Benchmarks
Spatialviz Bench
Models scored
8
Best score
0.45
Metric
Overall score
Spatialviz Bench is an AI evaluation tracked by Epoch AI, with 8 scored model versions on record. The scores here are reported by third parties rather than produced by Epoch AI running the evaluation itself.
Scored models span January 2024 to June 2025. The best score recorded is 0.45, measured as Overall score. Models come from Alibaba, Meta AI, OpenAI, Anthropic, Google DeepMind.
Full record
- Score metric
- Overall score
- Models scored
- 8
- Best score recorded
- 0.45
- Earliest model scored
- Jan 18, 2024
- Most recent model scored
- Jun 17, 2025
- Third-party reported
- Yes
Leaderboard
| 01 | gemini-2.5-pro | Google DeepMind | 0.45 |
| 02 | o1-2024-12-17_unknown | OpenAI | 0.41 |
| 03 | gemini-2.5-flash | Google DeepMind | 0.37 |
| 04 | Llama-4-Scout-17B-16E-Instruct | Meta AI | 0.34 |
| 05 | claude-3-7-sonnet-20250219_unknown | Anthropic | 0.34 |
| 06 | Qwen2.5-VL-72B-Instruct | Alibaba | 0.33 |
| 07 | Qwen-VL-Max | 0.32 | |
| 08 | Llama-4-Maverick-17B-128E-Instruct | Meta AI | 0.32 |
More benchmarks
SourceEpoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/benchmarks. Licensed under CC BY 4.0.
← All benchmarks