Artificial Analysis· @ArtificialAnlys · X·· 1 小时前AI 评分51
AI 导读
Artificial Analysis 测得 Mistral Large 4 (high) 在 Intelligence Index 每项任务上消耗 82K 输出 token，处于开放权重模型的帕累托前沿；得分更高的开放权重模型每项任务消耗 113K 或更多。相比 Preview 版本，Mistral Large 4 (high) 每项任务的输出 token 用量减少 39%。
正文
Mistral Large 4 (high) uses 82K output tokens per Intelligence Index task and sits on the open weights Pareto frontier, while open weights models that score higher use 113K or more. Compared to the Preview, Mistral Large 4 (high) uses 39% fewer output tokens per Intelligence Index task
来源：Artificial Analysis · x.com