Model comparison

Aion 3.5 vs Muse Spark 1.2

Muse Spark 1.2 has enough public results to be ranked (#48); Aion 3.5 does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Aion 3.5 AionLabs

58.1

Unranked Sparse

Muse Spark 1.2 Meta

50.3

Rank #48 Confirmed

Summary

  • They share 1 benchmark with published results for both. Aion 3.5 scores higher in 1 category and Muse Spark 1.2 in 0 categories; one gap is clear of the uncertainty.
  • Muse Spark 1.2 is cheaper at $1.25 / $4.25 per million input/output tokens, against $3 / $6 for Aion 3.5.
  • Muse Spark 1.2 accepts more context: 1.05M tokens versus 262K.

Side by side

Aion 3.5 and Muse Spark 1.2 specifications
Aion 3.5Muse Spark 1.2
ProviderAionLabsMeta
Noometry Index58.150.3
Released—2026-08-05
WeightsProprietaryProprietary
Context window262K1.05M
Max output33K131K
Input $ / M tokens$3$1.25
Output $ / M tokens$6$4.25
Results tracked131

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

Category by category

Coding Not comparable

Aion 3.5: —, Muse Spark 1.2: 49.2 (#51)

Coding benchmarks
BenchmarkAion 3.5Muse Spark 1.2
DeepSWE—54.9%
LMArena WebDev—1533
FrontierSWE—12%
SciCode—56.4%
WeirdML—60.3%
LMArena Coding—1495

Agentic & Tool Use Not comparable

Aion 3.5: —, Muse Spark 1.2: 29.4 (#87)

Agentic & Tool Use benchmarks
BenchmarkAion 3.5Muse Spark 1.2
APEX-Agents—36.4%
GDP.pdf—16%

Reasoning Not comparable

Aion 3.5: —, Muse Spark 1.2: 51.3 (#34)

Reasoning benchmarks
BenchmarkAion 3.5Muse Spark 1.2
SimpleBench—74.5%
NYT Connections (extended)—79.2%
CritPt—17.7%
LMArena Hard Prompts—1486
DTBench—94.7%
LMCA—48.4%
Epoch Capabilities Index—154.87

Math Not comparable

Aion 3.5: —, Muse Spark 1.2: 46.4 (#70)

Math benchmarks
BenchmarkAion 3.5Muse Spark 1.2
ProofBench—43%
LMArena Math—1471

Knowledge Not comparable

Aion 3.5: —, Muse Spark 1.2: 54.1 (#53)

Knowledge benchmarks
BenchmarkAion 3.5Muse Spark 1.2
SimpleQA Verified—60.3%
LMArena Expert—1480

Multimodal Not comparable

Aion 3.5: —, Muse Spark 1.2: 43.4 (#25)

Multimodal benchmarks
BenchmarkAion 3.5Muse Spark 1.2
LMArena Vision—1305

Multilingual Not comparable

Aion 3.5: —, Muse Spark 1.2: 57.1 (#11)

Multilingual benchmarks
BenchmarkAion 3.5Muse Spark 1.2
LMArena Non-English—1478
LMArena Chinese—1511
LMArena French—1513
LMArena Russian—1487
LMArena Spanish—1498

Instruction Following Not comparable

Aion 3.5: —, Muse Spark 1.2: 76.7 (#36)

Instruction Following benchmarks
BenchmarkAion 3.5Muse Spark 1.2
LMArena Instruction Following—1461

Long Context Not comparable

Aion 3.5: —, Muse Spark 1.2: 45.2 (#48)

Long Context benchmarks
BenchmarkAion 3.5Muse Spark 1.2
LMArena Longer Query—1475

Writing & Preference Aion 3.5 leads

Aion 3.5: 74.9, Muse Spark 1.2: 72.3 (#14)

Writing & Preference benchmarks
BenchmarkAion 3.5Muse Spark 1.2
EQ-Bench Creative Writing19291840
LMArena Text—1482
LMArena Creative Writing—1449
LMArena Multi-Turn—1494

Frequently asked questions

Is Aion 3.5 better than Muse Spark 1.2?

Muse Spark 1.2 has enough public results to be ranked (#48); Aion 3.5 does not yet, so treat this comparison as directional.

Which is cheaper, Aion 3.5 or Muse Spark 1.2?

Muse Spark 1.2 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Aion 3.5 lists at $3 and $6.

Which has the bigger context window?

Muse Spark 1.2 does, with 1.05M tokens against 262K.

How many benchmarks do Aion 3.5 and Muse Spark 1.2 share?

1 benchmark has published results for both models. Aion 3.5 has 1 scored results on Noometry and Muse Spark 1.2 has 31.

Related comparisons

Go deeper