RedCode — leaderboard
Tests risky code execution and harmful code generation capabilities. Evaluates both ability to generate exploits (RedCode-Gen) and willingness to execute dangerous code (RedCode-Exec).
Metric: Score (%). Source: huggingface.co. Status: saturated. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.1 70B Instruct | 75.54 |
| 2 | GPT-4o | 73.67 |
| 3 | Claude 3.5 Sonnet | 65.15 |
| 4 | GPT-4 | 64.14 |
| 5 | Mistral 7B | 61.7 |
| 6 | Llama 3.1 8B Instruct | 61.35 |
| 7 | GPT-3.5 | 54.29 |
| 8 | Llama 3 8B Instruct | 52.38 |
| 9 | Llama 2 7B | 44.38 |
| 10 | Claude 3 Opus | 2.2 |
Interactive version: theaggregate.ai/benchmark?slug=redcode · How the rankings work · Data refreshed daily, snapshot 2026-07-22.