Model comparison

Muse Spark vs Nova Premier 1.0

Muse Spark is the stronger model overall, scoring 50.3 to 37.7 on the Noometry Index.

Last verified . 0 shared benchmarks.

Muse Spark Meta

50.3

Rank #41 Confirmed

Nova Premier 1.0 Amazon

37.7

Rank #185 Confirmed

Summary

  • The widest gap is in knowledge, where Muse Spark leads 65.7 to 35.4.

Side by side

Muse Spark and Nova Premier 1.0 specifications
Muse SparkNova Premier 1.0
ProviderMetaAmazon
Noometry Index50.337.7
Released2026-04-082025-04-30
WeightsProprietaryProprietary
Context window—1M
Max output—10K
Input $ / M tokens—$2.50
Output $ / M tokens—$12.50
Results tracked276

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

Category by category

Coding Not comparable

Muse Spark: 45.6 (#65), Nova Premier 1.0: —

Coding benchmarks
BenchmarkMuse SparkNova Premier 1.0
SciCode51.5%—
LMArena Coding1482—

Reasoning Muse Spark leads

Muse Spark: 34.9 (#61), Nova Premier 1.0: 22.3 (#182)

Reasoning benchmarks
BenchmarkMuse SparkNova Premier 1.0
Kagi LLM Benchmark—44.8%
CritPt11.3%—
LMArena Hard Prompts1475—
Epoch Capabilities Index152.09—

Math Muse Spark leads

Muse Spark: 46.8 (#57), Nova Premier 1.0: 31.5 (#194)

Math benchmarks
BenchmarkMuse SparkNova Premier 1.0
OTIS Mock AIME 2024-202588.9%—
ProofBench17%—
Omni-MATH—35%
LMArena Math1455—
FrontierMath (Feb 2025 set)39%—
FrontierMath Tier 4 (v1)14.6%—

Knowledge Muse Spark leads

Muse Spark: 65.7 (#12), Nova Premier 1.0: 35.4 (#176)

Knowledge benchmarks
BenchmarkMuse SparkNova Premier 1.0
GPQA Diamond89.8%—
Humanity's Last Exam40.6%—
MMLU-Pro—72.6%
GPQA (HELM)—51.8%
LMArena Expert1458—

Multimodal Not comparable

Muse Spark: 42.7 (#23), Nova Premier 1.0: —

Multimodal benchmarks
BenchmarkMuse SparkNova Premier 1.0
LMArena Vision1306—
LMArena Document1444—

Multilingual Not comparable

Muse Spark: 56.3 (#23), Nova Premier 1.0: —

Multilingual benchmarks
BenchmarkMuse SparkNova Premier 1.0
LMArena Non-English1464—
LMArena Chinese1507—
LMArena French1497—
LMArena German1497—
LMArena Korean1457—
LMArena Russian1467—
LMArena Spanish1471—

Instruction Following Muse Spark leads

Muse Spark: 76.1 (#47), Nova Premier 1.0: 66.9 (#201)

Instruction Following benchmarks
BenchmarkMuse SparkNova Premier 1.0
IFEval—80.3%
LMArena Instruction Following1443—

Long Context Not comparable

Muse Spark: 44.4 (#65), Nova Premier 1.0: —

Long Context benchmarks
BenchmarkMuse SparkNova Premier 1.0
LMArena Longer Query1451—

Writing & Preference Muse Spark leads

Muse Spark: 66.2 (#37), Nova Premier 1.0: 51.0 (#174)

Writing & Preference benchmarks
BenchmarkMuse SparkNova Premier 1.0
LMArena Text1474—
LMArena Creative Writing1460—
WildBench—78.8%
LMArena Multi-Turn1477—

Frequently asked questions

Is Muse Spark better than Nova Premier 1.0?

Muse Spark is the stronger model overall, scoring 50.3 to 37.7 on the Noometry Index.

How many benchmarks do Muse Spark and Nova Premier 1.0 share?

0 benchmarks have published results for both models. Muse Spark has 27 scored results on Noometry and Nova Premier 1.0 has 6.

Related comparisons

Go deeper