Semgrep IDOR - Multimodal F1 — leaderboard
Metric: F1 score (%). Source: semgrep.dev. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol | 61.7 |
| 2 | GPT-5.6 Luna | 61.6 |
| 3 | GPT-5.6 Terra | 59.3 |
| 4 | GLM-5.2 | 58.1 |
| 5 | GPT-5.5 | 48.1 |
| 6 | Claude Opus 4.8 | 44.8 |
Interactive version: aibenchmarks.dev/benchmark?slug=semgrep-idor-multimodal-f1 · How the rankings work · Data refreshed daily, snapshot 2026-07-18.