PuzzleMate - Piece Selection with Natural Language Reference (Aria): leaderboard
Metric: Accuracy (%; correct as judged by human annotators for clarity and spatial accuracy; task: naming the piece that fits a missing slot among five unmarked candidates in a natural-language reference of at most 35 tokens; three 48-piece jigsaw puzzles photographed from an egocentric viewpoint, Project Aria glasses camera (low-resolution, noisy egocentric images)). Source: arxiv.org. Saturation forecast: Around 2032. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 52 |
| 2 | Gemini 2.5 Pro | 48 |
| 3 | Gemma 3 27B | 45 |
| 4 | Gemma 3 12B | 43 |
| 5 | Gemma 3 4B | 42 |
Interactive version: theaggregate.ai/benchmark?slug=puzzlemate-piece-selection-with-natural-language-reference-aria · How It Works · Data refreshed daily, snapshot 2026-09-26.