Verus-SpecBench: leaderboard
AI coding agents are increasingly used to write real-world software, but ensuring that their outputs are correct remains a fundamental challenge. Formal verification offers a promising path: an agent generates code together with a machine-checked proof, guaranteeing that the code satisfies a formal specification. However, there is no guarantee that the formal spec itself matches the user's intent.
Metric: Pass@1 (self-reported). Source: benchmarklist.com. Saturation forecast: Around August 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 77.8 | #152 |
| 2 | GPT-5.3 Codex | 57.8 | #69 |
| 3 | Claude Opus 4.6 | 51.1 | #63 |
| 4 | Kimi K2.6 | 25.5 | #104 |
| 5 | DeepSeek V4 Pro | 24.3 | #102 |
| 6 | GLM-5.1 | 21.5 | #97 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=verus-specbench · How It Works · Data refreshed daily, snapshot 2026-10-20.