Enter opens the highlighted result. Esc closes.

Muse Spark 1.1 vs Mistral Medium 3

Muse Spark 1.1 leads Mistral Medium 3 on the Artificial Analysis Intelligence Index, 33.7 to 9.0, and Mistral Medium 3 costs 2.1x less per output token ($2.00 vs $4.25 per million). Updated October 22, 2026; 48 benchmarks have a result for both.

Replace Muse Spark 1.1 Replace Mistral Medium 3
Muse Spark 1.1Meta
Coding
70.3
Overall
67.0
Output $/M
$4.25
48
Mistral Medium 3Mistral AI
Coding
No data
Overall
No data
Output $/M
$2.00
0
vs boards won of 48 shared

Muse Spark 1.1 or Mistral Medium 3: which to pick

Only Muse Spark 1.1 has a coding score, 70.3 on the Vibe Coding Index; Mistral Medium 3 has none, so the two cannot be ranked on coding.

Pick Mistral Medium 3 for output tokens 2.1x cheaper ($2.00 vs $4.25 per million).

Model AMuse Spark 1.1Meta70.3/1003 independent benchmarks$0.43 per solved taskModel BMistral Medium 3Mistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
48
Muse Spark 1.1 only
48
Mistral Medium 3 only
9
Like-for-like categories
7 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 1.1 70.3 from 3 benchmarks, Mistral Medium 3 not benchmarked.
Widest category
Web design, 27.7 points apart on average over 6 shared benchmarks.
Widest single gap
Long context reasoning (AA-LCR): Muse Spark 1.1 77.7% against Mistral Medium 3 31.3%, 46.3 points apart on a 0 to 100 scale.
Output price
Muse Spark 1.1 $4.25 against Mistral Medium 3 $2.00 per million output tokens, 2.1x apart.
Context window
Muse Spark 1.1 takes 1.05M tokens, Mistral Medium 3 131K.

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 1.1BarsMistral Medium 3Ties
Coding20
Intelligence20
Reasoning70
Math20
Knowledge40
Web design60
General250
All shared boards480
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
Coding benchmarks for Muse Spark 1.1 and Mistral Medium 3
BenchmarkMuse Spark 1.1Mistral Medium 3Leader
LMArena WebDev1542Not measuredOnly Muse Spark 1.1 measured
AA Coding Index71.3Not measuredOnly Muse Spark 1.1 measured
LiveCodeBench (Vals AI)85.9%Not measuredOnly Muse Spark 1.1 measured
SWE-bench Verified (Vals AI)82.0%Not measuredOnly Muse Spark 1.1 measured
Vibe Code Bench (Vals AI)72.2%Not measuredOnly Muse Spark 1.1 measured
Code migration (Vals AI)31.1%Not measuredOnly Muse Spark 1.1 measured
ProgramBench (Vals AI)0.0%Not measuredOnly Muse Spark 1.1 measured
Terminal-Bench 2.1 (Vals AI)69.3%Not measuredOnly Muse Spark 1.1 measured
SkillsBench (Vals AI)59.2%Not measuredOnly Muse Spark 1.1 measured
LiveCodeBench (Artificial Analysis run)Not measured40.0%Only Mistral Medium 3 measured
SciCode58.8%Not measuredOnly Muse Spark 1.1 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured3.8%Only Mistral Medium 3 measured
LMArena Text: coding14981385Muse Spark 1.1
LMArena Text: software and IT14981385Muse Spark 1.1
LMArena WebDev: React1532Not measuredOnly Muse Spark 1.1 measured
LMArena WebDev: HTML1540Not measuredOnly Muse Spark 1.1 measured
LMArena WebDev: from an image1540Not measuredOnly Muse Spark 1.1 measured
Neither model has a result on the other 22 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Muse Spark 1.1 and Mistral Medium 3
BenchmarkMuse Spark 1.1Mistral Medium 3Leader
AA Intelligence Index33.79.0Muse Spark 1.1
Epoch Capabilities Index154.1134.0Muse Spark 1.1
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index17 boards, none shared
Agentic work benchmarks for Muse Spark 1.1 and Mistral Medium 3
BenchmarkMuse Spark 1.1Mistral Medium 3Leader
AA Agentic Index25.8Not measuredOnly Muse Spark 1.1 measured
Design Arena: agents building web apps1207Not measuredOnly Muse Spark 1.1 measured
Design Arena: agents building full-stack apps1199Not measuredOnly Muse Spark 1.1 measured
Design Arena: agents building mobile apps1175Not measuredOnly Muse Spark 1.1 measured
Design Arena: agents building Android apps1178Not measuredOnly Muse Spark 1.1 measured
Design Arena: agents building Godot games1103Not measuredOnly Muse Spark 1.1 measured
Design Arena: agents building games1183Not measuredOnly Muse Spark 1.1 measured
Design Arena: HTML slides1195Not measuredOnly Muse Spark 1.1 measured
Design Arena: PowerPoint slides1155Not measuredOnly Muse Spark 1.1 measured
Design Arena: spreadsheets1042Not measuredOnly Muse Spark 1.1 measured
Finance Agent (Vals AI)57.2%Not measuredOnly Muse Spark 1.1 measured
Legal Research Bench (Vals AI)38.0%Not measuredOnly Muse Spark 1.1 measured
Excel Modeling Benchmark (Vals AI)56.4%Not measuredOnly Muse Spark 1.1 measured
Time Horizon Index (Vals AI)1.7%Not measuredOnly Muse Spark 1.1 measured
τ²-Bench TelecomNot measured24.3%Only Mistral Medium 3 measured
APEX-Agents31.8%Not measuredOnly Muse Spark 1.1 measured
Vending-Bench 2$6,520Not measuredOnly Muse Spark 1.1 measured
Neither model has a result on the other 24 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index70
Reasoning benchmarks for Muse Spark 1.1 and Mistral Medium 3
BenchmarkMuse Spark 1.1Mistral Medium 3Leader
GPQA Diamond91.2%Not measuredOnly Muse Spark 1.1 measured
MMMU Pro (Vals AI)86.6%Not measuredOnly Muse Spark 1.1 measured
GPQA Diamond (Artificial Analysis run)89.8%57.8%Muse Spark 1.1
Humanity's Last Exam (Artificial Analysis run)46.2%4.1%Muse Spark 1.1
Chess puzzles34.0%Not measuredOnly Muse Spark 1.1 measured
LMArena Text: hard prompts14851364Muse Spark 1.1
LMArena Text: expert14781342Muse Spark 1.1
LMArena Text: hard prompts in English14801374Muse Spark 1.1
LMArena Vision: diagrams13051155Muse Spark 1.1
LMArena Vision: homework12871165Muse Spark 1.1
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for Muse Spark 1.1 and Mistral Medium 3
BenchmarkMuse Spark 1.1Mistral Medium 3Leader
AA Math IndexNot measured30.3Only Mistral Medium 3 measured
AIME 2025 (Artificial Analysis run)Not measured30.3%Only Mistral Medium 3 measured
ProofBench39.0%Not measuredOnly Muse Spark 1.1 measured
LMArena Text: math14821353Muse Spark 1.1
LMArena Text: mathematical work14871354Muse Spark 1.1
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for Muse Spark 1.1 and Mistral Medium 3
BenchmarkMuse Spark 1.1Mistral Medium 3Leader
MMLU Pro88.7%Not measuredOnly Muse Spark 1.1 measured
LegalBench (Vals AI)85.0%Not measuredOnly Muse Spark 1.1 measured
CorpFin (Vals AI)71.3%Not measuredOnly Muse Spark 1.1 measured
TaxEval (Vals AI)79.7%Not measuredOnly Muse Spark 1.1 measured
MortgageTax (Vals AI)66.1%Not measuredOnly Muse Spark 1.1 measured
MMLU Pro (Artificial Analysis run)Not measured76.0%Only Mistral Medium 3 measured
SimpleQA Verified57.8%Not measuredOnly Muse Spark 1.1 measured
LMArena Text: science14841381Muse Spark 1.1
LMArena Text: medicine and healthcare14791381Muse Spark 1.1
LMArena Text: legal and government14811384Muse Spark 1.1
LMArena Text: business and finance14701352Muse Spark 1.1
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for Muse Spark 1.1 and Mistral Medium 3
BenchmarkMuse Spark 1.1Mistral Medium 3Leader
Design Arena: websites12701079Muse Spark 1.1
Design Arena: UI components12891022Muse Spark 1.1
Design Arena: game dev12691017Muse Spark 1.1
Design Arena: data viz12681034Muse Spark 1.1
Design Arena: 3D12601083Muse Spark 1.1
Design Arena: all code categories12761068Muse Spark 1.1
Design Arena: SVG1235Not measuredOnly Muse Spark 1.1 measured
Design Arena: ASCII art1271Not measuredOnly Muse Spark 1.1 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index250
General benchmarks for Muse Spark 1.1 and Mistral Medium 3
BenchmarkMuse Spark 1.1Mistral Medium 3Leader
Public Benefits Bench (Vals AI)61.3%Not measuredOnly Muse Spark 1.1 measured
SAGE (Vals AI)45.6%Not measuredOnly Muse Spark 1.1 measured
MedScribe (Vals AI)88.9%Not measuredOnly Muse Spark 1.1 measured
Vals Multimodal Index66.7%Not measuredOnly Muse Spark 1.1 measured
IFBenchNot measured39.3%Only Mistral Medium 3 measured
Long context reasoning (AA-LCR)77.7%31.3%Muse Spark 1.1
DTBench94.4%62.3%Muse Spark 1.1
LMCA49.9%Not measuredOnly Muse Spark 1.1 measured
Surface Evolver Bench52.5%Not measuredOnly Muse Spark 1.1 measured
LMArena Text14781370Muse Spark 1.1
LMArena Text: instruction following14571338Muse Spark 1.1
LMArena Text: creative writing14351343Muse Spark 1.1
LMArena Vision12931157Muse Spark 1.1
LMArena Text: English14781385Muse Spark 1.1
LMArena Text: non-English14711353Muse Spark 1.1
LMArena Text: Chinese15151374Muse Spark 1.1
LMArena Text: German14691377Muse Spark 1.1
LMArena Text: Japanese14501316Muse Spark 1.1
LMArena Text: Korean14591304Muse Spark 1.1
LMArena Text: French14921368Muse Spark 1.1
LMArena Text: Spanish14641364Muse Spark 1.1
LMArena Text: Russian14821359Muse Spark 1.1
LMArena Text: Polish14991371Muse Spark 1.1
LMArena Text: multi-turn14841384Muse Spark 1.1
LMArena Text: longer queries14621360Muse Spark 1.1
LMArena Text: writing and language14481352Muse Spark 1.1
LMArena Text: entertainment and media14381335Muse Spark 1.1
LMArena Vision: English12921172Muse Spark 1.1
LMArena Vision: Chinese13481161Muse Spark 1.1
LMArena Vision: reading text13011154Muse Spark 1.1
LMArena Vision: humor12881145Muse Spark 1.1
LMArena Vision: captioningNot measured1094Only Mistral Medium 3 measured
LMArena Vision: recognizing thingsNot measured1141Only Mistral Medium 3 measured
LMArena Vision: creative writing12531146Muse Spark 1.1
LMArena Document1465Not measuredOnly Muse Spark 1.1 measured
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Muse Spark 1.1 and Mistral Medium 3
BenchmarkMuse Spark 1.1Mistral Medium 3Leader
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 1.1$0.0034Fits in one request
Mistral Medium 3$0.0014Fits in one request

Mistral Medium 3 costs less

Repository review

50K input + 3K output tokens

Muse Spark 1.1$0.075Fits in one request
Mistral Medium 3$0.026Fits in one request

Mistral Medium 3 costs less

Agent loop

200K input + 10K output tokens

Muse Spark 1.1$0.292Fits in one request
Mistral Medium 3$0.100Exceeds the context window

Mistral Medium 3 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 1.1 and Mistral Medium 3
SpecificationMeta Muse Spark 1.1Mistral Medium 3
MakerMetaMistral AI
WeightsNo public weights listedNo public weights listed
ReleasedJuly 16, 2026May 7, 2025
Context window1.05M131K
Input $/Mtok$1.25$0.40
Output $/Mtok$4.25$2.00
Coding index70.3Not benchmarked
Independent measurements behind it30
Cost per solved task$0.43Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Muse Spark 1.1 better than Mistral Medium 3 for coding?

Only Muse Spark 1.1 has a coding score, 70.3 on the Vibe Coding Index; Mistral Medium 3 has none, so the two cannot be ranked on coding. Pick Mistral Medium 3 for output tokens 2.1x cheaper ($2.00 vs $4.25 per million).

Which is cheaper, Muse Spark 1.1 or Mistral Medium 3?

Muse Spark 1.1 costs $1.25 per million input tokens and $4.25 per million output tokens; Mistral Medium 3 costs $0.40 and $2.00. Cost per solved task is known for Muse Spark 1.1 only.

Which has the bigger context window, Muse Spark 1.1 or Mistral Medium 3?

Muse Spark 1.1, with 1.05M tokens against 131K.

How many benchmarks is the Muse Spark 1.1 vs Mistral Medium 3 comparison based on?

48 benchmarks have a result for both models as of October 22, 2026. Muse Spark 1.1's coding index rests on 3 independent benchmarks and Mistral Medium 3's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next