GST-Bench - Egocentric Distance (Semantic): leaderboard
Metric: Mean relative accuracy (%; distance to a previously seen object within relative-error thresholds 0.50 to 0.95, averaged; 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 August 2027. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 35.4 |
| 2 | GPT-5 | 27.39 |
| 3 | Gemini 3 Pro | 27.39 |
| 4 | Qwen 3 VL 32B | 16.19 |
| 5 | Seed 1.8 | 13.32 |
| 6 | GPT-4o | 10.13 |
| 7 | InternVL3.5-8B | 8.36 |
Interactive version: theaggregate.ai/benchmark?slug=gst-bench-egocentric-distance-semantic · How It Works · Data refreshed daily, snapshot 2026-09-29.