34 | #201 |
| 2 | Gemini 2.0 Flash (001) | 81.01 | #360 |
| 3 | GPT-4o (2024-08-06) | 79.75 | #336 |
| 4 | Grok 2 (1212) | 60.76 | #496 |
| 5 | GPT-4o Mini (2024-07-18) | 56.96 | #558 |
| 6 | Llama 3.3 70B Instruct | 49.37 | #534 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=gdm-intercode-ctf · How It Works · Data refreshed daily, snapshot 2026-10-20.