Vision2Code — leaderboard
Metric: Avg. (self-reported). Source: benchmarklist.com. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 4.12 |
| 2 | GPT-5.4 Mini | 4.1 |
| 3 | Gemini 3.1 Flash | 3.17 |
| 4 | Qwen 3.5 397B A17B | 2.41 |
| 5 | Qwen 3.5 9B | 1.6 |
Interactive version: theaggregate.ai/benchmark?slug=vision2code · How the rankings work · Data refreshed daily, snapshot 2026-07-22.