Seeing Culture - VQA Accuracy — leaderboard
Metric: Overall Accuracy (%). Source: seeingculture-benchmark.github.io. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O3 | 85.15 |
| 2 | Gemini 2.5 Pro | 82.88 |
| 3 | GPT-4.1 | 81.97 |
Interactive version: aibenchmarks.dev/benchmark?slug=seeing-culture-vqa-accuracy · How the rankings work · Data refreshed daily, snapshot 2026-07-20.