MiMo-V2.6 launches: 1.02T-param open model tops Artificial Analysis open rankings
natolambert · x · 2026-09-22
Nathan Lambert highlights the MiMo-V2.6 family: the flagship MiMo-V2.6-Pro is a 1.02T-parameter MoE with 42B active, and MiMo-V2.6-Flash is 310B with 15B active. The series is now the top open model on the Artificial Analysis leaderboard, shipping alongside an RL training dashboard and a technical report. Lambert is curious to see how adoption lands.
Related event: Xiaomi open-sources MiMo-V2.6, topping open-weight intelligence index(18 posts)→
More from Models
- User tests Grok 4.7 and calls it worse than the Gemini series — prvthvm · 2026-09-22
- DFlash2 reportedly chokes on super long prompts when paired with GLM 5.3 Flash — TheZachMueller · 2026-09-22
- Shots fired at DeepSeek: MiMo pioneered MOPD, observers weigh in on V2.6 — teortaxesTex · 2026-09-22
- Jev fails counting r's in strawberry, aces it 168/168 when given letters — BLUECOW009 · 2026-09-22
- Jev trails Gemini and DeepSeek on calibration, but still handles more decisions solo — frappuccinoCoin · 2026-09-22
- Blogger corrects himself: the real surprise is MiMo-2.6, beating Grok 4.7 at much lower cost — kimmonismus · 2026-09-22