PatRe - Office Action Quality (OA-DP): leaderboard

PatRe (2026) models patent examination on 480 recent USPTO cases across all eight IPC sections. Acting as the examiner, the model writes an office action from the claims with no prior art (direct prompting). 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 office action 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, office action generation under direct prompting: the model writes the office action from the claims (and any preceding rebuttal) with no prior art, 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: Around September 2028. 10 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-5 Mini4.56#373
2Qwen 3.5 27B4.35#380
3Gemini 2.5 Flash4.26#466
4DeepSeek V3.24.26#425
5Qwen 3.5 9B4.07#838
6Gemma 3 27B (IT)3.75#1341
7GPT-4o Mini3.75#1680
8Gemma 3 12B (IT)3.68#1907
9Llama 3.3 70B Instruct3.45#1394
10Llama 3.1 8B Instruct3.12#4655

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=patre-office-action-quality-oa-dp · How It Works · Data refreshed daily, snapshot 2026-11-22.