Enter opens the highlighted result. Esc closes.

Muse Spark 1.3 vs MiMo-V2.6-Pro

MiMo-V2.6-Pro leads Muse Spark 1.3 on coding, 65.4 to 57.4 on the Vibe Coding Index, and MiMo-V2.6-Pro costs 4.9x less per output token ($0.87 vs $4.25 per million). Updated October 22, 2026; 64 benchmarks have a result for both.

Replace Muse Spark 1.3 Replace MiMo-V2.6-Pro
Muse Spark 1.3Meta
Coding
57.4
Overall
68.6
Output $/M
$4.25
35
MiMo-V2.6-ProXiaomi
Coding
65.4
Overall
68.4
Output $/M
$0.87
28
vs boards won of 64 shared, 1 tied

Muse Spark 1.3 or MiMo-V2.6-Pro: which to pick

Pick MiMo-V2.6-Pro for coding: it scores 65.4 on the Vibe Coding Index against 57.4 for Muse Spark 1.3.

Pick Muse Spark 1.3 for work measured by LiveBench coding or LMArena WebDev, where it leads.

Model AMuse Spark 1.3Meta57.4/1004 independent benchmarksNo cost per solved taskModel BMiMo-V2.6-ProXiaomi65.4/1004 independent benchmarksNo cost per solved task
Shared results
64
Muse Spark 1.3 only
28
MiMo-V2.6-Pro only
9
Like-for-like categories
8 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Muse Spark 1.3 57.4 from 4 benchmarks, MiMo-V2.6-Pro 65.4 from 4 benchmarks.
Widest category
Coding, 6.1 points apart on average over 16 shared benchmarks.
Widest single gap
Terminal-Bench 4 (Vals AI): Muse Spark 1.3 10.6% against MiMo-V2.6-Pro 31.3%, 27.6 points apart on a 0 to 100 scale.
Output price
Muse Spark 1.3 $4.25 against MiMo-V2.6-Pro $0.87 per million output tokens, 4.9x apart.
Context window
Muse Spark 1.3 takes 1.05M tokens, MiMo-V2.6-Pro 1.05M.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryMuse Spark 1.3BarsMiMo-V2.6-ProTies
Coding871 tie
Intelligence10
Agentic work55
Reasoning34
Math03
Knowledge31
Web design61
General97
All shared boards35281 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index87
Coding benchmarks for Muse Spark 1.3 and MiMo-V2.6-Pro
BenchmarkMuse Spark 1.3MiMo-V2.6-ProLeader
LiveBench coding90.2%81.5%Muse Spark 1.3
LMArena WebDev16591625Muse Spark 1.3
AA Coding Index75.8Not measuredOnly Muse Spark 1.3 measured
Terminal-Bench 4 (Vals AI)10.6%31.3%MiMo-V2.6-Pro
Vibe Code Bench (Vals AI)82.9%85.2%MiMo-V2.6-Pro
Code migration (Vals AI)27.6%43.0%MiMo-V2.6-Pro
ProgramBench (Vals AI)0.5%0.5%Tie
IOI (Vals AI)43.9%39.3%Muse Spark 1.3
Terminal-Bench 2.1 (Vals AI)72.3%67.8%Muse Spark 1.3
SWE-bench Multimodal (Vals AI)Not measured41.3%Only MiMo-V2.6-Pro measured
CyberBench (Vals AI)69.4%72.9%MiMo-V2.6-Pro
SciCode59.7%60.9%MiMo-V2.6-Pro
FrontierSWE25.8%Not measuredOnly Muse Spark 1.3 measured
ALE-Bench1688.31158.1Muse Spark 1.3
LMArena Text: coding15101533MiMo-V2.6-Pro
LMArena Text: software and IT15111528MiMo-V2.6-Pro
LMArena WebDev: React16721639Muse Spark 1.3
LMArena WebDev: HTML16531616Muse Spark 1.3
LMArena WebDev: from an image16401598Muse Spark 1.3
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Muse Spark 1.3 and MiMo-V2.6-Pro
BenchmarkMuse Spark 1.3MiMo-V2.6-ProLeader
AA Intelligence Index48.146.3Muse Spark 1.3
Epoch Capabilities Index157.2Not measuredOnly Muse Spark 1.3 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index55
Agentic work benchmarks for Muse Spark 1.3 and MiMo-V2.6-Pro
BenchmarkMuse Spark 1.3MiMo-V2.6-ProLeader
AA Agentic Index55.5Not measuredOnly Muse Spark 1.3 measured
Design Arena: agents building web apps12971290Muse Spark 1.3
Design Arena: agents building full-stack apps1295Not measuredOnly Muse Spark 1.3 measured
Design Arena: agents building mobile apps1218Not measuredOnly Muse Spark 1.3 measured
Design Arena: agents building Godot games1241Not measuredOnly Muse Spark 1.3 measured
Design Arena: PowerPoint slides1219Not measuredOnly Muse Spark 1.3 measured
Design Arena: spreadsheets1062Not measuredOnly Muse Spark 1.3 measured
LiveBench research68.6%76.7%MiMo-V2.6-Pro
LiveBench browser80.0%88.0%MiMo-V2.6-Pro
LiveBench long agentic40.4%47.5%MiMo-V2.6-Pro
SREBench (Vals AI)Not measured3.0%Only MiMo-V2.6-Pro measured
Finance Agent (Vals AI)58.9%57.3%Muse Spark 1.3
Tax Agent Bench (Vals AI)36.0%32.4%Muse Spark 1.3
Legal Research Bench (Vals AI)40.9%47.1%MiMo-V2.6-Pro
Harvey's Legal Agent Benchmark (Vals AI)Not measured13.8%Only MiMo-V2.6-Pro measured
Excel Modeling Benchmark (Vals AI)62.7%62.9%MiMo-V2.6-Pro
Terminal-Bench-Science (Vals AI)4.3%2.9%Muse Spark 1.3
APEX-Agents58.6%54.4%Muse Spark 1.3
Neither model has a result on the other 23 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index34
Reasoning benchmarks for Muse Spark 1.3 and MiMo-V2.6-Pro
BenchmarkMuse Spark 1.3MiMo-V2.6-ProLeader
LiveBench reasoning89.7%79.6%Muse Spark 1.3
MysteryMechanism (Vals AI)Not measured15.3%Only MiMo-V2.6-Pro measured
GPQA Diamond (Artificial Analysis run)94.1%Not measuredOnly Muse Spark 1.3 measured
Humanity's Last Exam (Artificial Analysis run)48.7%49.4%MiMo-V2.6-Pro
Chess puzzles37.0%Not measuredOnly Muse Spark 1.3 measured
Mystery game puzzles25.0%Not measuredOnly Muse Spark 1.3 measured
LMArena Text: hard prompts15031511MiMo-V2.6-Pro
LMArena Text: expert15191541MiMo-V2.6-Pro
LMArena Text: hard prompts in English15001520MiMo-V2.6-Pro
LMArena Vision: diagrams13301281Muse Spark 1.3
LMArena Vision: homework12961264Muse Spark 1.3
Neither model has a result on the other 11 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Muse Spark 1.3 and MiMo-V2.6-Pro
BenchmarkMuse Spark 1.3MiMo-V2.6-ProLeader
OTIS Mock AIME99.2%Not measuredOnly Muse Spark 1.3 measured
FrontierMath, tiers 1 to 374.4%Not measuredOnly Muse Spark 1.3 measured
FrontierMath, tier 446.3%Not measuredOnly Muse Spark 1.3 measured
ProofBench58.0%70.0%MiMo-V2.6-Pro
LMArena Text: math14971500MiMo-V2.6-Pro
LMArena Text: mathematical work14911511MiMo-V2.6-Pro
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index31
Knowledge benchmarks for Muse Spark 1.3 and MiMo-V2.6-Pro
BenchmarkMuse Spark 1.3MiMo-V2.6-ProLeader
MedCode (Vals AI)Not measured45.0%Only MiMo-V2.6-Pro measured
LMArena Text: science15071506Muse Spark 1.3
LMArena Text: medicine and healthcare14931497MiMo-V2.6-Pro
LMArena Text: legal and government14991485Muse Spark 1.3
LMArena Text: business and finance14901468Muse Spark 1.3
Neither model has a result on the other 13 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index61
Web design benchmarks for Muse Spark 1.3 and MiMo-V2.6-Pro
BenchmarkMuse Spark 1.3MiMo-V2.6-ProLeader
Design Arena: websites13561308Muse Spark 1.3
Design Arena: UI components13491340Muse Spark 1.3
Design Arena: game dev13281314Muse Spark 1.3
Design Arena: data viz13431336Muse Spark 1.3
Design Arena: 3D13581330Muse Spark 1.3
Design Arena: all code categories13521317Muse Spark 1.3
Design Arena: SVG1301Not measuredOnly Muse Spark 1.3 measured
Design Arena: ASCII art1278Not measuredOnly Muse Spark 1.3 measured
LiveBench design74.8%78.5%MiMo-V2.6-Pro
GeneralLike-for-likePublic boards, shown as published, kept out of the index97
General benchmarks for Muse Spark 1.3 and MiMo-V2.6-Pro
BenchmarkMuse Spark 1.3MiMo-V2.6-ProLeader
Vals IndexNot measured57.8%Only MiMo-V2.6-Pro measured
LiveBench data analysis79.6%72.3%Muse Spark 1.3
Public Benefits Bench (Vals AI)Not measured68.9%Only MiMo-V2.6-Pro measured
SAGE (Vals AI)Not measured45.0%Only MiMo-V2.6-Pro measured
MedScribe (Vals AI)Not measured88.3%Only MiMo-V2.6-Pro measured
Long context reasoning (AA-LCR)83.0%86.3%MiMo-V2.6-Pro
DTBench96.5%Not measuredOnly Muse Spark 1.3 measured
LMCA53.9%Not measuredOnly Muse Spark 1.3 measured
LMArena Text14901491MiMo-V2.6-Pro
LMArena Text: instruction following14791491MiMo-V2.6-Pro
LMArena Text: creative writing14621466MiMo-V2.6-Pro
LMArena Vision13081263Muse Spark 1.3
LMArena Text: English14951504MiMo-V2.6-Pro
LMArena Text: non-English14811474Muse Spark 1.3
LMArena Text: Chinese15321529Muse Spark 1.3
LMArena Text: German1513Not measuredOnly Muse Spark 1.3 measured
LMArena Text: Japanese1470Not measuredOnly Muse Spark 1.3 measured
LMArena Text: Korean1490Not measuredOnly Muse Spark 1.3 measured
LMArena Text: French1511Not measuredOnly Muse Spark 1.3 measured
LMArena Text: Spanish1496Not measuredOnly Muse Spark 1.3 measured
LMArena Text: Russian14911479Muse Spark 1.3
LMArena Text: Polish1490Not measuredOnly Muse Spark 1.3 measured
LMArena Text: multi-turn14871466Muse Spark 1.3
LMArena Text: longer queries14881501MiMo-V2.6-Pro
LMArena Text: writing and language14701470Muse Spark 1.3
LMArena Text: entertainment and media14571465MiMo-V2.6-Pro
LMArena Vision: English12981268Muse Spark 1.3
LMArena Vision: Chinese1384Not measuredOnly Muse Spark 1.3 measured
LMArena Vision: reading text13191270Muse Spark 1.3
LMArena Vision: humor1293Not measuredOnly Muse Spark 1.3 measured
LMArena Vision: creative writing1296Not measuredOnly Muse Spark 1.3 measured
Neither model has a result on the other 15 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Muse Spark 1.3 and MiMo-V2.6-Pro
BenchmarkMuse Spark 1.3MiMo-V2.6-ProLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Muse Spark 1.3$0.0034Fits in one request
MiMo-V2.6-Pro$0.0009Fits in one request

MiMo-V2.6-Pro costs less

Repository review

50K input + 3K output tokens

Muse Spark 1.3$0.075Fits in one request
MiMo-V2.6-Pro$0.024Fits in one request

MiMo-V2.6-Pro costs less

Agent loop

200K input + 10K output tokens

Muse Spark 1.3$0.292Fits in one request
MiMo-V2.6-Pro$0.096Fits in one request

MiMo-V2.6-Pro costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Muse Spark 1.3 and MiMo-V2.6-Pro
SpecificationMeta Muse Spark 1.3Xiaomi MiMo-V2.6-Pro
MakerMetaXiaomi
WeightsNo public weights listedOpen weights
ReleasedSeptember 2, 2026September 21, 2026
Context window1.05M1.05M
Input $/Mtok$1.25$0.435
Output $/Mtok$4.25$0.87
Coding index57.465.4
Independent measurements behind it44
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Muse Spark 1.3 better than MiMo-V2.6-Pro for coding?

Pick MiMo-V2.6-Pro for coding: it scores 65.4 on the Vibe Coding Index against 57.4 for Muse Spark 1.3. Pick Muse Spark 1.3 for work measured by LiveBench coding or LMArena WebDev, where it leads.

Which is cheaper, Muse Spark 1.3 or MiMo-V2.6-Pro?

Muse Spark 1.3 costs $1.25 per million input tokens and $4.25 per million output tokens; MiMo-V2.6-Pro costs $0.435 and $0.87. Cost per solved task is known for neither of them.

Which has the bigger context window, Muse Spark 1.3 or MiMo-V2.6-Pro?

MiMo-V2.6-Pro, with 1.05M tokens against 1.05M.

How many benchmarks is the Muse Spark 1.3 vs MiMo-V2.6-Pro comparison based on?

64 benchmarks have a result for both models as of October 22, 2026. Muse Spark 1.3's coding index rests on 4 independent benchmarks and MiMo-V2.6-Pro's on 4. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/meta-muse-spark-1-3-vs-xiaomi-mimo-v2-6-pro" title="Muse Spark 1.3 vs MiMo-V2.6-Pro, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/meta-muse-spark-1-3-vs-xiaomi-mimo-v2-6-pro">LLMBenchmark.ai, Muse Spark 1.3 vs MiMo-V2.6-Pro</a></p>