8853.3 tok/s
8952.0 tok/s
9051.1 tok/s
9150.0 tok/s
92Qwen3.5 397B A17B48.9 tok/s
93
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher infere...
按基准分类汇总的 0-100 分表现。
Input and output token limits for this model, plus how it ranks on long-context understanding.
2 个指标
2 个指标
2 个指标
1 个指标
排名基于社区提交的测试数据与定期健康探测，仅供参考，非官方数据。Artificial Analysis标准基准数据可能包含 BenchLM 等公开来源。