小米 MiMo-V2.6-Pro/Flash 登陆 Agent Arena
MiMo-V2.6-Pro and MiMo-V2.6-Flash by @XiaomiMiMo have landed in Agent Arena!
小米 MiMo-V2.6-Pro 与 MiMo-V2.6-Flash 登陆 Agent Arena，Pro 在开源模型中排第 5，8.1K+ 真实智能体会话净提升 +3.17%，较 MiMo-V2.5-Pro 的 -7.23% 提升 10.4 个百分点、名次上升 9 位。其 Confirmed Success 得分 +7.35%，在开源模型中排第 2。Flash 在 13K+ 会话中净提升 -0.57%，开源排名第 9，单任务中位成本 $0.04，比 Pro 低 56%，并进入 Agent Arena 帕累托前沿。
查看原帖Introducing Xiaomi MiMo-V2.6 — Pro & Flash. Frontier intelligence, all the modalities, built in public. 🔹 Two omnimodal models, advancing through scaled reinforcement learning 🔹 Pro performs on par with Claude Opus 5 and GPT-5.6 Sol across most agent benchmarks 🔹 Pro scores 46 on the Artificial Analysis Intelligence Index — the highest among…
展开完整原文
Introducing Xiaomi MiMo-V2.6 — Pro & Flash. Frontier intelligence, all the modalities, built in public. 🔹 Two omnimodal models, advancing through scaled reinforcement learning 🔹 Pro performs on par with Claude Opus 5 and GPT-5.6 Sol across most agent benchmarks 🔹 Pro scores 46 on the Artificial Analysis Intelligence Index — the highest among open-source models 🔹 Stronger coding, computer use, 3D reasoning and creative capabilities 🔹 Open model weights, technical report, RL environments and training code Blog：https://t.co/JGdwC9Ymvj
正文
当前显示原文，中文全文译文尚未就绪。
MiMo-V2.6-Pro and MiMo-V2.6-Flash by @XiaomiMiMo have landed in Agent Arena!
MiMo-V2.6-Pro ranks #5 among open-source models with +3.17% net improvement across 8.1K+ real-world agentic sessions. This release is a +10.4 percentage-point lift and a 9-spot improvement from MiMo-V2.5-Pro at #13 with -7.23%!
Its strongest signal is Confirmed Success (explicit user feedback that the task worked) where it scored +7.35% and ranks #2 among open-source models!
MiMo-V2.6-Flash landed #9 among open models with -0.57% net improvement across 13K+ real-world agentic sessions.
At a $0.04 median cost per task (56% lower than MiMo-V2.6-Pro), it also landed on the Agent Arena Pareto frontier! See its placement below.
Congrats to the @XiaomiMiMo team on the release!