VSI-Super-Wild — leaderboard
Metric: Overall Accuracy (%). Source: vsi-super-wild.github.io. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 44.36 |
| 2 | GPT-5.4 | 34.52 |
| 3 | Qwen 3.5 9B | 33.87 |
| 4 | InternVL3.5-8B | 32.18 |
| 5 | Qwen 2 VL 7B | 26.67 |
| 6 | Gemini 3.1 Flash Lite | 23.85 |
Interactive version: aibenchmarks.dev/benchmark?slug=vsi-super-wild · How the rankings work · Data refreshed daily, snapshot 2026-07-20.