WikiVQABench — leaderboard
Metric: Accuracy (self-reported). Source: benchmarklist.com. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | InternVL3-78B | 75.6 |
| 2 | Claude Opus 4.6 | 70.3 |
| 3 | Claude Sonnet 4.6 | 66.3 |
| 4 | Llama 3.2 90B Vision Instruct | 65.7 |
| 5 | Qwen 3 VL 32B Instruct | 64 |
| 6 | Qwen 3 VL 8B Instruct | 63.1 |
| 7 | Qwen 3 VL 4B Instruct | 60.2 |
Interactive version: theaggregate.ai/benchmark?slug=wikivqabench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.