MiMo-V2.5-Pro vs MiMo-V2-Omni

Change models
IndexAll categories, out of 100.
56.3 ±4.6 best
47.2 ±6.6
GapIndex points below the top.
Top
−9.1
CoverageIndex weight that has results.
85%
85%
SpeedOutput tokens per second.
47/s
—
EloLMArena rating and rank.
1464 best
1423
ReleasedMonth of release.
2026-04
2026-03
Input / 1MUS dollars per 1M input tokens.
$0.48
—
Output / 1MUS dollars per 1M output tokens.
$1.80
—
1K chats2K tokens in, 500 out, each.
$1.86
—
1K documents20K tokens in, 1K out, each.
$11.40
—
1K agent tasks200K tokens in, 20K out, each.
$132.00
—
ContextMaximum tokens in one request.
1.02M best
262K
AgenticMulti-step tasks with tools.
58.2 best
46.9
CodingCode writing and repair.
57.2 best
56.4
ReasoningLogic problems and puzzles.
53.3 best
48.9
MultimodalTasks with images and text.
—
46.1
KnowledgeFacts and expert knowledge.
51.2 best
44.9
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
63.7 best
39.0
MathMath problems.
54.8
—

Benchmarks

8 shared
Only MiMo-V2.5-Pro: 31Only MiMo-V2-Omni: 2
MiMo-V2.5-Pro
MiMo-V2-Omni
35.7% best59 / 222
22.1%107 / 222
79.7% best45 / 217
75.0%95 / 217
4.0% best92 / 214
1.1%118 / 214
86.6% best63 / 199
82.8%90 / 199
22.4% best119 / 164
19.3%135 / 164
94.2% best26 / 149
91.2%39 / 149
79.9% best5 / 146
53.5%75 / 146
Claw-EvalAgentic
63.8% best19 / 42
45.2%40 / 42