GST-Bench: leaderboard
Metric: Average score (%; unweighted mean of the 12 subtask scores (mean accuracy over tolerance thresholds for direction and position, mean relative accuracy for distance, accuracy for multiple choice); 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 April 2028. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 42.68 |
| 2 | Gemini 2.5 Pro | 40.95 |
| 3 | GPT-5 | 40.85 |
| 4 | Seed 1.8 | 34.04 |
| 5 | Qwen 3 VL 32B | 30.43 |
| 6 | GPT-4o | 30.33 |
| 7 | InternVL3.5-8B | 22.99 |
Interactive version: theaggregate.ai/benchmark?slug=gst-bench · How It Works · Data refreshed daily, snapshot 2026-09-29.