Inference
EN

MiniMax M3.1 Flash vs Muse Wonder Full

Change models
MiniMax M3.1 FlashMiniMax
Muse Wonder FullMeta
IndexAll categories, out of 100.
69.3 ±5.4
77.3 ±5.3 best
GapIndex points below the top.
−8.0
Top
CoverageIndex weight that has results.
80%
80%
SpeedOutput tokens per second.
100/s
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-10
2026-10
Input / 1MUS dollars per 1M input tokens.
$0.15
—
Output / 1MUS dollars per 1M output tokens.
$0.60
—
1K chats2K tokens in, 500 out, each.
$0.60
—
1K documents20K tokens in, 1K out, each.
$3.60
—
1K agent tasks200K tokens in, 20K out, each.
$42.00
—
ContextMaximum tokens in one request.
1.05M best
1M
AgenticMulti-step tasks with tools.
71.8
78.2 best
CodingCode writing and repair.
69.4
77.3 best
ReasoningLogic problems and puzzles.
67.9
75.6 best
MultimodalTasks with images and text.
58.1
—
KnowledgeFacts and expert knowledge.
68.9
71.7 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
—
79.6

Benchmarks

14 shared
Only MiniMax M3.1 Flash: 22Only Muse Wonder Full: 28
MiniMax M3.1 Flash
Muse Wonder Full
Artificial Analysis Humanity's Last ExamKnowledge
48.0%17 / 222
53.6% best9 / 222
Artificial Analysis Long Context ReasoningReasoning
79.7%45 / 217
83.7% best10 / 217
Critical Physics TasksReasoning
22.3%25 / 214
32.9% best2 / 214
Artificial Analysis Omniscience AccuracyKnowledge
45.1% best37 / 164
41.0%46 / 164
GDPval-AA normalizedAgentic
47.9%31 / 133
67.9% best2 / 133
Vibe Code Bench v1.1Coding
73.9%45 / 123
86.0% best14 / 123
Artificial Analysis SciCodeCoding
53.4%39 / 114
62.6% best4 / 114
Legal Research BenchLegal
34.1%50 / 90
53.4% best6 / 90
Tax Agent BenchFinance
32.1%23 / 82
43.0% best8 / 82
Terminal-Bench 4.0Agentic
25.3%28 / 61
58.1% best6 / 61
DeepSWEAgentic
73.7%13 / 59
79.0% best1 / 59
Agent Arena steerabilityAgentic
−2.636 / 54
9.6 best12 / 54
Agent Arena task outcomeAgentic
−0.734 / 54
11.1 best9 / 54
HLAB-Vals-1.1Legal
7.5%24 / 35
23.3% best5 / 35