PatRe - Rebuttal Coverage: leaderboard
Metric: Point-wise coverage (%): share of the atomic rejection points of the office action that the generated applicant rebuttal answers, over PatRe (480 recent USPTO patent examination histories across all eight IPC sections, with office actions, rebuttals, claim versions and cited references), temperature 0; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 Mini | 90.5 |
| 2 | Gemini 2.5 Flash | 81.5 |
| 3 | Qwen 3.5 27B | 79.2 |
| 4 | DeepSeek V3.2 | 79.1 |
| 5 | Qwen 3.5 9B | 63.4 |
| 6 | Gemma 3 27B (IT) | 39.9 |
| 7 | Llama 3.3 70B Instruct | 30.9 |
| 8 | Gemma 3 12B (IT) | 30.5 |
| 9 | Llama 3.1 8B Instruct | 29.5 |
| 10 | GPT-4o Mini | 27.8 |
Interactive version: theaggregate.ai/benchmark?slug=patre-rebuttal-coverage · How It Works · Data refreshed daily, snapshot 2026-10-07.