SpatialBabel — leaderboard
Metric: Three.js (self-reported). Source: benchmarklist.com. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 79.2 |
| 2 | Gemini 2.5 Pro | 73.2 |
| 3 | GPT-4o | 73 |
| 4 | Claude Sonnet 4.6 | 69.3 |
| 5 | Gemini 3 Flash (Preview) | 68.4 |
| 6 | Gemini 2.5 Flash | 67.2 |
| 7 | GPT-5 | 64.6 |
| 8 | InternVL3-8B | 54.1 |
Interactive version: theaggregate.ai/benchmark?slug=spatialbabel · How the rankings work · Data refreshed daily, snapshot 2026-07-22.