PatRe - Rebuttal Quality: leaderboard
PatRe (2026) models patent examination on 480 recent USPTO cases across all eight IPC sections. Acting as the applicant, the model writes the rebuttal to an office action. A Gemini 3.1 Flash Lite judge rates soundness, clarity, constructiveness, completeness and legal style from 1 to 10, and the score is their mean; higher is better.
Metric: Overall rebuttal quality on a 1-10 scale: mean of the soundness, clarity, constructiveness, completeness and legal-style ratings of a Gemini-3.1-Flash-Lite judge at temperature 0, for applicant rebuttals to the office actions of 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. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 Mini | 9.18 | #364 |
| 2 | DeepSeek V3.2 | 8.37 | #419 |
| 3 | Gemini 2.5 Flash | 8.34 | #463 |
| 4 | Qwen 3.5 27B | 8.29 | #375 |
| 5 | Qwen 3.5 9B | 7.09 | #828 |
| 6 | Gemma 3 27B (IT) | 5.47 | #1324 |
| 7 | Llama 3.3 70B Instruct | 4.59 | #1385 |
| 8 | Gemma 3 12B (IT) | 4.58 | #1887 |
| 9 | GPT-4o Mini | 4.5 | #1667 |
| 10 | Llama 3.1 8B Instruct | 3.71 | #4600 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=patre-rebuttal-quality · How It Works · Data refreshed daily, snapshot 2026-11-21.