CyberSecEval2 Vulnerability Exploit — leaderboard
Metric: Accuracy (%). Source: github.com. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.7 Sonnet (20250219) | 56.82 |
| 2 | GPT-4o (2024-08-06) | 53.28 |
| 3 | Gemini 2.0 Flash (001) | 50.38 |
| 4 | Grok 2 (1212) | 50.16 |
| 5 | Llama 3.3 70B Instruct | 48.93 |
| 6 | DeepSeek V3 Chat | 46.13 |
| 7 | Llama 3.2 90B Vision Instruct | 40.45 |
| 8 | mistral-large-latest | 38.11 |
| 9 | O4 Mini (2025-04-16) | 37.3 |
| 10 | mistral-small-latest | 35.91 |
| 11 | GPT-4o Mini (2024-07-18) | 34.15 |
Interactive version: theaggregate.ai/benchmark?slug=cyberseceval2-vulnerability-exploit · How the rankings work · Data refreshed daily, snapshot 2026-07-22.