Models / Muse Spark

Meta

Muse Spark

Muse Spark is best for writing and sticking to the facts; it is not on sale through OpenRouter, so it is here for reference.

Superseded. Muse Spark 1.3 is Meta's newer model in this line, at $2.00 blended: see Muse Spark 1.3 or compare the two.

Results 16 Nov 2026 · 17 results · 2 sources

Price per million tokens
Not available through OpenRouter
Speed
Not measured
Intelligence Index
31.3
Artificial Analysis
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Meta, based in the US
Weights not published
Released
8 Apr 2026

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 50th of 186Claude Opus 5.5 – – –
Models from developers based in the US 34th of 93Claude Opus 5.5 – – –

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 61st of 160 available
BenchmarkMuse SparkRank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 62.2% 43rd of 108 Claude Fable 5.1 91.4%
  • tau2-bench: has not measured this model.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • OpenHands Index: has not measured this model.
  • Microsoft STATE-Bench: has not measured this model.
  • Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects Not measured
  • APEX-Agents: has not measured this model.
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 58th of 188 available
BenchmarkMuse SparkRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 31.3 50th of 186 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 40.7% 43rd of 187 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 88.4% 53rd of 169 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 12th of 170 available
BenchmarkMuse SparkRank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,489 12th of 154 Gemini 4 Argon 1,525
  • UGI Leaderboard: has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers 23rd of 140 available
BenchmarkMuse SparkRank among availableBest available
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,468 23rd of 110 Gemini 4 Argon 1,511
  • Vectara Hallucination Leaderboard: has not measured this model.
  • SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against Muse Spark, Intelligence Index 31.3. "Similar intelligence" means within 4 points or better.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

Muse SparkClaude Opus 5.5
most intelligent available today
Claude Fable 5.2
leads overall
Muse Wonder
Meta's best other model
GPT-6.1 Sol
near the top overall
Price per million tokens – $8.00$16.00$8.00$4.00
Tokens a second – 96–15353
Intelligence Index 31.3 57.6–52.451.8
Spring Prompt overall – 82907080
Rank among available models, by use case
Product listings – 13th5th5th2nd
Decks from an analysis – 7th4th13th5th
User surveys – 4th1st2nd3rd
Marketing planning – 9th1st22nd–
Agents and tool use 61st of 160 3rd–11th6th
Professional work – 3rd––9th
Reasoning and knowledge 58th of 188 1st–8th6th
Writing 12th of 170 5th––17th
Sticking to the facts 23rd of 140 3rd––20th
Speed under pressure – –8th14th3rd

Shaded figures are better than Muse Spark's. A dash means no result.

Where it has been measured

Compared with the models available today (it is not on sale itself), in the top quarter (by percentile) for writing and sticking to the facts.

Artificial Analysis lists it but has not published a speed for it yet

Every result

17 published results from 2 sources, each in the source's own units, with the configuration that produced it.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 8 results
MeasureValueRankConfigurationDated
Arena Document: overallArena rating, higher is better 1,467
1,449–1,486
20 of 44 Muse Spark 13 Sep 2026
Arena Text factuality: overallArena rating, higher is better 1,468
1,462–1,473
31 of 182 Muse Spark 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,489
1,478–1,501
11 of 406 Muse Spark 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,465
1,452–1,479
21 of 411 Muse Spark 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,492
1,476–1,508
57 of 363 Muse Spark 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,465
1,456–1,474
44 of 413 Muse Spark 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,489
1,484–1,495
15 of 413 Muse Spark 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,463
1,452–1,473
33 of 412 Muse Spark 2 Oct 2026

Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Artificial Analysis · reported by Artificial Analysis · 9 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 58.6 78 of 187 Muse Spark 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 31.3 109 of 413 Muse Spark 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 88.4% 92 of 360 Muse Spark 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 40.7% 84 of 419 Muse Spark 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 75.9% 21 of 288 Muse Spark 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 78.0% 117 of 407 Muse Spark 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 62.2% 84 of 188 Muse Spark 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 45.5% 33 of 282 Muse Spark 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 91.5% 51 of 286 Muse Spark 20 Oct 2026

Not shown: Not your codebase or tools.

Test your own prompt.

Benchmarks aren't your task. Run your prompt on the models you could use, with every answer checked and costed.