45%
best score so far on SpatialViz-Bench, the hardest of these 4 image understanding benchmarks for AI
What the chart shows
Each row is one image understanding benchmark in Epoch AI’s hub. The best score so far is highest on VPCT (physics from images) (91%, Gemini 3 Pro Preview, 2025) and lowest on SpatialViz-Bench (45%, Gemini 2.5 Pro (Jun 2025), 2025).
VPCT (physics from images) is at 90% or more, close to its ceiling, so it no longer separates the leading models. Newer benchmarks are built to stay hard, which is why their scores start low.
Key numbers
| Measure | Value |
|---|---|
| VPCT (physics from images) (2025) | 91% |
| GeoBench (country from photo) (2025) | 88% |
| MindCube (spatial views) (2025) | 47% |
| SpatialViz-Bench (2025) | 45% |
How to read it
- Each cell is the best score among models released that year, from Epoch AI’s own runs or the results it collects; settings differ by benchmark.
- Only benchmarks scored as a share of questions or tasks, with results from at least two release years, are included.
- Choose a benchmark from the list above the chart; the full grid is in the downloadable image and CSV.
Source: Epoch AI, 2026: Benchmarking Hub, read 3 November 2026. Chart and text by AI Adoption.
Numbers checked against the published data on 3 November 2026.
Download the data (CSV) · Cite this chart
Numbers checked against the published data on 3 November 2026.
Download the data (CSV) · Cite this chart
Discussion