MiMo-V2.6-Pro
Description
MiMo-V2.6-Pro is Xiaomi's MIT-licensed omnimodal sparse Mixture-of-Experts model with 1.02T total parameters and 42B 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-Pro-RL. Benchmark results are Xiaomi-reported release evaluations, distinct from intermediate live-training checkpoints. UltraSpeed serves the same model at higher speed for $4.35 input and $8.70 output per million tokens.
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 | 74 | 47.0 | LS |
| Code Ranking | 30 | 82.0 | LB |
| General Ranking | 28 | 45.0 | AA |
| Multimodal Ranking | 35 | 60.0 | LS |
| Reasoning | 40 | 80.0 | LB |
| Science | 32 | 43.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Agents
Code
General
Multimodal
Reasoning
AA Evaluation Indices
(Artificial Analysis)LLM Stats Category Scores
(LLM Stats (zeroeval))Pricing
Speed
Provider Price Ranking
Provider Price Ranking
18 providers
Compare pricing across different API providers for this model.