Unverified50% confidenceFactExact time
MiMo-V2.6 uses native FP8 weights.
1
Sources
50%
Confidence
Long-term
Relevance
9/24/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedAt the time of observation, MiMo-V2.6 Pro's DeepSWE v1.1 score was 62.24 and MiMo-V2.6 Flash's was 60.77.77% similarVerifiedThe live-stream page simultaneously trains two models, MiMo-V2.6 Pro and MiMo-V2.6 Flash.72% similarUnverifiedXiaomi launched MiMo-V2.6 on Product Hunt, an open-source omnimodal model family designed for long-horizon agent tasks.71% similarUnverifiedXiaomi has publicly released MiMo-V2.6's model weights, technical report, reinforcement learning (RL) environment, and training code.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/945493API
curl https://kongchang.com/api/v1/knowledge/claims/945493MCP
get_claim(id=945493)