MiMo-V2.6-Flash
Description
MiMo-V2.6-Flash is Xiaomi's MIT-licensed omnimodal sparse Mixture-of-Experts model with 309B total parameters and 15B active parameters. It supports text, image, video, and audio understanding with a 1,048,576-token context window and text output. MiMo-V2.6 scales reinforcement learning across coding, general agents, visual tasks, and cybersecurity. Xiaomi's launch article is dated September 22, 2026; released weights are named MiMo-V2.6-Flash-RL. Benchmark results are Xiaomi-reported release evaluations, distinct from intermediate live-training checkpoints.
Capability Radar
Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agentic Capability | 142 | 26.0 | LS |
| General Ranking | 35 | 40.0 | AA |
| Multimodal Ranking | 55 | 56.0 | LS |
| Science | 37 | 38.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Agents
Code
Multimodal
Reasoning
AA Evaluation Indices
(Artificial Analysis)LLM Stats Category Scores
(LLM Stats (zeroeval))Pricing
Speed
Provider Price Ranking
Provider Price Ranking
22 providers
Compare pricing across different API providers for this model.