Enter opens the highlighted result. Esc closes.

gpt-oss-20b vs Muse Spark 1.3

Muse Spark 1.3 leads gpt-oss-20b on the Artificial Analysis Intelligence Index, 48.1 to 10.0, and gpt-oss-20b costs 28.3x less per output token ($0.15 vs $4.25 per million). Updated October 23, 2026; 40 benchmarks have a result for both.

Replace gpt-oss-20b Replace Muse Spark 1.3
gpt-oss-20bOpenAI
Coding
No data
Overall
38.5
Output $/M
$0.15
0
Muse Spark 1.3Meta
Coding
57.4
Overall
68.6
Output $/M
$4.25
40
vs boards won of 40 shared

gpt-oss-20b or Muse Spark 1.3: which to pick

Only Muse Spark 1.3 has a coding score, 57.4 on the Vibe Coding Index; gpt-oss-20b has none, so the two cannot be ranked on coding.

Pick gpt-oss-20b for output tokens 28.3x cheaper ($0.15 vs $4.25 per million).

Model Agpt-oss-20bOpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BMuse Spark 1.3Meta57.4/1004 independent benchmarksNo cost per solved task
Shared results
40
gpt-oss-20b only
23
Muse Spark 1.3 only
56
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
gpt-oss-20b not benchmarked, Muse Spark 1.3 57.4 from 4 benchmarks.
Widest category
Web design, 57.1 points apart on average over 2 shared benchmarks.
Widest single gap
Design Arena: websites: gpt-oss-20b 852 against Muse Spark 1.3 1356, 63.0 points apart on a 0 to 100 scale.
Output price
gpt-oss-20b $0.15 against Muse Spark 1.3 $4.25 per million output tokens, 28.3x apart.
Context window
gpt-oss-20b takes 131K tokens, Muse Spark 1.3 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
Categorygpt-oss-20bBarsMuse Spark 1.3Ties
Coding04
Intelligence02
Reasoning05
Math04
Knowledge04
Web design02
General019
All shared boards040
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for gpt-oss-20b and Muse Spark 1.3
Benchmarkgpt-oss-20bMuse Spark 1.3Leader
LiveBench codingNot measured90.2%Only Muse Spark 1.3 measured
LMArena WebDevNot measured1657Only Muse Spark 1.3 measured
AA Coding IndexNot measured75.8Only Muse Spark 1.3 measured
LiveCodeBench (Vals AI)80.4%Not measuredOnly gpt-oss-20b measured
Terminal-Bench 4 (Vals AI)Not measured10.6%Only Muse Spark 1.3 measured
Vibe Code Bench (Vals AI)Not measured82.9%Only Muse Spark 1.3 measured
Code migration (Vals AI)Not measured27.6%Only Muse Spark 1.3 measured
ProgramBench (Vals AI)Not measured0.5%Only Muse Spark 1.3 measured
IOI (Vals AI)Not measured43.9%Only Muse Spark 1.3 measured
Terminal-Bench 2.1 (Vals AI)Not measured72.3%Only Muse Spark 1.3 measured
CyberBench (Vals AI)Not measured69.4%Only Muse Spark 1.3 measured
LiveCodeBench (Artificial Analysis run)77.7%Not measuredOnly gpt-oss-20b measured
SciCode38.9%59.7%Muse Spark 1.3
Terminal-Bench Hard (Artificial Analysis run)10.6%Not measuredOnly gpt-oss-20b measured
Terminal-Bench3.4%Not measuredOnly gpt-oss-20b measured
FrontierSWENot measured25.8%Only Muse Spark 1.3 measured
WeirdML40.9%Not measuredOnly gpt-oss-20b measured
ALE-Bench566.01688.3Muse Spark 1.3
LMArena Text: coding13061511Muse Spark 1.3
LMArena Text: software and IT13111511Muse Spark 1.3
LMArena WebDev: ReactNot measured1671Only Muse Spark 1.3 measured
LMArena WebDev: HTMLNot measured1653Only Muse Spark 1.3 measured
LMArena WebDev: from an imageNot measured1640Only Muse Spark 1.3 measured
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for gpt-oss-20b and Muse Spark 1.3
Benchmarkgpt-oss-20bMuse Spark 1.3Leader
AA Intelligence Index10.048.1Muse Spark 1.3
Epoch Capabilities Index137.7157.2Muse Spark 1.3
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index18 boards, none shared
Agentic work benchmarks for gpt-oss-20b and Muse Spark 1.3
Benchmarkgpt-oss-20bMuse Spark 1.3Leader
AA Agentic IndexNot measured55.5Only Muse Spark 1.3 measured
Design Arena: agents building web appsNot measured1297Only Muse Spark 1.3 measured
Design Arena: agents building full-stack appsNot measured1295Only Muse Spark 1.3 measured
Design Arena: agents building mobile appsNot measured1218Only Muse Spark 1.3 measured
Design Arena: agents building Godot gamesNot measured1241Only Muse Spark 1.3 measured
Design Arena: PowerPoint slidesNot measured1210Only Muse Spark 1.3 measured
Design Arena: spreadsheetsNot measured1075Only Muse Spark 1.3 measured
LiveBench researchNot measured68.6%Only Muse Spark 1.3 measured
LiveBench browserNot measured80.0%Only Muse Spark 1.3 measured
LiveBench long agenticNot measured40.4%Only Muse Spark 1.3 measured
Finance Agent (Vals AI)Not measured58.9%Only Muse Spark 1.3 measured
Tax Agent Bench (Vals AI)Not measured36.0%Only Muse Spark 1.3 measured
Legal Research Bench (Vals AI)Not measured40.9%Only Muse Spark 1.3 measured
Excel Modeling Benchmark (Vals AI)Not measured62.7%Only Muse Spark 1.3 measured
Terminal-Bench-Science (Vals AI)Not measured4.3%Only Muse Spark 1.3 measured
τ²-Bench Telecom60.2%Not measuredOnly gpt-oss-20b measured
APEX-AgentsNot measured58.6%Only Muse Spark 1.3 measured
BrowseComp-Plus50.6%Not measuredOnly gpt-oss-20b measured
Neither model has a result on the other 24 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for gpt-oss-20b and Muse Spark 1.3
Benchmarkgpt-oss-20bMuse Spark 1.3Leader
GPQA Diamond68.9%Not measuredOnly gpt-oss-20b measured
LiveBench reasoningNot measured89.7%Only Muse Spark 1.3 measured
GPQA Diamond (Artificial Analysis run)68.8%94.1%Muse Spark 1.3
Humanity's Last Exam (Artificial Analysis run)11.0%48.7%Muse Spark 1.3
GPQA Diamond (Epoch AI run)60.8%Not measuredOnly gpt-oss-20b measured
Chess puzzlesNot measured37.0%Only Muse Spark 1.3 measured
Mystery game puzzlesNot measured25.0%Only Muse Spark 1.3 measured
LMArena Text: hard prompts12741504Muse Spark 1.3
LMArena Text: expert12581515Muse Spark 1.3
LMArena Text: hard prompts in English12921501Muse Spark 1.3
LMArena Vision: diagramsNot measured1330Only Muse Spark 1.3 measured
LMArena Vision: homeworkNot measured1296Only Muse Spark 1.3 measured
Kagi LLM Benchmark53.2%Not measuredOnly gpt-oss-20b measured
Humanity's Last Exam (Scale run)Not measured25.4%Only Muse Spark 1.3 measured
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index04
Math benchmarks for gpt-oss-20b and Muse Spark 1.3
Benchmarkgpt-oss-20bMuse Spark 1.3Leader
AIME86.0%Not measuredOnly gpt-oss-20b measured
MATH 500 (Vals AI)94.2%Not measuredOnly gpt-oss-20b measured
MGSM (Vals AI)89.0%Not measuredOnly gpt-oss-20b measured
AA Math Index89.3Not measuredOnly gpt-oss-20b measured
AIME 2025 (Artificial Analysis run)89.3%Not measuredOnly gpt-oss-20b measured
OTIS Mock AIME65.3%99.2%Muse Spark 1.3
FrontierMath, tiers 1 to 3Not measured74.4%Only Muse Spark 1.3 measured
FrontierMath, tier 4Not measured46.3%Only Muse Spark 1.3 measured
ProofBenchNot measured58.0%Only Muse Spark 1.3 measured
LMArena Text: math13171502Muse Spark 1.3
LMArena Text: mathematical work13051493Muse Spark 1.3
MathArena12.8%43.0%Muse Spark 1.3
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for gpt-oss-20b and Muse Spark 1.3
Benchmarkgpt-oss-20bMuse Spark 1.3Leader
MMLU Pro71.6%Not measuredOnly gpt-oss-20b measured
LegalBench (Vals AI)70.8%Not measuredOnly gpt-oss-20b measured
CaseLaw (Vals AI)43.8%Not measuredOnly gpt-oss-20b measured
CorpFin (Vals AI)53.1%Not measuredOnly gpt-oss-20b measured
TaxEval (Vals AI)63.7%Not measuredOnly gpt-oss-20b measured
MedQA (Vals AI)82.9%Not measuredOnly gpt-oss-20b measured
MMLU Pro (Artificial Analysis run)74.8%Not measuredOnly gpt-oss-20b measured
LMArena Text: science12961506Muse Spark 1.3
LMArena Text: medicine and healthcare13101493Muse Spark 1.3
LMArena Text: legal and government12801499Muse Spark 1.3
LMArena Text: business and finance12831489Muse Spark 1.3
PRBench FinanceNot measured59.5%Only Muse Spark 1.3 measured
PRBench LegalNot measured61.6%Only 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 index02
Web design benchmarks for gpt-oss-20b and Muse Spark 1.3
Benchmarkgpt-oss-20bMuse Spark 1.3Leader
Design Arena: websites8521356Muse Spark 1.3
Design Arena: UI componentsNot measured1350Only Muse Spark 1.3 measured
Design Arena: game devNot measured1328Only Muse Spark 1.3 measured
Design Arena: data viz9331343Muse Spark 1.3
Design Arena: 3DNot measured1364Only Muse Spark 1.3 measured
Design Arena: all code categoriesNot measured1351Only Muse Spark 1.3 measured
Design Arena: SVGNot measured1301Only Muse Spark 1.3 measured
Design Arena: ASCII artNot measured1279Only Muse Spark 1.3 measured
LiveBench designNot measured74.8%Only Muse Spark 1.3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index019
General benchmarks for gpt-oss-20b and Muse Spark 1.3
Benchmarkgpt-oss-20bMuse Spark 1.3Leader
LiveBench data analysisNot measured79.6%Only Muse Spark 1.3 measured
IFBench65.1%Not measuredOnly gpt-oss-20b measured
Long context reasoning (AA-LCR)34.7%83.0%Muse Spark 1.3
DTBench68.0%96.5%Muse Spark 1.3
LMCA14.5%53.9%Muse Spark 1.3
LMArena Text12871491Muse Spark 1.3
LMArena Text: instruction following12361479Muse Spark 1.3
LMArena Text: creative writing12011462Muse Spark 1.3
LMArena VisionNot measured1308Only Muse Spark 1.3 measured
LMArena Text: English13031496Muse Spark 1.3
LMArena Text: non-English12681482Muse Spark 1.3
LMArena Text: Chinese13151529Muse Spark 1.3
LMArena Text: German12551513Muse Spark 1.3
LMArena Text: Japanese12441465Muse Spark 1.3
LMArena Text: Korean12341494Muse Spark 1.3
LMArena Text: FrenchNot measured1516Only Muse Spark 1.3 measured
LMArena Text: Spanish12671493Muse Spark 1.3
LMArena Text: Russian12781494Muse Spark 1.3
LMArena Text: Polish12521487Muse Spark 1.3
LMArena Text: multi-turn12681489Muse Spark 1.3
LMArena Text: longer queries12501489Muse Spark 1.3
LMArena Text: writing and language12381470Muse Spark 1.3
LMArena Text: entertainment and media12161458Muse Spark 1.3
LMArena Vision: EnglishNot measured1298Only Muse Spark 1.3 measured
LMArena Vision: ChineseNot measured1384Only Muse Spark 1.3 measured
LMArena Vision: reading textNot measured1319Only Muse Spark 1.3 measured
LMArena Vision: humorNot measured1293Only Muse Spark 1.3 measured
LMArena Vision: creative writingNot measured1296Only Muse Spark 1.3 measured
Neither model has a result on the other 20 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for gpt-oss-20b and Muse Spark 1.3
Benchmarkgpt-oss-20bMuse Spark 1.3Leader
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

gpt-oss-20b$0.0001Fits in one request
Muse Spark 1.3$0.0034Fits in one request

gpt-oss-20b costs less

Repository review

50K input + 3K output tokens

gpt-oss-20b$0.0019Fits in one request
Muse Spark 1.3$0.075Fits in one request

gpt-oss-20b costs less

Agent loop

200K input + 10K output tokens

gpt-oss-20b$0.0075Exceeds the context window
Muse Spark 1.3$0.292Fits in one request

gpt-oss-20b 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 gpt-oss-20b and Muse Spark 1.3
SpecificationOpenAI gpt-oss-20bMeta Muse Spark 1.3
MakerOpenAIMeta
WeightsOpen weightsNo public weights listed
ReleasedAugust 5, 2025September 2, 2026
Context window131K1.05M
Input $/Mtok$0.03$1.25
Output $/Mtok$0.15$4.25
Coding indexNot benchmarked57.4
Independent measurements behind it04
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is gpt-oss-20b better than Muse Spark 1.3 for coding?

Only Muse Spark 1.3 has a coding score, 57.4 on the Vibe Coding Index; gpt-oss-20b has none, so the two cannot be ranked on coding. Pick gpt-oss-20b for output tokens 28.3x cheaper ($0.15 vs $4.25 per million).

Which is cheaper, gpt-oss-20b or Muse Spark 1.3?

gpt-oss-20b costs $0.03 per million input tokens and $0.15 per million output tokens; Muse Spark 1.3 costs $1.25 and $4.25. Cost per solved task is known for neither of them.

Which has the bigger context window, gpt-oss-20b or Muse Spark 1.3?

Muse Spark 1.3, with 1.05M tokens against 131K.

How many benchmarks is the gpt-oss-20b vs Muse Spark 1.3 comparison based on?

40 benchmarks have a result for both models as of October 23, 2026. gpt-oss-20b's coding index rests on 0 independent benchmarks and Muse Spark 1.3's on 4. Where only one model has a result, the page says so instead of naming a winner.

Compare next