RustMizan - Line Localization: leaderboard

Metric: Micro-averaged F1 (%) of the predicted vulnerable (file, line) pairs over the 173 compilable crate-, file- and function-level Rust variants of 42 RustSec memory-safety CVEs, unmutated, each analysed by a ReAct agent with shell access in an Inspect sandbox that returns a structured JSON verdict; higher is better. Source: arxiv.org. Saturation forecast: Around 2028. 4 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.623.2
2Gemini 3.1 Pro (Preview)23.1
3Qwen 3.6 Plus20.2
4GPT-5.417.5

Interactive version: theaggregate.ai/benchmark?slug=rustmizan-line-localization · How It Works · Data refreshed daily, snapshot 2026-09-29.