Noometry

Model comparison

Muse Spark 1.1 vs Tulu 3 (Tülu 3) 70B

Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 33.0 on the Noometry Index.

Last verified . 11 shared benchmarks.

Muse Spark 1.1 Meta

49.9

Rank #51 Confirmed

Tulu 3 (Tülu 3) 70B Allen Institute for AI (Ai2)

33.0

Rank #251 Confirmed

Summary

  • They share 11 benchmarks with published results for both. Muse Spark 1.1 scores higher in 8 categories and Tulu 3 (Tülu 3) 70B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Muse Spark 1.1 leads 45.5 to 14.2.
  • Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.

Side by side

Muse Spark 1.1Tulu 3 (Tülu 3) 70B
ProviderMetaAllen Institute for AI (Ai2)
Noometry Index49.933.0
Released2026-04-082024-11-21
WeightsProprietaryOpen
Context window1.05M—
Max output131K—
Input $ / M tokens$1.25—
Output $ / M tokens$4.25—
Results tracked3714

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

Category by category

Coding Muse Spark 1.1 leads

Muse Spark 1.1: 51.3 (#40), Tulu 3 (Tülu 3) 70B: 36.0 (#214)

BenchmarkMuse Spark 1.1Tulu 3 (Tülu 3) 70B
LMArena Coding14981235
DeepSWE53.3%—
LMArena WebDev1542—
SciCode58.8%—

Agentic & Tool Use Not comparable

Muse Spark 1.1: 30.8 (#73), Tulu 3 (Tülu 3) 70B: —

BenchmarkMuse Spark 1.1Tulu 3 (Tülu 3) 70B
APEX-Agents31.8%—
τ²-bench Banking40.5%—
GBAEval7.9%—
GDP.pdf15%—
Vending-Bench 26,520—

Reasoning Muse Spark 1.1 leads

Muse Spark 1.1: 47.1 (#44), Tulu 3 (Tülu 3) 70B: 23.9 (#169)

BenchmarkMuse Spark 1.1Tulu 3 (Tülu 3) 70B
LMArena Hard Prompts14861220
NYT Connections (extended)84.9%—
CritPt15.1%—
DTBench94.4%—
LMCA49.9%—
Surface Evolver Bench52.5%—
Epoch Capabilities Index154.21—

Math Muse Spark 1.1 leads

Muse Spark 1.1: 45.5 (#76), Tulu 3 (Tülu 3) 70B: 14.2 (#303)

BenchmarkMuse Spark 1.1Tulu 3 (Tülu 3) 70B
LMArena Math14831242
OTIS Mock AIME 2024-2025—4.4%
ProofBench39%—
MATH Level 5—42.7%

Knowledge Muse Spark 1.1 leads

Muse Spark 1.1: 53.1 (#59), Tulu 3 (Tülu 3) 70B: 25.0 (#264)

BenchmarkMuse Spark 1.1Tulu 3 (Tülu 3) 70B
GPQA Diamond—46.3%
SimpleQA Verified57.8%—
LMArena Expert1478—

Multimodal Not comparable

Muse Spark 1.1: 42.6 (#29), Tulu 3 (Tülu 3) 70B: —

BenchmarkMuse Spark 1.1Tulu 3 (Tülu 3) 70B
LMArena Vision1293—
LMArena Document1465—

Multilingual Muse Spark 1.1 leads

Muse Spark 1.1: 56.7 (#17), Tulu 3 (Tülu 3) 70B: 39.9 (#222)

BenchmarkMuse Spark 1.1Tulu 3 (Tülu 3) 70B
LMArena Non-English14721236
LMArena Chinese15181249
LMArena Russian14831246
LMArena French1494—
LMArena German1466—
LMArena Japanese1451—
LMArena Korean1458—
LMArena Spanish1464—

Instruction Following Muse Spark 1.1 leads

Muse Spark 1.1: 76.5 (#39), Tulu 3 (Tülu 3) 70B: 64.8 (#227)

BenchmarkMuse Spark 1.1Tulu 3 (Tülu 3) 70B
LMArena Instruction Following14571233

Long Context Muse Spark 1.1 leads

Muse Spark 1.1: 44.8 (#58), Tulu 3 (Tülu 3) 70B: 37.1 (#222)

BenchmarkMuse Spark 1.1Tulu 3 (Tülu 3) 70B
LMArena Longer Query14621224

Writing & Preference Muse Spark 1.1 leads

Muse Spark 1.1: 73.4 (#11), Tulu 3 (Tülu 3) 70B: 45.6 (#223)

BenchmarkMuse Spark 1.1Tulu 3 (Tülu 3) 70B
LMArena Text14791256
LMArena Creative Writing14371231
LMArena Multi-Turn14851252
EQ-Bench Creative Writing1927—
EQ-Bench 41260—

Frequently asked questions

Is Muse Spark 1.1 better than Tulu 3 (Tülu 3) 70B?

Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 33.0 on the Noometry Index.

Is Muse Spark 1.1 or Tulu 3 (Tülu 3) 70B better for coding?

Muse Spark 1.1 scores higher on coding benchmarks: 51.3 versus 36.0 in the Noometry coding category.

How many benchmarks do Muse Spark 1.1 and Tulu 3 (Tülu 3) 70B share?

11 benchmarks have published results for both models. Muse Spark 1.1 has 37 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.

Related comparisons

Go deeper