AssertLLM2: leaderboard
Assertion-based verification (ABV) is a cornerstone of modern hardware design, yet manually translating design intent into formal SystemVerilog Assertions (SVAs) remains labor-intensive and error-prone. While Large Language Models (LLMs) show promise for automating this process, existing benchmarks remain limited by unrealistic task formulations, weak specification inputs, and oversimplified evalu
Metric: Coverage Formal (self-reported). Source: benchmarklist.com. Saturation forecast: Around April 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 28.32 | #142 |
| 2 | GPT-5.2 | 27.15 | #110 |
| 3 | Gemini 2.5 Pro | 25.71 | #152 |
| 4 | DeepSeek V3.2 | 24.17 | #205 |
| 5 | Qwen 3 Coder Plus | 18.55 | #338 |
| 6 | Llama 4 Maverick | 12.69 | #464 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=assertllm2 · How It Works · Data refreshed daily, snapshot 2026-10-20.