WorldVQA — Distinct named world-knowledge VQA benchmark; Kimi K2.5 card
| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Qwen3.7 Plus Preview | Alibaba | 61.1 | 1 | 2026-08-23 |
| 2 | Kimi K3 | Moonshot | 51 | 1 | 2026-08-23 |
| 3 | Gemini 3 Pro | 47.4 | 1 | 2026-06-15 | |
| 4 | Kimi K2.5 | Moonshot | 46.3 | 2 | 2026-08-23 |
| 5 | Claude Opus 4.5 | Anthropic | 36.8 | 1 | 2026-06-15 |
| 6 | GPT-5.2 | OpenAI | 28 | 1 | 2026-06-15 |
| 7 | Qwen3 VL 235B A22B Reasoning | Alibaba | 23.5 | 1 | 2026-06-15 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.