POLECAT-FOR-ME - Israel: leaderboard
The Israel test set of POLECAT-FOR-ME (ThinkTank-ME paper by Li et al., 2026): given the history of related POLECAT events as (subject, relation, object) triples, the model predicts the missing object of a later event query. Accuracy in percent; higher is better.
Metric: Accuracy (%; predicted object entity of event queries on the Israel test set). Source: arxiv.org. Saturation forecast: Around April 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 22.2 | #741 |
| 2 | GPT-4o Mini | 20.3 | #1627 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=polecat-for-me-israel · How It Works · Data refreshed daily, snapshot 2026-11-12.