PuzzleMate - Piece Sequence Ordering (GoPro): leaderboard
A task of PuzzleMate (Dasgupta et al., 2026), an egocentric jigsaw-puzzle benchmark for multimodal assistants built on three 48-piece puzzles: the model orders five marked candidate pieces for five consecutive missing slots, on photos from a high-resolution GoPro camera. Scored as Kendall rank correlation between the predicted and correct order, from -1 to 1; higher is better.
Metric: Kendall rank correlation (tau, -1 to 1) between the predicted and correct order; task: ordering five unordered candidate pieces, marked with numbered boxes, for five consecutive missing slots; three 48-piece jigsaw puzzles photographed from an egocentric viewpoint, GoPro Hero10 camera (high-resolution images). Source: arxiv.org. Saturation forecast: Around 2029. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 | 0.35 | #172 |
| 2 | Gemma 3 27B | 0.34 | #1638 |
| 3 | Gemma 3 12B | 0.29 | #2013 |
| 4 | Gemini 2.5 Pro | 0.19 | #262 |
| 5 | Gemma 3 4B | 0.14 | #5104 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=puzzlemate-piece-sequence-ordering-gopro · How It Works · Data refreshed daily, snapshot 2026-11-12.