Noometry

Meta, proprietary

Muse Spark 1.3

Muse Spark 1.3 by Meta ranks 27th of 354 ranked models on the Noometry Index as of October 2026, with a score of 54.8. Its strongest category is multilingual, where it ranks 8th. API pricing starts at $1.25 per million input tokens and $4.25 per million output tokens, with a 1.05M-token context window.

Last verified

Noometry rank
#27 of 354
Index score
54.8
Evidence
Confirmed 37 results
Provider
Meta
Released
September 2, 2026
Weights
Proprietary
Reasoning
Yes
Context window
1.05M
Max output
131K
Input price
$1.25 / M
Output price
$4.25 / M
Blended price
$2 / M
Output speed
Not measured
Value
#139 of 219
Knowledge cutoff
Unknown
Input
text, image, video, pdf, audio

Category scores

Each category score combines every public result we have in that category.

  1. Coding 56.6
  2. Agentic & Tool Use 38.6
  3. Reasoning 54.0
  4. Math 73.1
  5. Knowledge 42.6
  6. Multimodal 43.7
  7. Multilingual 57.4
  8. Instruction Following 77.5
  9. Long Context 45.6
  10. Writing & Preference 73.6
CategoryScoreRankResults
Coding56.6#214
Agentic & Tool Use38.6#302
Reasoning54.0#277
Math73.1#215
Knowledge42.6#951
Multimodal43.7#221
Multilingual57.4#81
Instruction Following77.5#221
Long Context45.6#321
Writing & Preference73.6#94

Strengths and weaknesses

Categories where Muse Spark 1.3 places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Multilingual57.4+10.0#8 of 297, top 3%
Writing & Preference73.6+19.8#9 of 312, top 3%
Coding56.6+17.9#21 of 340, top 7%

Weakest categories

CategoryScorevs medianRank
Knowledge42.6+5.3#95 of 314, top 31%
Agentic & Tool Use38.6+8.3#30 of 154, top 20%
Multimodal43.7+5.1#22 of 128, top 18%

Closest competitors

The models ranked just above and below Muse Spark 1.3. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
Gemini 3.1 Pro Preview#2356.7$4.50—Compare
Gemini 4 Argon#2456.5——Compare
Grok 4.5#2555.0$34Compare
GLM-5.3#2654.8$2.15—Compare
Gemini 3 Pro#2854.8—1Compare
Claude Sonnet 5#2954.6$4—Compare
GPT-5.6 Luna#3054.6$0.4512Compare
DeepSeek V4 Pro#3154.3$0.9916Compare

Sponsored placements are available on pages like this one. Advertise on Noometry

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
CursorBench33.4%highEpoch AI
CursorBench29.3%lowEpoch AI
CursorBench41.6%#8 of 14, top 58%maxEpoch AI
CursorBench32.6%mediumEpoch AI
CursorBench24.3%minimalEpoch AI
CursorBench37.5%xhighEpoch AI
LMArena WebDev1657#10 of 113, top 9%LMArena2026-10-08
LMArena WebDev1626muse-spark-1.3 (xHigh)LMArena2026-10-08
SciCode58.8%maxEpoch AI
SciCode59.7%#8 of 121, top 7%xhighEpoch AI
LMArena Coding1514#9 of 294, top 4%LMArena2026-10-08

Agentic & Tool Use

BenchmarkScorePositionSettingSourceDate
APEX-Agents57.8%#15 of 49, top 31%Epoch AI
GDP.pdf27.6%#7 of 36, top 20%Epoch AI
GDP.pdf27.6%xhighEpoch AI

Reasoning

BenchmarkScorePositionSettingSourceDate
NYT Connections (extended)85.1%#28 of 91, top 31%high reasoningLech Mazur benchmarks
CritPt24.9%maxEpoch AI
CritPt26%#16 of 134, top 12%xhighEpoch AI
Chess Puzzles38%#25 of 129, top 20%maxEpoch AI2026-09-18
Chess Puzzles35%xhighEpoch AI2026-09-16
LMArena Hard Prompts1503#10 of 297, top 4%LMArena2026-10-08
Mystery Game Puzzles25%#34 of 74, top 46%maxEpoch AI2026-09-18
Mystery Game Puzzles14.1%xhighEpoch AI2026-09-16
DTBench96.5%#11 of 151, top 8%Epoch AI
LMCA53.9%#14 of 125, top 12%Epoch AI
Bench to the Future 30.14#5 of 10, top 50%xhighEpoch AI
Epoch Capabilities Index156.75#19 of 213, top 9%Epoch AI2026-09-02

Math

BenchmarkScorePositionSettingSourceDate
FrontierMath (Tiers 1-3)74%maxEpoch AI2026-09-18
FrontierMath (Tiers 1-3)74.4%#20 of 81, top 25%xhighEpoch AI2026-09-16
FrontierMath Tier 446.3%#20 of 63, top 32%maxEpoch AI2026-09-18
FrontierMath Tier 441.5%xhighEpoch AI2026-09-16
OTIS Mock AIME 2024-202599.2%#14 of 173, top 9%xhighEpoch AI2026-09-17
ProofBench55%Epoch AI
ProofBench58%#21 of 77, top 28%maxEpoch AI
LMArena Math1494#16 of 285, top 6%LMArena2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
LMArena Expert1516#13 of 273, top 5%LMArena2026-10-08

Multimodal

BenchmarkScorePositionSettingSourceDate
LMArena Vision1309#11 of 122, top 10%LMArena2026-10-09
LMArena Vision1301muse-spark-1.3 (xHigh)LMArena2026-10-09
LMArena Document1471#12 of 38, top 32%LMArena2026-09-13

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1481#8 of 297, top 3%LMArena2026-10-08
LMArena Chinese1529#16 of 285, top 6%LMArena2026-10-08
LMArena French1524#2 of 223, top 1%LMArena2026-10-08
LMArena German1515#3 of 231, top 2%LMArena2026-10-08
LMArena Japanese1474#16 of 211, top 8%LMArena2026-10-08
LMArena Korean1501#3 of 213, top 2%LMArena2026-10-08
LMArena Russian1490#13 of 283, top 5%LMArena2026-10-08
LMArena Spanish1490#11 of 226, top 5%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1477#19 of 298, top 7%LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1488#14 of 291, top 5%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1490#10 of 297, top 4%LMArena2026-10-08
LMArena Creative Writing1455#23 of 295, top 8%LMArena2026-10-08
EQ-Bench Creative Writing1906#14 of 115, top 13%EQ-Bench
LMArena Multi-Turn1482#16 of 295, top 6%LMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
meta$1.25$4.25$0.152026-10-10
openrouter$1.25$4.25$0.152026-10-10

All Meta API prices → Estimate your cost →

Compare Muse Spark 1.3

Other Meta models

Frequently asked questions

How good is Muse Spark 1.3?

Muse Spark 1.3 by Meta ranks 27th of 354 ranked models on the Noometry Index as of October 2026, with a score of 54.8. Its strongest category is multilingual, where it ranks 8th. API pricing starts at $1.25 per million input tokens and $4.25 per million output tokens, with a 1.05M-token context window.

How much does Muse Spark 1.3 cost?

Muse Spark 1.3 costs $1.25 per million input tokens and $4.25 per million output tokens on Meta's own API, with cached input at $0.15.

What is Muse Spark 1.3's context window?

Muse Spark 1.3 accepts up to 1.05M tokens of input and can write up to 131K tokens in one response.

Is Muse Spark 1.3 open source?

No. Muse Spark 1.3 is proprietary and available only through Meta's API and partner platforms.

What are Muse Spark 1.3's strengths and weaknesses?

Relative to other ranked models, Muse Spark 1.3 places best in multilingual, writing & preference, coding and lowest in knowledge, agentic & tool use, multimodal.

What is Muse Spark 1.3 best at?

Its best category is multilingual, where it ranks 8th on Noometry.