SABRE-Prior - Attribute: leaderboard

Metric: Exact counting accuracy (%; open-ended count of the visible components of a familiar object with a noncanonical number of parts, normalized exact match; zero-shot, greedy decoding where supported, 8-16 output tokens for API models; 100 generated or edited cases per subset that survived filtering against Gemini 3.5 Flash and human review). Source: arxiv.org. Saturation forecast: Around 2029. 6 models tracked.

Top models

#ModelScore
1GPT-5.4 (Non-reasoning)20
2Claude Sonnet 4.617
3Kimi K2.6 (Non-reasoning)17
4Grok 4.316
5Qwen 3.5 27B (Non-reasoning)14

Interactive version: theaggregate.ai/benchmark?slug=sabre-prior-attribute · How It Works · Data refreshed daily, snapshot 2026-09-29.