SpatialWorld - Physical: leaderboard
Metric: Task success rate (%) on all 655 physical-simulator tasks (task-weighted over the five scenario categories); task success rate (%) judged by terminal-state verifiers, vision-only egocentric observation and a unified text action interface, temperature 1.0, 30-turn history, step budget twice the human golden action count plus 10; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 14.4 |
| 2 | Qwen 3.5 397B A17B | 12.2 |
| 3 | Gemini 3.1 Pro (Preview) | 9.2 |
| 4 | Kimi K2.5 | 9.2 |
| 5 | Gemini 3 Flash | 7.2 |
| 6 | Qwen 3 VL 235B A22B Instruct | 6.9 |
| 7 | Gemini 2.5 Pro | 6.7 |
| 8 | GPT-5.4 | 6.6 |
| 9 | Qwen 3 VL 235B A22B (Thinking) | 6.1 |
| 10 | Seed 2.0 Lite | 5.8 |
| 11 | GLM-4.5V | 4 |
| 12 | Qwen 2.5 VL 72B Instruct | 3.4 |
| 13 | GLM-4.6V | 2.7 |
Interactive version: theaggregate.ai/benchmark?slug=spatialworld-physical · How It Works · Data refreshed daily, snapshot 2026-09-29.