MiMo-V2.5-Pro vs MiMo-V2.6-Pro

Xiaomi against Xiaomi, the same lab's consecutive models. Prices, scores and speed below are live.

  • MiMo-V2.6-Pro costs 33% less on blended price ($0.82 against $1.22 per 1M tokens, 3 input to 1 output).
  • MiMo-V2.6-Pro scores higher on the Artificial Analysis Intelligence Index: 29.9 against 26.4.
  • On the 20 benchmarks both have scores on, MiMo-V2.5-Pro leads on 1 and MiMo-V2.6-Pro on 19.
  • MiMo-V2.6-Pro reads more context: 1.1M tokens against 1M.
  • MiMo-V2.6-Pro is newer: listed Sep 21, 2026, against Apr 22, 2026.

Side by side

MiMo-V2.5-ProMiMo-V2.6-Pro
LabXiaomiXiaomi
ListedApr 22, 2026Sep 21, 2026
Input per 1M tokens$0.72$0.65
Output per 1M tokens$2.70$1.30
Cached input per 1M$0.14$0.0054
Blended (3:1) per 1M$1.22$0.82
Context window1M1.1M
Max output236K131K
Knowledge cutoff--
Intelligence index26.429.9
Coding index60.2-
ReasoningYesYes
Reads imagesNoYes
Tool useYesYes
Structured outputYesYes

Every benchmark both are scored on

Each model's best score per benchmark, with its source. Scores from different sources or settings are not always comparable; each links to where it was published.

More comparisons

Where these figures come from

Prices are GenMagic's own, what the studio and the API charge, recomputed from each provider's price list every few minutes. The indices are the Artificial Analysis indices, and every benchmark score links to its source, re-read daily. Measured speed is GenMagic's own generation records, in aggregate. See Xiaomi models, Xiaomi models, every LLM's price and our sources.