WeSCE - Complete Clearance: leaderboard
Part of WeSCE (Zhang et al., 2026): the percentage of programs left with near-zero residual vulnerability risk after a model edits them under functional-only instructions, averaged over feature addition, feature removal, bug fixing and refactoring. Risk combines CodeQL, Bandit and Atheris findings; higher is better.
Metric: Complete clearance rate (%; share of edited programs whose residual risk after the edit falls below 0.01; 400 executable real-world-derived Python programs edited under functional-only (weak-security) instructions, 100 each for feature addition, feature removal, bug fixing and refactoring; risk before and after the edit aggregates CodeQL and Bandit static findings and 90-second Atheris fuzzing findings, severity-weighted and size-normalized, through LogSumExp; mean of the four task rates; top-p 0.9, top-k 20). Source: arxiv.org. Saturation forecast: Around April 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 51.25 | #102 |
| 2 | GPT-5.4 | 50.5 | #123 |
| 3 | Claude Sonnet 4 | 50.5 | #400 |
| 4 | DeepSeek V4 Flash | 49.25 | #258 |
| 5 | Kimi K2.5 | 39.75 | #256 |
| 6 | Claude Haiku 4.5 | 38.5 | #568 |
| 7 | Doubao-1.5-Pro-32k | 36.5 | #683 |
| 8 | GLM-4 32B | 31.5 | #1299 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=wesce-complete-clearance · How It Works · Data refreshed daily, snapshot 2026-11-13.