ALPHA CWE Penalty (SecurityEval): leaderboard

Metric: ALPHA penalty (sum over 121 vulnerable Python functions of hierarchy distance x direction multiplier between the predicted and true CWE; 0 is perfect; mean of three runs at temperature 0.8). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 7 models tracked.

Top models

#ModelScore
1devstral:24b [Q4_K_M]578.5
2qwen2.5-coder:32b [Q4_K_M]617.8
3phi4:14b [Q4_K_M]797.4
4llama3.1:8b [Q4_K_M]856.5
5qwen2.5-coder:7b [Q4_K_M]921.5
6mistral:7b [Q4_K_M]1156.9
7deepseek-coder:6.7b [Q4_0]1228.5

Interactive version: theaggregate.ai/benchmark?slug=alpha-cwe-penalty-securityeval · How It Works · Data refreshed daily, snapshot 2026-09-25.