GST-Bench - Global Position (Semantic): leaderboard
Metric: Mean accuracy (%; predicted top-down map position of a previously seen object within 100 to 300 pixels, averaged over five thresholds; target named by its category; zero-shot, greedy decoding, official prompt templates, over human-verified questions on 6,790 minutes of simulator-rendered egocentric exploration video). Source: arxiv.org. Saturation forecast: Around May 2027. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 43.67 |
| 2 | GPT-5 | 43.23 |
| 3 | Seed 1.8 | 36.07 |
| 4 | Gemini 2.5 Pro | 32.4 |
| 5 | Qwen 3 VL 32B | 26.55 |
| 6 | GPT-4o | 25.24 |
| 7 | InternVL3.5-8B | 14.85 |
Interactive version: theaggregate.ai/benchmark?slug=gst-bench-global-position-semantic · How It Works · Data refreshed daily, snapshot 2026-09-29.