MiMo-V2.5 vs Mistral Large 2
Compare MiMo-V2.5 by Xiaomi against Mistral Large 2 by Mistral AI, context windows of 1.0M vs 128K, tested across 23 shared challenges.
Our Verdict
MiMo-V2.5
Mistral Large 2Runner-up
No community votes yet. On paper, MiMo-V2.5 has the edge — newer, bigger context window.
MiMo-V2.5 is 12x cheaper per token — worth considering if cost matters.
Too close to call
API pricing
Cost per 1M tokens
MiMo-V2.5
Input
$0.40
20× cheaper
Output
$2.00
12× cheaper
Mistral Large 2
Input
$8.00
Output
$24.00
MiMo-V2.5 is cheaper on both — 20× input, 12× output
Writing DNA
Style Comparison
Similarity
63%
MiMo-V2.5 uses 6.6x more transitions
MiMo-V2.5
Mistral Large 2
57%Vocabulary43%
17wSentence Length21w
0.64Hedging0.39
5.9Bold14.4
2.8Lists7.4
1.01Emoji0.80
1.07Headings1.41
0.07Transitions0.01
Based on 27 + 10 text responses
Research
What we learned reading every model
FAQ
