Model comparison

Aion 3.5 vs Muse Spark 1.3

Muse Spark 1.3 has enough public results to be ranked (#27); Aion 3.5 does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Aion 3.5 AionLabs

57.9

Unranked Sparse

Muse Spark 1.3 Meta

54.4

Rank #27 Confirmed

Summary

  • They share 1 benchmark with published results for both. Aion 3.5 scores higher in 1 category and Muse Spark 1.3 in 0 categories; one gap is clear of the uncertainty.
  • Muse Spark 1.3 is cheaper at $1.25 / $4.25 per million input/output tokens, against $3 / $6 for Aion 3.5.
  • Muse Spark 1.3 accepts more context: 1.05M tokens versus 262K.

Side by side

Aion 3.5 and Muse Spark 1.3 specifications
Aion 3.5Muse Spark 1.3
ProviderAionLabsMeta
Noometry Index57.954.4
Released—2026-09-02
WeightsProprietaryProprietary
Context window262K1.05M
Max output33K131K
Input $ / M tokens$3$1.25
Output $ / M tokens$6$4.25
Results tracked134

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

Category by category

Coding Not comparable

Aion 3.5: —, Muse Spark 1.3: 56.1 (#18)

Coding benchmarks
BenchmarkAion 3.5Muse Spark 1.3
CursorBench—41.6%
LMArena WebDev—1655
SciCode—59.7%
LMArena Coding—1516

Agentic & Tool Use Not comparable

Aion 3.5: —, Muse Spark 1.3: 38.6 (#28)

Agentic & Tool Use benchmarks
BenchmarkAion 3.5Muse Spark 1.3
APEX-Agents—57.8%
GDP.pdf—27.6%

Reasoning Not comparable

Aion 3.5: —, Muse Spark 1.3: 52.9 (#27)

Reasoning benchmarks
BenchmarkAion 3.5Muse Spark 1.3
NYT Connections (extended)—85.1%
CritPt—24.9%
Chess Puzzles—38%
LMArena Hard Prompts—1503
Mystery Game Puzzles—25%
DTBench—96.5%
LMCA—53.9%
Bench to the Future 3—0.14
Epoch Capabilities Index—156.89

Math Not comparable

Aion 3.5: —, Muse Spark 1.3: 72.4 (#16)

Math benchmarks
BenchmarkAion 3.5Muse Spark 1.3
FrontierMath (Tiers 1-3)—74.4%
FrontierMath Tier 4—46.3%
OTIS Mock AIME 2024-2025—99.2%
LMArena Math—1497

Knowledge Not comparable

Aion 3.5: —, Muse Spark 1.3: 42.0 (#92)

Knowledge benchmarks
BenchmarkAion 3.5Muse Spark 1.3
LMArena Expert—1516

Multimodal Not comparable

Aion 3.5: —, Muse Spark 1.3: 43.0 (#21)

Multimodal benchmarks
BenchmarkAion 3.5Muse Spark 1.3
LMArena Vision—1310
LMArena Document—1471

Multilingual Not comparable

Aion 3.5: —, Muse Spark 1.3: 57.8 (#6)

Multilingual benchmarks
BenchmarkAion 3.5Muse Spark 1.3
LMArena Non-English—1485
LMArena Chinese—1527
LMArena French—1534
LMArena Korean—1513
LMArena Russian—1491
LMArena Spanish—1485

Instruction Following Not comparable

Aion 3.5: —, Muse Spark 1.3: 77.8 (#14)

Instruction Following benchmarks
BenchmarkAion 3.5Muse Spark 1.3
LMArena Instruction Following—1481

Long Context Not comparable

Aion 3.5: —, Muse Spark 1.3: 45.7 (#29)

Long Context benchmarks
BenchmarkAion 3.5Muse Spark 1.3
LMArena Longer Query—1491

Writing & Preference Aion 3.5 leads

Aion 3.5: 74.9, Muse Spark 1.3: 73.7 (#10)

Writing & Preference benchmarks
BenchmarkAion 3.5Muse Spark 1.3
EQ-Bench Creative Writing19291906
LMArena Text—1490
LMArena Creative Writing—1450
LMArena Multi-Turn—1486

Frequently asked questions

Is Aion 3.5 better than Muse Spark 1.3?

Muse Spark 1.3 has enough public results to be ranked (#27); Aion 3.5 does not yet, so treat this comparison as directional.

Which is cheaper, Aion 3.5 or Muse Spark 1.3?

Muse Spark 1.3 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 1.3 does, with 1.05M tokens against 262K.

How many benchmarks do Aion 3.5 and Muse Spark 1.3 share?

1 benchmark has published results for both models. Aion 3.5 has 1 scored results on Noometry and Muse Spark 1.3 has 34.

Related comparisons

Go deeper