Inference
EN

MiMo-V2.6-Pro vs Muse Wonder

Change models
MiMo-V2.6-ProXiaomi
Muse WonderMeta
IndexAll categories, out of 100.
70.2 ±4.7
73.1 ±4.0 best
GapIndex points below the top.
−2.9 · no clear gap
Top
CoverageIndex weight that has results.
80%
85% best
SpeedOutput tokens per second.
31/s
80/s best
EloLMArena rating and rank.
1492
1503 best
ReleasedMonth of release.
2026-09
2026-10
Input / 1MUS dollars per 1M input tokens.
$0.435 best
$4.00
Output / 1MUS dollars per 1M output tokens.
$0.87 best
$20.00
1K chats2K tokens in, 500 out, each.
$1.31 best
$18.00
1K documents20K tokens in, 1K out, each.
$9.57 best
$100.00
1K agent tasks200K tokens in, 20K out, each.
$104.40 best
$1,200.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
72.1
73.0 best
CodingCode writing and repair.
66.6
72.3 best
ReasoningLogic problems and puzzles.
68.3
73.1 best
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
64.2
68.6 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
74.4
MathMath problems.
71.3
73.5 best

Benchmarks

39 shared
Only MiMo-V2.6-Pro: 19Only Muse Wonder: 23
MiMo-V2.6-Pro
Muse Wonder
Artificial Analysis Humanity's Last ExamKnowledge
49.4%14 / 222
50.1% best12 / 222
Artificial Analysis Long Context ReasoningReasoning
86.3% best3 / 217
80.7%37 / 217
Critical Physics TasksReasoning
26.6%19 / 214
28.3% best15 / 214
Artificial Analysis Omniscience AccuracyKnowledge
34.8%67 / 164
38.0% best59 / 164
GDPval-AA normalizedAgentic
59.2%9 / 133
63.5% best5 / 133
Vibe Code Bench v1.1Coding
85.2% best16 / 123
83.1%22 / 123
Artificial Analysis SciCodeCoding
60.9% best8 / 114
60.3%10 / 114
Legal Research BenchLegal
47.1%16 / 90
50.5% best7 / 90
Tax Agent BenchFinance
32.4%22 / 82
36.3% best15 / 82
LiveBench Data AnalysisReasoning
72.3%49 / 80
81.6% best5 / 80
LiveBench ReasoningReasoning
79.6%59 / 80
90.6% best11 / 80
Finance Agent (v2)Finance
57.3% best16 / 79
56.6%18 / 79
Code MigrationCoding
43.0%26 / 77
62.6% best6 / 77
EMBFinance
62.9%30 / 75
67.1% best18 / 75
Terminal-Bench 4.0Agentic
31.3%24 / 61
49.5% best11 / 61
DeepSWEAgentic
71.9%18 / 59
78.8% best2 / 59
Agent Arena steerabilityAgentic
1.525 / 54
2.6 best22 / 54
Agent Arena task outcomeAgentic
5.016 / 54
5.4 best13 / 54
ProofBench v1.1Math
70.0%21 / 54
84.0% best15 / 54
LiveBench Coding 2.0Coding
81.5%30 / 52
86.2% best20 / 52