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

Change models
MiMo-V2.5Xiaomi
IndexAll categories, out of 100.
54.8 ±6.8
70.2 ±4.7 best
GapIndex points below the top.
−15.4
Top
CoverageIndex weight that has results.
75%
80% best
SpeedOutput tokens per second.
4/s
31/s best
EloLMArena rating and rank.
1428
1492 best
ReleasedMonth of release.
2026-04
2026-09
Input / 1MUS dollars per 1M input tokens.
$0.40 best
$0.435
Output / 1MUS dollars per 1M output tokens.
$2.00
$0.87 best
1K chats2K tokens in, 500 out, each.
$1.80
$1.31 best
1K documents20K tokens in, 1K out, each.
$10.00
$9.57 best
1K agent tasks200K tokens in, 20K out, each.
$120.00
$104.40 best
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
56.5
72.1 best
CodingCode writing and repair.
55.5
66.6 best
ReasoningLogic problems and puzzles.
—
68.3
MultimodalTasks with images and text.
57.2
—
KnowledgeFacts and expert knowledge.
50.5
64.2 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
52.7
71.3 best

Benchmarks

10 shared
Only MiMo-V2.5: 18Only MiMo-V2.6-Pro: 48
MiMo-V2.5
MiMo-V2.6-Pro
42.2%75 / 123
85.2% best16 / 123
MedScribeHealthcare
72.2%90 / 109
88.3% best13 / 109
MedCodeHealthcare
31.9%91 / 106
45.0% best39 / 106
9.1%82 / 90
47.1% best16 / 90
7.8%71 / 82
32.4% best22 / 82
36.7%67 / 79
57.3% best16 / 79
14.2%57 / 77
43.0% best26 / 77
EMBFinance
55.1%50 / 75
62.9% best30 / 75
60.7%40 / 75
67.8% best32 / 75
16.0%46 / 54
70.0% best21 / 54