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

#ModelScoreOverall rank
1Gemini 2.5 Pro66.82#276
2Gemini 2.5 Flash62.76#463
3GPT-5 Mini57.6#364
4Qwen 3 30B A3B54.84#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.