GST-Bench - Egocentric Direction (Semantic): leaderboard
Metric: Mean accuracy (%; share of predicted egocentric directions to a previously seen object within 15, 30 and 45 degrees, 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 2029. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 31.09 |
| 2 | Gemini 2.5 Pro | 23.08 |
| 3 | Gemini 3 Pro | 22.11 |
| 4 | Seed 1.8 | 20.35 |
| 5 | InternVL3.5-8B | 16.67 |
| 6 | Qwen 3 VL 32B | 15.22 |
| 7 | GPT-4o | 13.46 |
Interactive version: theaggregate.ai/benchmark?slug=gst-bench-egocentric-direction-semantic · How It Works · Data refreshed daily, snapshot 2026-09-29.