Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d66, 14 pendingSources1,015

Muse Spark 1.1

MetaReleased Jul 9, 2026Current

Score basis

Muse Spark 1.1 is strong in factuality; capable in long context, reasoning, agentic tasks, and coding; and behind the leaders in instruction following and math. Too few results yet to rate safety, multimodal tasks, or multilingual tasks.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.

Strong1 capability
  1. Factuality−7.9%3 of 4
Capable4 capabilities
  1. Long Context−15.5%1 of 3
  2. Reasoning−16.8%4 of 6
  3. Agentic−17.1%5 of 7
  4. Coding−20.2%6 of 10
Limited2 capabilities
  1. Instruction Following−31.2%2 of 3
  2. Math−41.0%3 of 5
Not rated3 capabilities

Too few results yet to rate Safety, Multimodal or Multilingual.

Price

$1.25input$4.25outputper million tokens

From Artificial Analysis · 3 providers tracked · All prices

Costs more than 71% of 330 priced models · 3:1 input-to-output blend, log scale

Evidence

56results on50benchmarks

  • 14 independently verified
  • 15 aggregator
  • 27 vendor-reported

From 11 sources · latest Oct 8, 2026 · How verification works

API features

Tool callingStructured outputsReasoning

As listed by OpenRouter

Research

1 paper reference Muse Spark 1.1

Muse Spark 1.1 benchmark results

56 results on 50 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Factuality

StrongFull factuality ranking

7.9% behind the leader3 of 4 ranked benchmarks measured

Long Context

CapableFull long context ranking

15.5% behind the leader1 of 3 ranked benchmarks measured

Reasoning

CapableFull reasoning ranking

16.8% behind the leader4 of 6 ranked benchmarks measured

Show 2 more reasoning resultsHide 2 reasoning results

Agentic

CapableFull agentic ranking

17.1% behind the leader5 of 7 ranked benchmarks measured

Show 1 more agentic resultHide 1 agentic result

Coding

CapableFull coding ranking

20.2% behind the leader6 of 10 ranked benchmarks measured

Show 2 more coding resultsHide 2 coding results

Instruction Following

LimitedFull instruction following ranking

31.2% behind the leader2 of 3 ranked benchmarks measured

Math

LimitedFull math ranking

41.0% behind the leader3 of 5 ranked benchmarks measured

Multimodal

Not enough dataFull multimodal ranking

0 of 6 ranked benchmarks measured

More results

Benchmarks outside the capability baskets. They are not ranked against a leader.

Show 21 more resultsHide 21 results

Muse Spark 1.1: common questions

Who makes Muse Spark 1.1?

Muse Spark 1.1 is made by Meta.

When was Muse Spark 1.1 released?

Muse Spark 1.1 was released on Jul 9, 2026, according to Artificial Analysis.

What is Muse Spark 1.1 good at?

Muse Spark 1.1 is strong in factuality; capable in long context, reasoning, agentic tasks, and coding; and behind the leaders in instruction following and math. Too few results yet to rate safety, multimodal tasks, or multilingual tasks.

How much does Muse Spark 1.1 cost?

Muse Spark 1.1 costs $1.25 per million input tokens and $4.25 per million output tokens, according to Artificial Analysis. We track its price at 3 providers. At a mix of three input tokens to one output token, it costs more than 71% of the 330 priced models we track.

How many benchmarks has Muse Spark 1.1 been tested on?

We track 56 results for Muse Spark 1.1 on 50 benchmarks from 11 sources, 14 of them independently verified. The latest was recorded on Oct 8, 2026.

Which API features does Muse Spark 1.1 support?

OpenRouter lists tool calling, structured outputs, and reasoning for Muse Spark 1.1.

About this record

Where Muse Spark 1.1's numbers come from, and every name it appears under.

Tracked since
Jul 14, 2026
Newest source mention
Aug 23, 2026

Where the results come from

Verification: 56 scores · 14 independently verified · 15 aggregator-attributed · 27 vendor-reported. How these tiers are assigned

From 11 sources on 8 sites. ai.meta.com supplies 16 of them; the 14 independently verified results come from 5 sites. Bars are coloured by trust tier.

  • ai.meta.com16
  • artificialanalysis.ai15
  • api.llm-stats.com11
  • livebench.ai7
  • labs.scale.com3
  • datasets-server.huggingface.co2
  • epoch.ai1
  • lmarena.ai1

Also known as

muse spark 1.1*muse spark 1.1 (xhigh)muse-spark-1-1