MiMo-V2-Omni vs MiMo-V2-Pro

Change models
IndexAll categories, out of 100.
47.2 ±6.6
51.8 ±7.6 best
GapIndex points below the top.
−4.6 · no clear gap
Top
CoverageIndex weight that has results.
85% best
75%
SpeedOutput tokens per second.
—
—
EloLMArena rating and rank.
1423
1437 best
ReleasedMonth of release.
2026-03
2026-03
Input / 1MUS dollars per 1M input tokens.
—
—
Output / 1MUS dollars per 1M output tokens.
—
—
1K chats2K tokens in, 500 out, each.
—
—
1K documents20K tokens in, 1K out, each.
—
—
1K agent tasks200K tokens in, 20K out, each.
—
—
ContextMaximum tokens in one request.
262K
1M best
AgenticMulti-step tasks with tools.
46.9
53.3 best
CodingCode writing and repair.
56.4
58.8 best
ReasoningLogic problems and puzzles.
48.9 best
45.8
MultimodalTasks with images and text.
46.1
—
KnowledgeFacts and expert knowledge.
44.9
52.0 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
39.0
53.3 best
MathMath problems.
—
—

Benchmarks

9 shared
Only MiMo-V2-Omni: 1Only MiMo-V2-Pro: 2
MiMo-V2-Omni
MiMo-V2-Pro
22.1%107 / 222
30.4% best78 / 222
75.0% best95 / 217
68.3%122 / 217
1.1% best118 / 214
0.3%137 / 214
82.8%90 / 199
87.0% best60 / 199
19.3%135 / 164
26.6% best93 / 164
91.2%39 / 149
95.0% best23 / 149
53.5%75 / 146
68.8% best49 / 146
74.8%45 / 114
78.0% best29 / 114
Claw-EvalAgentic
45.2%40 / 42
57.8% best30 / 42