PanoSpace-Bench - Absolute Direction: leaderboard
Metric: Accuracy (%; 250 four-option multiple-choice questions on one ERP panorama). Source: arxiv.org. Saturation forecast: Around 2033. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 VL 8B | 47.6 |
| 2 | GPT-4o | 37.2 |
| 3 | Ministral 3 14B | 35.6 |
| 4 | Qwen 2.5 VL 7B Instruct | 34 |
| 5 | MiMo-V2.5 | 26.8 |
| 6 | Qwen 3.5 9B | 25.2 |
| 7 | Ministral 3 8B | 22.4 |
Interactive version: theaggregate.ai/benchmark?slug=panospace-bench-absolute-direction · How It Works · Data refreshed daily, snapshot 2026-09-25.