Meta, proprietary

Muse Spark 1.2

Muse Spark 1.2 by Meta ranks 48th of 354 ranked models on the Noometry Index as of October 2026, with a score of 50.3. Its strongest category is multilingual, where it ranks 11th. 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

Specifications

Noometry rank
#48 of 354
Index score
50.3
Evidence
Confirmed 31 results
Provider
Meta
Released
August 5, 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
#143 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.

Muse Spark 1.2 category scores
  1. Coding 49.2
  2. Agentic & Tool Use 29.4
  3. Reasoning 51.3
  4. Math 46.4
  5. Knowledge 54.1
  6. Multimodal 43.4
  7. Multilingual 57.1
  8. Instruction Following 76.7
  9. Long Context 45.2
  10. Writing & Preference 72.3
Muse Spark 1.2 category ranks
CategoryScoreRankResults
Coding49.2#516
Agentic & Tool Use29.4#872
Reasoning51.3#346
Math46.4#702
Knowledge54.1#532
Multimodal43.4#251
Multilingual57.1#111
Instruction Following76.7#361
Long Context45.2#481
Writing & Preference72.3#144

Strengths and weaknesses

Categories where Muse Spark 1.2 places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

Muse Spark 1.2: strongest categories
CategoryScorevs medianRank
Multilingual57.1+9.7#11 of 297, top 4%
Writing & Preference72.3+18.5#14 of 312, top 5%
Reasoning51.3+27.7#34 of 350, top 10%

Weakest categories

Muse Spark 1.2: weakest categories
CategoryScorevs medianRank
Agentic & Tool Use29.4−0.9#87 of 154, top 57%
Math46.4+9.9#70 of 327, top 22%
Multimodal43.4+4.8#25 of 128, top 20%

Closest competitors

The models ranked just above and below Muse Spark 1.2. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Muse Spark 1.2
ModelRankScoreBlended $/MSpeed
GLM-5.2#4451.1$2.1523Compare
GPT-5#4550.9$3.442Compare
Muse Spark#4650.6——Compare
Claude Opus 4.5#4750.5$1013Compare
MiMo-V2.6-Pro#4950.3$0.54—Compare
Claude Sonnet 4.6#5050.3$6—Compare
Muse Spark 1.1#5149.9$2—Compare
Claude Haiku 5.5#5249.5$0.20—Compare

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

Muse Spark 1.2 Coding benchmark results
BenchmarkScorePositionSettingSourceDate
DeepSWE54.9%#19 of 29, top 66%xhighEpoch AI
LMArena WebDev1533#39 of 113, top 35%muse-spark-1.2 (xHigh)LMArena2026-10-08
FrontierSWE12%#17 of 18, top 95%xhighEpoch AI
SciCode56.4%#22 of 121, top 19%xhighEpoch AI
WeirdML60.3%#33 of 119, top 28%xhighEpoch AI
LMArena Coding1495#26 of 294, top 9%muse-spark-1.2 (xHigh)LMArena2026-10-08

Agentic & Tool Use

Muse Spark 1.2 Agentic & Tool Use benchmark results
BenchmarkScorePositionSettingSourceDate
APEX-Agents36.4%#40 of 49, top 82%Epoch AI
GDP.pdf12%Epoch AI
GDP.pdf16%#26 of 36, top 73%xhighEpoch AI

Reasoning

Muse Spark 1.2 Reasoning benchmark results
BenchmarkScorePositionSettingSourceDate
SimpleBench74.5%#8 of 77, top 11%Epoch AI
NYT Connections (extended)79.2%#38 of 91, top 42%high reasoningLech Mazur benchmarks
CritPt17.7%#32 of 134, top 24%xhighEpoch AI
LMArena Hard Prompts1486#20 of 297, top 7%muse-spark-1.2 (xHigh)LMArena2026-10-08
DTBench94.7%#20 of 151, top 14%xhighEpoch AI
LMCA48.4%#26 of 125, top 21%xhighEpoch AI
Epoch Capabilities Index154.87#32 of 213, top 16%Epoch AI2026-08-05

Math

Muse Spark 1.2 Math benchmark results
BenchmarkScorePositionSettingSourceDate
ProofBench43%#34 of 77, top 45%Epoch AI
LMArena Math1471#38 of 285, top 14%muse-spark-1.2 (xHigh)LMArena2026-10-08

Knowledge

Muse Spark 1.2 Knowledge benchmark results
BenchmarkScorePositionSettingSourceDate
SimpleQA Verified60.3%#15 of 77, top 20%xhighEpoch AI2026-08-27
LMArena Expert1480#41 of 273, top 16%muse-spark-1.2 (xHigh)LMArena2026-10-08

Multimodal

Muse Spark 1.2 Multimodal benchmark results
BenchmarkScorePositionSettingSourceDate
LMArena Vision1305#14 of 122, top 12%muse-spark-1.2 (xHigh)LMArena2026-10-09

Multilingual

Muse Spark 1.2 Multilingual benchmark results
BenchmarkScorePositionSettingSourceDate
LMArena Non-English1478#11 of 297, top 4%muse-spark-1.2 (xHigh)LMArena2026-10-08
LMArena Chinese1511#33 of 285, top 12%muse-spark-1.2 (xHigh)LMArena2026-10-08
LMArena French1513#6 of 223, top 3%muse-spark-1.2 (xHigh)LMArena2026-10-08
LMArena Russian1487#15 of 283, top 6%muse-spark-1.2 (xHigh)LMArena2026-10-08
LMArena Spanish1498#6 of 226, top 3%muse-spark-1.2 (xHigh)LMArena2026-10-08

Instruction Following

Muse Spark 1.2 Instruction Following benchmark results
BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1461#32 of 298, top 11%muse-spark-1.2 (xHigh)LMArena2026-10-08

Long Context

Muse Spark 1.2 Long Context benchmark results
BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1475#30 of 291, top 11%muse-spark-1.2 (xHigh)LMArena2026-10-08

Writing & Preference

Muse Spark 1.2 Writing & Preference benchmark results
BenchmarkScorePositionSettingSourceDate
LMArena Text1482#13 of 297, top 5%muse-spark-1.2 (xHigh)LMArena2026-10-08
LMArena Creative Writing1449#28 of 295, top 10%muse-spark-1.2 (xHigh)LMArena2026-10-08
EQ-Bench Creative Writing1840#18 of 115, top 16%EQ-Bench
LMArena Multi-Turn1494#8 of 295, top 3%muse-spark-1.2 (xHigh)LMArena2026-10-08

API pricing by provider

Muse Spark 1.2 API prices
RouteInput $/MOutput $/MCached input $/MChecked
meta$1.25$4.25$0.152026-10-10
openrouter$1.25$4.25$0.152026-10-10

Compare Muse Spark 1.2

Other Meta models

Frequently asked questions

How good is Muse Spark 1.2?

Muse Spark 1.2 by Meta ranks 48th of 354 ranked models on the Noometry Index as of October 2026, with a score of 50.3. Its strongest category is multilingual, where it ranks 11th. 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 1.2 cost?

Muse Spark 1.2 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 1.2's context window?

Muse Spark 1.2 accepts up to 1.05M tokens of input and can write up to 131K tokens in one response.

Is Muse Spark 1.2 open source?

No. Muse Spark 1.2 is proprietary and available only through Meta's API and partner platforms.

What are Muse Spark 1.2's strengths and weaknesses?

Relative to other ranked models, Muse Spark 1.2 places best in multilingual, writing & preference, reasoning and lowest in agentic & tool use, math, multimodal.

What is Muse Spark 1.2 best at?

Its best category is multilingual, where it ranks 11th on Noometry.