← Benchmarks
V*
A visual reasoning benchmark evaluating multimodal inference under challenging spatial and grounded tasks.
id v-star · max 1 · 7 models reported
| # | Model | Score |
|---|---|---|
| 1 | Kimi K2.6 Moonshot AI · open | 0.97 |
| 2 | Qwen3.6 Plus Alibaba Cloud / Qwen Team | 0.97 |
| 3 | Qwen3.6-27B Alibaba Cloud / Qwen Team · open | 0.95 |
| 4 | Qwen3.5-27B Alibaba Cloud / Qwen Team · open | 0.94 |
| 5 | Qwen3.5-122B-A10B Alibaba Cloud / Qwen Team · open | 0.93 |
| 6 | Qwen3.5-35B-A3B Alibaba Cloud / Qwen Team · open | 0.93 |
| 7 | GLM-5V-Turbo Zhipu AI | 0.89 |