AssertLLM2 — leaderboard
Metric: Coverage Formal (self-reported). Source: benchmarklist.com. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 28.32 |
| 2 | GPT-5.2 | 27.15 |
| 3 | Gemini 2.5 Pro | 25.71 |
| 4 | DeepSeek V3.2 | 24.17 |
| 5 | Qwen 3 Coder Plus | 18.55 |
| 6 | Llama 4 Maverick | 12.69 |
Interactive version: theaggregate.ai/benchmark?slug=assertllm2 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.