WorldVQA Culture F-score
Multimodal · 2026-01-28
WorldVQA category F-score on 506 Culture, Arts & Crafts questions.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 3 Pro Preview | 47.2 |
| Kimi K2.5 | 43.0 |
| Opus 4.5 | 34.1 |
| Seed1.5-VL | 33.4 |
| Gemini 2.5 Pro | 32.6 |
| GPT-5.2 | 26.7 |
| Qwen3-VL-235B-A22B-Instruct | 22.9 |
| GPT-5.1 | 22.5 |
| Grok 4.1 Fast | 20.2 |
| Grok 4 Fast | 18.6 |
| GPT-4o | 17.8 |
| GLM-4.6V | 17.8 |
| Sonnet 4.5 | 17.4 |
| Qwen3 VL 32B Instruct | 16.8 |
| GLM 4.6V Flash | 13.2 |