German Statutory QA - Pre-Amendment (Vanilla): leaderboard
German statutory case questions whose fact date requires an earlier version of one provision rather than the current law (Prior, Schultz and Grabmair, 2026). Share of 113 expert-validated questions whose legal outcome a Gemini 3 Flash Preview judge rates fully correct, in percent, answered without retrieval or web search; higher is better.
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 June 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 | 49.56 | #172 |
| 2 | DeepSeek V3.2 | 37.17 | #403 |
| 3 | Claude Opus 4.5 | 35.4 | #152 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=german-statutory-qa-pre-amendment-vanilla · How It Works · Data refreshed daily, snapshot 2026-11-12.