Kimi K3投资研究能力获基准测试,击败GPT-5.5和OPUS-4.8

Kimi K3 Investment Research Capability Benchmarked: Moonshot AI Top Model Now Powers AlphaEngine With First-Tier IRB Scores

精选理由

Kimi K3在投资研究上直接干翻了GPT-5.5和OPUS-4.8,时间判断和证据边界控制尤其强,已经在AlphaEngine上用了,搞金融研究的可以试试。

AI 摘要

Moonshot AI旗下Kimi K3模型在AlphaEngine的专有IRB投资研究基准测试中,以更高得分击败GPT-5.5和OPUS-4.8。测试涵盖时间判断、证据边界控制和前提修正三个维度。Kimi K3已部署在AlphaEngine平台上。

原文 · Pandaily

Kimi K3 Investment Research Capability Benchmarked: Moonshot AI Top Model Now Powers AlphaEngine With First-Tier IRB Scores

AlphaEngine tests Kimi K3 on proprietary IRB investment research benchmark: K3 beats GPT-5.5 and OPUS-4.8 in temporal judgment, evidence boundary control, and premise correction, already deployed on platform.