PanoSpace-Bench - Seam Continuity: leaderboard
Metric: Accuracy (%; 250 two- or four-option multiple-choice questions on one ERP panorama). Source: arxiv.org. Saturation forecast: Around July 2027. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | MiMo-V2.5 | 45.6 |
| 2 | Qwen 3.5 9B | 41.2 |
| 3 | GPT-4o | 37.6 |
| 4 | Qwen 3 VL 8B | 34.4 |
| 5 | Qwen 2.5 VL 7B Instruct | 32 |
| 6 | Ministral 3 8B | 28.4 |
| 7 | Ministral 3 14B | 21.6 |
Interactive version: theaggregate.ai/benchmark?slug=panospace-bench-seam-continuity · How It Works · Data refreshed daily, snapshot 2026-09-25.