Noometry

Meta, proprietary

Muse Spark

Muse Spark by Meta ranks 46th of 354 ranked models on the Noometry Index as of October 2026, with a score of 50.6. Its strongest category is knowledge, where it ranks 13th.

Last verified

Noometry rank
#46 of 354
Index score
50.6
Evidence
Confirmed 27 results
Provider
Meta
Released
April 8, 2026
Weights
Proprietary
Reasoning
Unknown
Context window
—
Max output
—
Input price
Not listed
Output price
Not listed
Blended price
Not listed
Output speed
Not measured
Value
Not ranked
Knowledge cutoff
Unknown

Category scores

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

  1. Coding 46.2
  2. Reasoning 35.9
  3. Math 47.8
  4. Knowledge 65.7
  5. Multimodal 43.4
  6. Multilingual 56.1
  7. Instruction Following 75.9
  8. Long Context 44.4
  9. Writing & Preference 66.0
CategoryScoreRankResults
Coding46.2#692
Reasoning35.9#672
Math47.8#663
Knowledge65.7#133
Multimodal43.4#241
Multilingual56.1#241
Instruction Following75.9#511
Long Context44.4#691
Writing & Preference66.0#393

Strengths and weaknesses

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

Strongest categories

CategoryScorevs medianRank
Knowledge65.7+28.4#13 of 314, top 5%
Multilingual56.1+8.7#24 of 297, top 9%
Writing & Preference66.0+12.2#39 of 312, top 13%

Weakest categories

CategoryScorevs medianRank
Long Context44.4+3.4#69 of 296, top 24%
Coding46.2+7.5#69 of 340, top 21%
Math47.8+11.2#66 of 327, top 21%

Closest competitors

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

ModelRankScoreBlended $/MSpeed
Qwen3.7 Max#4251.5$3.75—Compare
Qwen3.6 Max Preview#4351.5$2.92—Compare
GLM-5.2#4451.1$2.1523Compare
GPT-5#4550.9$3.442Compare
Claude Opus 4.5#4750.5$1013Compare
Muse Spark 1.2#4850.3$2—Compare
MiMo-V2.6-Pro#4950.3$0.54—Compare
Claude Sonnet 4.6#5050.3$6—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

BenchmarkScorePositionSettingSourceDate
SciCode51.5%#38 of 121, top 32%Epoch AI
LMArena Coding1481#46 of 294, top 16%LMArena2026-10-08

Reasoning

BenchmarkScorePositionSettingSourceDate
CritPt11.3%#45 of 134, top 34%Epoch AI
LMArena Hard Prompts1474#36 of 297, top 13%LMArena2026-10-08
Epoch Capabilities Index152.04#44 of 213, top 21%Epoch AI2026-04-08

Math

BenchmarkScorePositionSettingSourceDate
OTIS Mock AIME 2024-202588.9%#53 of 173, top 31%Epoch AI2026-04-08
ProofBench17%#53 of 77, top 69%Epoch AI
LMArena Math1455#58 of 285, top 21%LMArena2026-10-08
FrontierMath (Feb 2025 set)39%#9 of 68, top 14%Epoch AI2026-04-08
FrontierMath Tier 4 (v1)14.6%#14 of 55, top 26%Epoch AI2026-04-08

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond89.8%#41 of 186, top 23%Epoch AI2026-04-08
Humanity's Last Exam40.6%#6 of 41, top 15%Epoch AI
LMArena Expert1457#64 of 273, top 24%LMArena2026-10-08

Multimodal

BenchmarkScorePositionSettingSourceDate
LMArena Vision1306#12 of 122, top 10%LMArena2026-10-09
LMArena Document1444#24 of 38, top 64%LMArena2026-09-13

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1464#24 of 297, top 9%LMArena2026-10-08
LMArena Chinese1509#38 of 285, top 14%LMArena2026-10-08
LMArena French1497#14 of 223, top 7%LMArena2026-10-08
LMArena German1497#8 of 231, top 4%LMArena2026-10-08
LMArena Korean1459#11 of 213, top 6%LMArena2026-10-08
LMArena Russian1466#29 of 283, top 11%LMArena2026-10-08
LMArena Spanish1472#21 of 226, top 10%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1442#48 of 298, top 17%LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1451#52 of 291, top 18%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1474#21 of 297, top 8%LMArena2026-10-08
LMArena Creative Writing1459#19 of 295, top 7%LMArena2026-10-08
LMArena Multi-Turn1477#22 of 295, top 8%LMArena2026-10-08

Compare Muse Spark

Other Meta models

Frequently asked questions

How good is Muse Spark?

Muse Spark by Meta ranks 46th of 354 ranked models on the Noometry Index as of October 2026, with a score of 50.6. Its strongest category is knowledge, where it ranks 13th.

Is Muse Spark open source?

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

What are Muse Spark's strengths and weaknesses?

Relative to other ranked models, Muse Spark places best in knowledge, multilingual, writing & preference and lowest in long context, coding, math.

What is Muse Spark best at?

Its best category is knowledge, where it ranks 13th on Noometry.