Models scored
25
evaluated
Modality
multimodal
Category
spatial reasoning
+1 more
Published
—
Search
| # | Model | Lab | Score |
|---|---|---|---|
| 01 | Qwen3.7-Plus | Alibaba Cloud / Qwen Team | 87 |
| 02 | Seed 2.1 Pro | ByteDance | 87 |
| 03 | Seed 2.1 Turbo | ByteDance | 86 |
| 04 | Qwen3.6 Plus | Alibaba Cloud / Qwen Team | 85 |
| 05 | Qwen3.6-35B-A3B | Alibaba Cloud / Qwen Team | 85 |
| 06 | Qwen3.5-122B-A10B | Alibaba Cloud / Qwen Team | 85 |
| 07 | Qwen3.6-27B | Alibaba Cloud / Qwen Team | 84 |
| 08 | Qwen3.5-35B-A3B | Alibaba Cloud / Qwen Team | 84 |
| 09 | Qwen3.5-27B | Alibaba Cloud / Qwen Team | 84 |
| 10 | Qwen3 VL 235B A22B Thinking | Alibaba Cloud / Qwen Team | 81 |
| 11 | Qwen3 VL 235B A22B Instruct | Alibaba Cloud / Qwen Team | 79 |
| 12 | Qwen3 VL 32B Instruct | Alibaba Cloud / Qwen Team | 79 |
| 13 | Qwen3 VL 32B Thinking | Alibaba Cloud / Qwen Team | 78 |
| 14 | Qwen2-VL-72B-Instruct | Alibaba Cloud / Qwen Team | 78 |
| 15 | Qwen3 VL 30B A3B Thinking | Alibaba Cloud / Qwen Team | 77 |
| 16 | Qwen3 VL 30B A3B Instruct | Alibaba Cloud / Qwen Team | 74 |
| 17 | Qwen3 VL 8B Thinking | Alibaba Cloud / Qwen Team | 74 |
| 18 | Qwen3 VL 4B Thinking | Alibaba Cloud / Qwen Team | 73 |
| 19 | Qwen3 VL 8B Instruct | Alibaba Cloud / Qwen Team | 72 |
| 20 | Qwen3 VL 4B Instruct | Alibaba Cloud / Qwen Team | 71 |
| 21 | Qwen2.5-Omni-7B | Alibaba Cloud / Qwen Team | 70 |
| 22 | Grok-1.5V | xAI | 69 |
| 23 | DeepSeek VL2 | DeepSeek | 68 |
| 24 | DeepSeek VL2 Small | DeepSeek | 65 |
| 25 | DeepSeek VL2 Tiny | DeepSeek | 64 |
25 of 25 models · score normalized 0–100 where available