Enter opens the highlighted result. Esc closes.

Muse Spark 1.2 vs Inkling Small

Muse Spark 1.2 leads Inkling Small on coding, 55.7 to 27.3 on the Vibe Coding Index, and Inkling Small costs 3.5x less per output token ($1.20 vs $4.25 per million). Updated October 22, 2026; 65 benchmarks have a result for both.

Replace Muse Spark 1.2 Replace Inkling Small
Muse Spark 1.2Meta
Coding
55.7
Overall
60.4
Output $/M
$4.25
64
T Inkling SmallThinking Machines
Coding
27.3
Overall
43.6
Output $/M
$1.20
0
vs boards won of 65 shared, 1 tied

Muse Spark 1.2 or Inkling Small: which to pick

Pick Muse Spark 1.2 for coding: it scores 55.7 on the Vibe Coding Index against 27.3 for Inkling Small.

Pick Inkling Small for output tokens 3.5x cheaper ($1.20 vs $4.25 per million) and a lower cost per solved task ($0.16 against $0.64).

Model AMuse Spark 1.2Meta55.7/1005 independent benchmarks$0.64 per solved taskModel BInkling SmallThinking Machines27.3/1004 independent benchmarks$0.16 per solved task
Shared results
65
Muse Spark 1.2 only
32
Inkling Small only
19
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 1.2 55.7 from 5 benchmarks, Inkling Small 27.3 from 4 benchmarks.
Widest category
Agentic work, 20.0 points apart on average over 5 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Muse Spark 1.2 79.1% against Inkling Small 19.1%, 60.0 points apart on a 0 to 100 scale.
Output price
Muse Spark 1.2 $4.25 against Inkling Small $1.20 per million output tokens, 3.5x apart.
Context window
Muse Spark 1.2 takes 1.05M tokens, Inkling Small 524K.

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 1.2BarsInkling SmallTies
Coding1501 tie
Intelligence20
Agentic work50
Reasoning60
Math30
Knowledge110
General220
All shared boards6401 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index150
Coding benchmarks for Muse Spark 1.2 and Inkling Small
BenchmarkMuse Spark 1.2Inkling SmallLeader
LiveBench coding78.2%Not measuredOnly Muse Spark 1.2 measured
LMArena WebDev15341409Muse Spark 1.2
AA Coding Index72.252.9Muse Spark 1.2
LiveCodeBench (Vals AI)Not measured85.9%Only Inkling Small measured
SWE-bench Verified (Vals AI)86.6%82.2%Muse Spark 1.2
Terminal-Bench 4 (Vals AI)6.1%0.0%Muse Spark 1.2
Vibe Code Bench (Vals AI)79.1%19.1%Muse Spark 1.2
Code migration (Vals AI)29.9%13.7%Muse Spark 1.2
ProgramBench (Vals AI)0.5%0.5%Tie
IOI (Vals AI)21.8%9.3%Muse Spark 1.2
Terminal-Bench 2.1 (Vals AI)69.7%55.1%Muse Spark 1.2
SkillsBench (Vals AI)53.0%33.6%Muse Spark 1.2
CyberBench (Vals AI)69.5%64.1%Muse Spark 1.2
SciCode57.4%49.7%Muse Spark 1.2
FrontierSWE12.0%Not measuredOnly Muse Spark 1.2 measured
WeirdML60.3%Not measuredOnly Muse Spark 1.2 measured
LMArena Text: coding15051450Muse Spark 1.2
LMArena Text: software and IT15051447Muse Spark 1.2
LMArena WebDev: React15261399Muse Spark 1.2
LMArena WebDev: HTML15431398Muse Spark 1.2
LMArena WebDev: from an imageNot measured1410Only Inkling Small measured
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Muse Spark 1.2 and Inkling Small
BenchmarkMuse Spark 1.2Inkling SmallLeader
AA Intelligence Index39.625.7Muse Spark 1.2
Epoch Capabilities Index155.1150.3Muse Spark 1.2
Agentic workLike-for-likePublic boards, shown as published, kept out of the index50
Agentic work benchmarks for Muse Spark 1.2 and Inkling Small
BenchmarkMuse Spark 1.2Inkling SmallLeader
AA Agentic Index43.223.5Muse Spark 1.2
Design Arena: agents building web apps1221Not measuredOnly Muse Spark 1.2 measured
Design Arena: agents building full-stack apps1210Not measuredOnly Muse Spark 1.2 measured
Design Arena: agents building mobile apps1181Not measuredOnly Muse Spark 1.2 measured
Design Arena: agents building Android apps1222Not measuredOnly Muse Spark 1.2 measured
Design Arena: agents building games1179Not measuredOnly Muse Spark 1.2 measured
Design Arena: HTML slides1085Not measuredOnly Muse Spark 1.2 measured
Design Arena: PowerPoint slides1172Not measuredOnly Muse Spark 1.2 measured
LiveBench research67.7%Not measuredOnly Muse Spark 1.2 measured
LiveBench browser36.0%Not measuredOnly Muse Spark 1.2 measured
LiveBench long agentic21.3%Not measuredOnly Muse Spark 1.2 measured
SREBench (Vals AI)0.0%Not measuredOnly Muse Spark 1.2 measured
Finance Agent (Vals AI)60.6%41.3%Muse Spark 1.2
Tax Agent Bench (Vals AI)32.8%15.4%Muse Spark 1.2
Legal Research Bench (Vals AI)43.8%25.5%Muse Spark 1.2
Harvey's Legal Agent Benchmark (Vals AI)Not measured2.9%Only Inkling Small measured
Excel Modeling Benchmark (Vals AI)57.0%31.8%Muse Spark 1.2
BioMysteryBench (Vals AI)64.8%Not measuredOnly Muse Spark 1.2 measured
APEX-Agents45.4%Not measuredOnly Muse Spark 1.2 measured
Neither model has a result on the other 22 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
Reasoning benchmarks for Muse Spark 1.2 and Inkling Small
BenchmarkMuse Spark 1.2Inkling SmallLeader
GPQA DiamondNot measured83.6%Only Inkling Small measured
LiveBench reasoning90.0%Not measuredOnly Muse Spark 1.2 measured
MMMU Pro (Vals AI)86.1%Not measuredOnly Muse Spark 1.2 measured
GPQA Diamond (Artificial Analysis run)90.4%89.5%Muse Spark 1.2
Humanity's Last Exam (Artificial Analysis run)45.5%33.3%Muse Spark 1.2
GPQA Diamond (Epoch AI run)Not measured88.5%Only Inkling Small measured
ARC-AGINot measured84.0%Only Inkling Small measured
ARC-AGI-2Not measured40.1%Only Inkling Small measured
SimpleBench74.5%Not measuredOnly Muse Spark 1.2 measured
Chess puzzles27.0%Not measuredOnly Muse Spark 1.2 measured
Mystery game puzzlesNot measured6.0%Only Inkling Small measured
LMArena Text: hard prompts14891423Muse Spark 1.2
LMArena Text: expert14751441Muse Spark 1.2
LMArena Text: hard prompts in English14871429Muse Spark 1.2
LMArena Vision: diagrams13171251Muse Spark 1.2
LMArena Vision: homeworkNot measured1257Only Inkling Small measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for Muse Spark 1.2 and Inkling Small
BenchmarkMuse Spark 1.2Inkling SmallLeader
OTIS Mock AIMENot measured90.0%Only Inkling Small measured
FrontierMath, tiers 1 to 3Not measured46.3%Only Inkling Small measured
FrontierMath, tier 4Not measured17.1%Only Inkling Small measured
ProofBench43.0%6.0%Muse Spark 1.2
LMArena Text: math14841459Muse Spark 1.2
LMArena Text: mathematical work14801441Muse Spark 1.2
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index110
Knowledge benchmarks for Muse Spark 1.2 and Inkling Small
BenchmarkMuse Spark 1.2Inkling SmallLeader
MMLU Pro88.3%85.6%Muse Spark 1.2
LegalBench (Vals AI)85.3%83.0%Muse Spark 1.2
CorpFin (Vals AI)70.9%69.6%Muse Spark 1.2
TaxEval (Vals AI)80.4%75.5%Muse Spark 1.2
MortgageTax (Vals AI)65.4%62.3%Muse Spark 1.2
MedCode (Vals AI)49.4%37.9%Muse Spark 1.2
SimpleQA Verified60.3%19.1%Muse Spark 1.2
LMArena Text: science15001428Muse Spark 1.2
LMArena Text: medicine and healthcare14961413Muse Spark 1.2
LMArena Text: legal and government15171415Muse Spark 1.2
LMArena Text: business and finance14841413Muse Spark 1.2
Neither model has a result on the other 7 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for Muse Spark 1.2 and Inkling Small
BenchmarkMuse Spark 1.2Inkling SmallLeader
Design Arena: websites1312Not measuredOnly Muse Spark 1.2 measured
Design Arena: UI components1298Not measuredOnly Muse Spark 1.2 measured
Design Arena: game dev1301Not measuredOnly Muse Spark 1.2 measured
Design Arena: data viz1334Not measuredOnly Muse Spark 1.2 measured
Design Arena: 3D1301Not measuredOnly Muse Spark 1.2 measured
Design Arena: all code categories1312Not measuredOnly Muse Spark 1.2 measured
Design Arena: SVG1284Not measuredOnly Muse Spark 1.2 measured
Design Arena: ASCII art1284Not measuredOnly Muse Spark 1.2 measured
LiveBench design67.1%Not measuredOnly Muse Spark 1.2 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index220
General benchmarks for Muse Spark 1.2 and Inkling Small
BenchmarkMuse Spark 1.2Inkling SmallLeader
Vals IndexNot measured27.6%Only Inkling Small measured
LiveBench data analysis76.5%Not measuredOnly Muse Spark 1.2 measured
Public Benefits Bench (Vals AI)68.5%59.4%Muse Spark 1.2
SAGE (Vals AI)47.7%32.7%Muse Spark 1.2
MedScribe (Vals AI)90.1%84.1%Muse Spark 1.2
Vals Multimodal Index69.8%50.0%Muse Spark 1.2
Long context reasoning (AA-LCR)79.0%75.7%Muse Spark 1.2
DTBench94.7%Not measuredOnly Muse Spark 1.2 measured
LMCA48.4%Not measuredOnly Muse Spark 1.2 measured
LMArena Text14821413Muse Spark 1.2
LMArena Text: instruction following14621399Muse Spark 1.2
LMArena Text: creative writing14361334Muse Spark 1.2
LMArena Vision13041237Muse Spark 1.2
LMArena Text: English14831421Muse Spark 1.2
LMArena Text: non-English14761401Muse Spark 1.2
LMArena Text: Chinese15091464Muse Spark 1.2
LMArena Text: GermanNot measured1408Only Inkling Small measured
LMArena Text: JapaneseNot measured1401Only Inkling Small measured
LMArena Text: Korean14621367Muse Spark 1.2
LMArena Text: French14951435Muse Spark 1.2
LMArena Text: Spanish14841422Muse Spark 1.2
LMArena Text: Russian14831394Muse Spark 1.2
LMArena Text: PolishNot measured1428Only Inkling Small measured
LMArena Text: multi-turn15021416Muse Spark 1.2
LMArena Text: longer queries14731402Muse Spark 1.2
LMArena Text: writing and language14531357Muse Spark 1.2
LMArena Text: entertainment and media14431352Muse Spark 1.2
LMArena Vision: English12911243Muse Spark 1.2
LMArena Vision: ChineseNot measured1292Only Inkling Small measured
LMArena Vision: reading text13131243Muse Spark 1.2
LMArena Vision: humorNot measured1207Only Inkling Small measured
LMArena Vision: creative writingNot measured1205Only Inkling Small measured
Neither model has a result on the other 14 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Muse Spark 1.2 and Inkling Small
BenchmarkMuse Spark 1.2Inkling SmallLeader
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 1.2$0.0034Fits in one request
Inkling Small$0.0010Fits in one request

Inkling Small costs less

Repository review

50K input + 3K output tokens

Muse Spark 1.2$0.075Fits in one request
Inkling Small$0.026Fits in one request

Inkling Small costs less

Agent loop

200K input + 10K output tokens

Muse Spark 1.2$0.292Fits in one request
Inkling Small$0.102Fits in one request

Inkling Small 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 1.2 and Inkling Small
SpecificationMeta Muse Spark 1.2Thinking Machines Inkling Small
MakerMetaThinking Machines
WeightsNo public weights listedOpen weights
ReleasedAugust 5, 2026July 30, 2026
Context window1.05M524K
Input $/Mtok$1.25$0.45
Output $/Mtok$4.25$1.20
Coding index55.727.3
Independent measurements behind it54
Cost per solved task$0.64$0.16
SourceOpenRouter listingOpenRouter listing

Questions

Is Muse Spark 1.2 better than Inkling Small for coding?

Pick Muse Spark 1.2 for coding: it scores 55.7 on the Vibe Coding Index against 27.3 for Inkling Small. Pick Inkling Small for output tokens 3.5x cheaper ($1.20 vs $4.25 per million) and a lower cost per solved task ($0.16 against $0.64).

Which is cheaper, Muse Spark 1.2 or Inkling Small?

Muse Spark 1.2 costs $1.25 per million input tokens and $4.25 per million output tokens; Inkling Small costs $0.45 and $1.20. Per solved SWE-bench Verified task, Muse Spark 1.2 costs $0.64 and Inkling Small $0.16.

Which has the bigger context window, Muse Spark 1.2 or Inkling Small?

Muse Spark 1.2, with 1.05M tokens against 524K.

How many benchmarks is the Muse Spark 1.2 vs Inkling Small comparison based on?

65 benchmarks have a result for both models as of October 22, 2026. Muse Spark 1.2's coding index rests on 5 independent benchmarks and Inkling Small'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-1-2-vs-thinkingmachines-inkling-small" title="Muse Spark 1.2 vs Inkling Small, 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-1-2-vs-thinkingmachines-inkling-small">LLMBenchmark.ai, Muse Spark 1.2 vs Inkling Small</a></p>