An experimental research model focusing on advanced visual reasoning and step-by-step cognitive capabilities. Achieves strong performance on multi-modal science and mathematics tasks, though exhibits some limitations such as potential language mixing and recursive reasoning loops.
发布日期2024年12月25日
参数规模73.4B
上下文长度—
许可证Qwen
知识截止—
Benchmarks
评测成绩
| 评测基准 | 类别 | 分数 | 来源 |
|---|---|---|---|
| MathVista | math vision multimodal | 71.4 | 来源 |
| MMMU | multimodal reasoning general | 70.3 | 来源 |
| MathVision | math vision multimodal | 35.9 | 来源 |
| OlympiadBench | math reasoning physics multimodal | 20.4 | 来源 |
Pricing
API 价格对比
暂无 API 价格。