Enter opens the highlighted result. Esc closes.

Muse Spark 1.3 vs Mistral Large 3 2512

Muse Spark 1.3 leads Mistral Large 3 2512 on the Artificial Analysis Intelligence Index, 48.1 to 9.3, and Mistral Large 3 2512 costs 2.8x less per output token ($1.50 vs $4.25 per million). Updated October 22, 2026; 14 benchmarks have a result for both.

Replace Muse Spark 1.3 Replace Mistral Large 3 2512
Muse Spark 1.3Meta
Coding
57.4
Overall
68.6
Output $/M
$4.25
14
Mistral Large 3 2512Mistral AI
Coding
No data
Overall
No data
Output $/M
$1.50
0
vs boards won of 14 shared

Muse Spark 1.3 or Mistral Large 3 2512: which to pick

Only Muse Spark 1.3 has a coding score, 57.4 on the Vibe Coding Index; Mistral Large 3 2512 has none, so the two cannot be ranked on coding.

Pick Mistral Large 3 2512 for output tokens 2.8x cheaper ($1.50 vs $4.25 per million).

Model AMuse Spark 1.3Meta57.4/1004 independent benchmarksNo cost per solved taskModel BMistral Large 3 2512Mistral AINot benchmarked1 independent benchmark$0.77 per solved task
Shared results
14
Muse Spark 1.3 only
78
Mistral Large 3 2512 only
14
Like-for-like categories
5 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, Mistral Large 3 2512 not benchmarked.
Widest category
Agentic work, 54.5 points apart on average over 1 shared benchmark.
Widest single gap
AA Coding Index: Muse Spark 1.3 75.8 against Mistral Large 3 2512 20.1, 55.7 points apart on a 0 to 100 scale.
Output price
Muse Spark 1.3 $4.25 against Mistral Large 3 2512 $1.50 per million output tokens, 2.8x apart.
Context window
Muse Spark 1.3 takes 1.05M tokens, Mistral Large 3 2512 262K.

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 1.3BarsMistral Large 3 2512Ties
Coding20
Intelligence10
Agentic work10
Web design80
General20
All shared boards140
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
Coding benchmarks for Muse Spark 1.3 and Mistral Large 3 2512
BenchmarkMuse Spark 1.3Mistral Large 3 2512Leader
LiveBench coding90.2%Not measuredOnly Muse Spark 1.3 measured
LMArena WebDev1659Not measuredOnly Muse Spark 1.3 measured
AA Coding Index75.820.1Muse Spark 1.3
LiveCodeBench (Vals AI)Not measured55.3%Only Mistral Large 3 2512 measured
SWE-bench Verified (Vals AI)Not measured41.4%Only Mistral Large 3 2512 measured
Terminal-Bench 4 (Vals AI)10.6%Not measuredOnly Muse Spark 1.3 measured
Vibe Code Bench (Vals AI)82.9%Not measuredOnly Muse Spark 1.3 measured
Code migration (Vals AI)27.6%Not measuredOnly Muse Spark 1.3 measured
ProgramBench (Vals AI)0.5%Not measuredOnly Muse Spark 1.3 measured
IOI (Vals AI)43.9%Not measuredOnly Muse Spark 1.3 measured
Terminal-Bench 2.1 (Vals AI)72.3%Not measuredOnly Muse Spark 1.3 measured
CyberBench (Vals AI)69.4%Not measuredOnly Muse Spark 1.3 measured
SciCode59.7%Not measuredOnly Muse Spark 1.3 measured
FrontierSWE25.8%Not measuredOnly Muse Spark 1.3 measured
ALE-Bench1688.3264.7Muse Spark 1.3
LMArena Text: coding1510Not measuredOnly Muse Spark 1.3 measured
LMArena Text: software and IT1511Not measuredOnly Muse Spark 1.3 measured
LMArena WebDev: React1672Not measuredOnly Muse Spark 1.3 measured
LMArena WebDev: HTML1653Not measuredOnly Muse Spark 1.3 measured
LMArena WebDev: from an image1640Not measuredOnly Muse Spark 1.3 measured
Neither model has a result on the other 19 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Muse Spark 1.3 and Mistral Large 3 2512
BenchmarkMuse Spark 1.3Mistral Large 3 2512Leader
AA Intelligence Index48.19.3Muse 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 index10
Agentic work benchmarks for Muse Spark 1.3 and Mistral Large 3 2512
BenchmarkMuse Spark 1.3Mistral Large 3 2512Leader
AA Agentic Index55.51.0Muse Spark 1.3
Design Arena: agents building web apps1297Not measuredOnly Muse Spark 1.3 measured
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%Not measuredOnly Muse Spark 1.3 measured
LiveBench browser80.0%Not measuredOnly Muse Spark 1.3 measured
LiveBench long agentic40.4%Not measuredOnly Muse Spark 1.3 measured
Finance Agent (Vals AI)58.9%Not measuredOnly Muse Spark 1.3 measured
Tax Agent Bench (Vals AI)36.0%Not measuredOnly Muse Spark 1.3 measured
Legal Research Bench (Vals AI)40.9%Not measuredOnly Muse Spark 1.3 measured
Excel Modeling Benchmark (Vals AI)62.7%Not measuredOnly Muse Spark 1.3 measured
Terminal-Bench-Science (Vals AI)4.3%Not measuredOnly Muse Spark 1.3 measured
APEX-Agents58.6%Not measuredOnly Muse Spark 1.3 measured
Neither model has a result on the other 25 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index12 boards, none shared
Reasoning benchmarks for Muse Spark 1.3 and Mistral Large 3 2512
BenchmarkMuse Spark 1.3Mistral Large 3 2512Leader
GPQA DiamondNot measured68.4%Only Mistral Large 3 2512 measured
LiveBench reasoning89.7%Not measuredOnly Muse Spark 1.3 measured
MMMU Pro (Vals AI)Not measured66.2%Only Mistral Large 3 2512 measured
GPQA Diamond (Artificial Analysis run)94.1%Not measuredOnly Muse Spark 1.3 measured
Humanity's Last Exam (Artificial Analysis run)48.7%Not measuredOnly Muse Spark 1.3 measured
Chess puzzles37.0%Not measuredOnly Muse Spark 1.3 measured
Mystery game puzzles25.0%Not measuredOnly Muse Spark 1.3 measured
LMArena Text: hard prompts1503Not measuredOnly Muse Spark 1.3 measured
LMArena Text: expert1519Not measuredOnly Muse Spark 1.3 measured
LMArena Text: hard prompts in English1500Not measuredOnly Muse Spark 1.3 measured
LMArena Vision: diagrams1330Not measuredOnly Muse Spark 1.3 measured
LMArena Vision: homework1296Not measuredOnly Muse Spark 1.3 measured
Neither model has a result on the other 10 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Math benchmarks for Muse Spark 1.3 and Mistral Large 3 2512
BenchmarkMuse Spark 1.3Mistral Large 3 2512Leader
AIMENot measured42.9%Only Mistral Large 3 2512 measured
MGSM (Vals AI)Not measured85.4%Only Mistral Large 3 2512 measured
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%Not measuredOnly Muse Spark 1.3 measured
LMArena Text: math1497Not measuredOnly Muse Spark 1.3 measured
LMArena Text: mathematical work1491Not measuredOnly Muse Spark 1.3 measured
Neither model has a result on the other 5 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
Knowledge benchmarks for Muse Spark 1.3 and Mistral Large 3 2512
BenchmarkMuse Spark 1.3Mistral Large 3 2512Leader
MMLU ProNot measured79.8%Only Mistral Large 3 2512 measured
LegalBench (Vals AI)Not measured79.1%Only Mistral Large 3 2512 measured
CaseLaw (Vals AI)Not measured61.4%Only Mistral Large 3 2512 measured
CorpFin (Vals AI)Not measured61.0%Only Mistral Large 3 2512 measured
TaxEval (Vals AI)Not measured73.1%Only Mistral Large 3 2512 measured
MortgageTax (Vals AI)Not measured52.1%Only Mistral Large 3 2512 measured
MedQA (Vals AI)Not measured82.2%Only Mistral Large 3 2512 measured
LMArena Text: science1507Not measuredOnly Muse Spark 1.3 measured
LMArena Text: medicine and healthcare1493Not measuredOnly Muse Spark 1.3 measured
LMArena Text: legal and government1499Not measuredOnly Muse Spark 1.3 measured
LMArena Text: business and finance1490Not measuredOnly Muse Spark 1.3 measured
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Muse Spark 1.3 and Mistral Large 3 2512
BenchmarkMuse Spark 1.3Mistral Large 3 2512Leader
Design Arena: websites13561162Muse Spark 1.3
Design Arena: UI components13491099Muse Spark 1.3
Design Arena: game dev13281080Muse Spark 1.3
Design Arena: data viz13431136Muse Spark 1.3
Design Arena: 3D13581099Muse Spark 1.3
Design Arena: all code categories13521141Muse Spark 1.3
Design Arena: SVG1301992Muse Spark 1.3
Design Arena: ASCII art12781069Muse Spark 1.3
LiveBench design74.8%Not measuredOnly Muse Spark 1.3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index20
General benchmarks for Muse Spark 1.3 and Mistral Large 3 2512
BenchmarkMuse Spark 1.3Mistral Large 3 2512Leader
LiveBench data analysis79.6%Not measuredOnly Muse Spark 1.3 measured
SAGE (Vals AI)Not measured24.6%Only Mistral Large 3 2512 measured
Long context reasoning (AA-LCR)83.0%Not measuredOnly Muse Spark 1.3 measured
DTBench96.5%65.1%Muse Spark 1.3
LMCA53.9%16.7%Muse Spark 1.3
LMArena Text1490Not measuredOnly Muse Spark 1.3 measured
LMArena Text: instruction following1479Not measuredOnly Muse Spark 1.3 measured
LMArena Text: creative writing1462Not measuredOnly Muse Spark 1.3 measured
LMArena Vision1308Not measuredOnly Muse Spark 1.3 measured
LMArena Text: English1495Not measuredOnly Muse Spark 1.3 measured
LMArena Text: non-English1481Not measuredOnly Muse Spark 1.3 measured
LMArena Text: Chinese1532Not measuredOnly Muse Spark 1.3 measured
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: Russian1491Not measuredOnly Muse Spark 1.3 measured
LMArena Text: Polish1490Not measuredOnly Muse Spark 1.3 measured
LMArena Text: multi-turn1487Not measuredOnly Muse Spark 1.3 measured
LMArena Text: longer queries1488Not measuredOnly Muse Spark 1.3 measured
LMArena Text: writing and language1470Not measuredOnly Muse Spark 1.3 measured
LMArena Text: entertainment and media1457Not measuredOnly Muse Spark 1.3 measured
LMArena Vision: English1298Not measuredOnly Muse Spark 1.3 measured
LMArena Vision: Chinese1384Not measuredOnly Muse Spark 1.3 measured
LMArena Vision: reading text1319Not measuredOnly Muse Spark 1.3 measured
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 18 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 Mistral Large 3 2512
BenchmarkMuse Spark 1.3Mistral Large 3 2512Leader
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
Mistral Large 3 2512$0.0013Fits in one request

Mistral Large 3 2512 costs less

Repository review

50K input + 3K output tokens

Muse Spark 1.3$0.075Fits in one request
Mistral Large 3 2512$0.029Fits in one request

Mistral Large 3 2512 costs less

Agent loop

200K input + 10K output tokens

Muse Spark 1.3$0.292Fits in one request
Mistral Large 3 2512$0.115Fits in one request

Mistral Large 3 2512 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 Mistral Large 3 2512
SpecificationMeta Muse Spark 1.3Mistral Large 3 2512
MakerMetaMistral AI
WeightsNo public weights listedNo public weights listed
ReleasedSeptember 2, 2026December 1, 2025
Context window1.05M262K
Input $/Mtok$1.25$0.50
Output $/Mtok$4.25$1.50
Coding index57.4Not benchmarked
Independent measurements behind it41
Cost per solved taskNot computable$0.77
SourceOpenRouter listingOpenRouter listing

Questions

Is Muse Spark 1.3 better than Mistral Large 3 2512 for coding?

Only Muse Spark 1.3 has a coding score, 57.4 on the Vibe Coding Index; Mistral Large 3 2512 has none, so the two cannot be ranked on coding. Pick Mistral Large 3 2512 for output tokens 2.8x cheaper ($1.50 vs $4.25 per million).

Which is cheaper, Muse Spark 1.3 or Mistral Large 3 2512?

Muse Spark 1.3 costs $1.25 per million input tokens and $4.25 per million output tokens; Mistral Large 3 2512 costs $0.50 and $1.50. Cost per solved task is known for Mistral Large 3 2512 only.

Which has the bigger context window, Muse Spark 1.3 or Mistral Large 3 2512?

Muse Spark 1.3, with 1.05M tokens against 262K.

How many benchmarks is the Muse Spark 1.3 vs Mistral Large 3 2512 comparison based on?

14 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 Mistral Large 3 2512's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next