Model creator

Xiaomi

Every Xiaomi model in the BenchSift catalogue, with its scores, ranks, prices and capabilities as the sources publish them.

View in the catalogue
Models
15
17 configurations, reasoning levels included
Open weights
8
8 of 15 models
Latest release
Sep 21, 2026
MiMo-V2.6-Flash · First dated model: Dec 16, 2025
Median price
$0.544
$0.166 to $5.44 per million tokens, across 5 priced models

Best scores and ranks

The creator's best model on each measure, and its rank among every measured model in the catalogue.

Intelligence

MiMo-V2.6-Pro
29.9Rank 131 of 782 measured models
60.2Rank 85 of 301 measured models
96.3Rank 6 of 270 measured models
21.3Rank 96 of 191 measured models

Output speed

MiMo-V2.5
79.2 t/sRank 253 of 449 measured models
$0.15Rank 150 of 740 measured models

OpenRouter ranking

MiMo-V2.6-Flash
#12

Capabilities

Number of models that declare each capability. Tool calling and structured outputs come from OpenRouter.
Reasoning11 of 15
Open weights8 of 15
Tool calling5 of 15
Structured outputs5 of 15

Input

  • Text15
  • Image6
  • Audio5
  • Video5

Output

  • Text11
  • Speech4

Overview

Model types

  • Text11
  • Audio4

Releases by year

  • 202613
  • 20252

Models

15

Reasoning levels are folded into one entry. The rank is the whole catalogue's: sorting does not change it.

  • MiMo-V2.6-Pro

    Text · Reasoning · Open weights · Sep 21, 2026 · $0.544 · 57.3 t/s

    29.9#131 of 782
  • MiMo-V2-Pro

    Text · Reasoning · Mar 18, 2026

    28.6#141 of 782
  • MiMo-V2.6-Flash

    Text · Reasoning · Open weights · Sep 21, 2026 · $0.175 · 37.6 t/s

    26.7#164 of 782
  • MiMo-V2.5-Pro

    Text · Reasoning · Open weights · 2 configurations · Apr 22, 2026 · $0.544 · 51.7 t/s

    26.0#173 of 782
  • MiMo-V2-Omni-0327

    Text · Reasoning · Mar 27, 2026

    25.1#184 of 782
  • MiMo-V2-Omni

    Text · Reasoning · Mar 19, 2026

    23.9#203 of 782
  • MiMo-V2-Flash (Feb 2026)

    Text · Reasoning · Open weights · Dec 16, 2025

    22.4#229 of 782
  • MiMo-V2.5

    Text · Reasoning · Open weights · Apr 22, 2026 · $0.166 · 79.2 t/s

    21.8#235 of 782
  • MiMo-V2-Flash

    Text · Reasoning · Open weights · 2 configurations · Dec 16, 2025

    16.0#318 of 782
  • MiMo-V2.6-Pro-UltraSpeed

    Text · Reasoning · Open weights · Sep 21, 2026 · $5.44

    —
  • MiMo-V2.5-Pro-UltraSpeed

    Text · Reasoning · Open weights · Jun 8, 2026

    —
  • MiMo-V2.5-TTS

    Audio · Apr 22, 2026

    —
  • MiMo-V2.5-TTS-VoiceClone

    Audio · Apr 22, 2026

    —
  • MiMo-V2.5-TTS-VoiceDesign

    Audio · Apr 22, 2026

    —
  • MiMo-V2-TTS

    Audio · Mar 18, 2026

    —
Where these figures come from

Each catalogue model is tied to its creator by the identity Artificial Analysis publishes, or OpenRouter's and Models.dev's for models it does not track. Counts fold the reasoning levels of one model together. Ranks compare each measure with every measured model in the catalogue, configurations included, as model pages do. The price is the published blended price (3 input tokens to 1 output token).

Figures computed by BenchSift from the catalogue: Artificial Analysis, OpenRouter, Models.dev and Hugging Face. A value no model carries is not shown.

Data retrieved on Nov 12, 2026.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy