SecGoal (Zero-Shot): leaderboard
SecGoal (2026) is an expert-annotated benchmark for extracting formalizable security-goal statements from the specification documents of 15 widely deployed protocols. This board is Extraction-Coverage F1 from 0 to 1, the harmonic mean of extraction precision and property-level recall, with zero-shot prompting, averaged over protocols; higher is better.
Metric: Extraction-Coverage F1 (0-1), the harmonic mean of extraction precision and property-level recall, for extracting formalizable security-goal statements from protocol documents with zero-shot prompting, averaged over 15 protocols; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 10 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 0.452 | #119 |
| 2 | GLM-5 | 0.444 | #269 |
| 3 | Qwen 3.5 Plus | 0.419 | #242 |
| 4 | Gemini 3 Flash (Preview) | 0.378 | #152 |
| 5 | DeepSeek V4 Pro | 0.361 | #196 |
| 6 | DeepSeek V4 Flash | 0.353 | #267 |
| 7 | GPT-5.4 | 0.329 | #135 |
| 8 | Claude Sonnet 4.6 | 0.322 | #173 |
| 9 | Qwen 2.5 7B Instruct | 0.314 | #2723 |
| 10 | Gemma 2 9B (IT) | 0.207 | #2369 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=secgoal-zero-shot · How It Works · Data refreshed daily, snapshot 2026-11-21.