German Statutory QA - Pre-Amendment (Vanilla): leaderboard
Metric: Correct outcomes (%; share of 113 expert-validated German statutory questions whose fact date requires an earlier version of one provision whose legal conclusion a Gemini 3 Flash Preview judge scores fully correct, model without retrieval or tools). Source: arxiv.org. Saturation forecast: Around December 2027. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 49.56 |
| 2 | DeepSeek V3.2 | 37.17 |
| 3 | Claude Opus 4.5 | 35.4 |
Interactive version: theaggregate.ai/benchmark?slug=german-statutory-qa-pre-amendment-vanilla · How It Works · Data refreshed daily, snapshot 2026-09-26.