LLM Stats (WorldVQA): leaderboard
WorldVQA as reported by LLM Stats — visual question answering over images and knowledge grounded in the world; leaderboard score.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Around 2029. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Seed 2.1 Pro | 53 | #67 |
| 2 | Kimi K3 | 51 | #30 |
| 3 | Muse Spark Open | 49.4 | #54 |
| 4 | Seed 2.1 Turbo | 48.6 | #86 |
| 5 | Seed 2.0 Mini | 47.6 | #276 |
| 6 | Kimi K2.5 | 46.3 | #144 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-worldvqa · How It Works · Data refreshed daily, snapshot 2026-10-20.