Precedent Treatment - Fine-Grained (Few-Shot): leaderboard
Negative precedent treatment classification (Validate Your Authority, 2026): given the passages of a later US court opinion that discuss a precedent, a model labels how the opinion treats it, on citing relationships annotated by Paul Hellyer. This board uses the sixteen fine-grained citator treatment labels and a prompt with three worked examples; a prediction counts when it matches any expert-acceptable label. Accuracy in percent; higher is better.
Metric: Instance-based accuracy (%): share of the scored citing relationships (239 in the corpus) whose single predicted fine-grained treatment label (one of 16 citator signals such as distinguished, questioned or overruled) matches any of the expert-acceptable ground-truth labels, few-shot prompt with three dataset examples, which are removed from the test set, given the citing-opinion paragraphs that discuss the precedent; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 4 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 66.82 | #276 |
| 2 | Gemini 2.5 Flash | 62.76 | #463 |
| 3 | GPT-5 Mini | 57.6 | #364 |
| 4 | Qwen 3 30B A3B | 54.84 | #1156 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=precedent-treatment-fine-grained-few-shot · How It Works · Data refreshed daily, snapshot 2026-11-21.