Compare / Muse Spark vs Muse Spark 1.3

Muse Spark vs Muse Spark 1.3

Which is cheaper, which is more capable, and which does better at each kind of work, from 14 results on 2 sources that measured both models.

MetaMuse Spark Released 8 Apr 2026 · Not on sale
MetaMuse Spark 1.3 Released 2 Sep 2026 · $1.25 in · $4.25 out
Muse Spark wins 05 too close to callMuse Spark 1.3 wins 9

Of the 14 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee).

Muse Spark or Muse Spark 1.3? The short answer

Pick Muse Spark 1.3: it scores higher (Intelligence Index 48.1 against 31.3) at about the same price.

  • Muse Spark 1.3 scores higher on the Artificial Analysis Intelligence Index: 48.1 against 31.3.
  • Muse Spark 1.3 is newer: released 2 Sep 2026, against 8 Apr 2026 for Muse Spark.
  • On third-party benchmarks, on the results both models have: Muse Spark 1.3 does better for agents and tool use, reasoning and knowledge and sticking to the facts.

Head to head

31.3
Intelligence Index
48.1

Every fact side by side

Muse SparkMuse Spark 1.3
Price per million tokensNot on sale$1.25 in · $4.25 out
Blended (3 in : 1 out)–$2.00
Cheapest host, blended––
Cached input, per million–$0.15 cached input
Intelligence Index31.348.1
Spring Prompt overall–59
Output speed, tokens a second–254
Context window–1,048,576 tokens
Released8 Apr 20262 Sep 2026 (newer)
WeightsClosedClosed
Developer based inthe USthe US

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Product listingsTurning a sparse product feed and photos into listings that can go live not measured 17 of 32
Decks from an analysisTurning a finished analysis into a deck you could present as it is not measured 25 of 32
Marketing planningPlanning a year of ad spend without overspending not measured 25 of 32
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 61 of 160 13 of 159
Professional workReal tasks from banking, consulting and law, business documents and freelance projects not measured 8 of 51
Reasoning and knowledgeHard questions across science, maths and general knowledge 58 of 188 11 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 12 of 170 7 of 169
Sticking to the factsSummarising without inventing things, and factual answers 23 of 140 11 of 139
Speed under pressureGood decisions against a real clock (fast chess) not measured 33 of 35

From our research

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureMuse SparkMuse Spark 1.3
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 12 · 8 of 387 measured 1,489 1,494max reasoning
Overall · Text factualityArena rating, higher is better 26 · 13 of 163 measured 1,468 1,480max reasoning
Business, management and finance · TextArena rating, higher is better 9 · 4 of 380 measured 1,489 1,505max reasoning
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 52 · 10 of 249 measured 31.3 48.1max reasoning
GPQA Diamond% of questions, higher is better 58 · 5 of 232 measured 88.4% 94.1%xhigh reasoning
Humanity's Last Exam% of questions, higher is better 44 · 13 of 250 measured 40.7% 48.7%max reasoning
Show all 14 results (8 more)
MeasureMuse SparkMuse Spark 1.3
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 5 results
Creative writing · TextArena rating, higher is better 18 · 22 of 385 measured 1,465 1,459max reasoning
Expert prompts · TextArena rating, higher is better 50 · 12 of 338 measured 1,492 1,529max reasoning
Instruction following · TextArena rating, higher is better 37 · 13 of 387 measured 1,465 1,486max reasoning
Overall · DocumentArena rating, higher is better 16 · 15 of 38 measured 1,467 1,468max reasoning
Writing, literature and language · TextArena rating, higher is better 26 · 19 of 386 measured 1,463 1,470max reasoning
Artificial Analysis reported by Artificial Analysis · 3 results
Terminal-Bench 2.1% of tasks, higher is better 45 · 11 of 131 measured 62.2% 85.4%xhigh reasoning
Artificial Analysis Coding Indexindex score, higher is better 42 · 7 of 130 measured 58.6 76.5xhigh reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 65 · 16 of 241 measured 78.0% 83.0%max reasoning

Quick answers

Is Muse Spark better than Muse Spark 1.3?

Pick Muse Spark 1.3: it scores higher (Intelligence Index 48.1 against 31.3) at about the same price.

Which is better for agents and tool use, Muse Spark or Muse Spark 1.3?

Muse Spark 1.3 ranks 13 of 160 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 61 for Muse Spark.

Which is better for reasoning and knowledge, Muse Spark or Muse Spark 1.3?

Muse Spark 1.3 ranks 11 of 188 models on sale for hard questions across science, maths and general knowledge, against 58 for Muse Spark.

Which is better for writing, Muse Spark or Muse Spark 1.3?

Muse Spark 1.3 ranks 7 of 170 models on sale for what people prefer in blind comparisons, and judged writing quality, against 12 for Muse Spark.

Which is better for sticking to the facts, Muse Spark or Muse Spark 1.3?

Muse Spark 1.3 ranks 11 of 140 models on sale for summarising without inventing things, and factual answers, against 23 for Muse Spark.

Run Muse Spark and Muse Spark 1.3 on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.