> ## Content Index
> Fetch the complete content index at: https://aiadoption.org/llms.txt
> Use this file to discover other available public pages before exploring further.

# AI's best scores on 4 image understanding benchmarks range from 45% on SpatialViz-Bench to 91% on VPCT (physics from images)
- URL: https://aiadoption.org/data/ai-image-understanding-benchmarks-explorer/
- Published: 2026-10-31T12:12:25.000Z
- Updated: 2026-11-03T20:39:43.000Z
- Description: Across 4 image understanding benchmarks in Epoch AI's data, the best score so far runs from 45% on SpatialViz-Bench to 91% on VPCT (physics from images). Choose a benchmark to see its best score year by year.
- Author: Manu
- Tags: Data, AI Benchmarks, Computer Vision, #chart, #hub-benchmarks

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](https://aiadoption.org/sources/#epoch-ai), 2026: [Benchmarking Hub](https://epoch.ai/benchmarks?ref=aiadoption.org), read 3 November 2026\. Chart and text by AI Adoption.  
Numbers checked against the published data on 3 November 2026.  
[Download the data (CSV)](https://charts.aiadoption.org/ai-index/csv/ai-image-understanding-benchmarks-explorer.csv?ref=aiadoption.org) · [Cite this chart](#source)