Noometry

Model comparison

Gemini 3.1 Pro Preview vs Muse Spark 1.3

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 54.4 on the Noometry Index. Muse Spark 1.3 costs 2.3× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Last verified . 32 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #20 Confirmed

Muse Spark 1.3 Meta

54.4

Rank #27 Confirmed

Summary

  • They share 32 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 3 categories and Muse Spark 1.3 in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Gemini 3.1 Pro Preview leads 71.8 to 42.0.
  • The biggest single-benchmark swing is APEX-Agents: 35.3% for Gemini 3.1 Pro Preview and 57.8% for Muse Spark 1.3.
  • Muse Spark 1.3 is cheaper at $1.25 / $4.25 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.

Side by side

Gemini 3.1 Pro PreviewMuse Spark 1.3
ProviderGoogleMeta
Noometry Index56.754.4
Released2026-02-192026-09-02
WeightsProprietaryProprietary
Context window1.05M1.05M
Max output66K131K
Input $ / M tokens$2$1.25
Output $ / M tokens$12$4.25
Results tracked7134

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

Category by category

Coding Muse Spark 1.3 leads

Gemini 3.1 Pro Preview: 42.7 (#88), Muse Spark 1.3: 56.1 (#18)

BenchmarkGemini 3.1 Pro PreviewMuse Spark 1.3
LMArena WebDev14461655
SciCode58.9%59.7%
LMArena Coding14831516
SWE-bench Verified75.6%—
DeepSWE11.7%—
CursorBench—41.6%
GSO22.6%—
WeirdML72.1%—
MirrorCode8.9%—
ALE-Bench1,161—
AlgoTune2.02—

Agentic & Tool Use Too close to call

Gemini 3.1 Pro Preview: 37.7 (#33), Muse Spark 1.3: 38.6 (#28)

BenchmarkGemini 3.1 Pro PreviewMuse Spark 1.3
APEX-Agents35.3%57.8%
GDP.pdf17%27.6%
Terminal-Bench80.2%—
τ²-bench Banking26%—
DeepResearch Bench47.8%—
PostTrainBench22%—
BALROG57%—
ExploitBench26.1%—
GBAEval0.8%—
LMArena Search1211—
METR Time Horizons77%—
Vending-Bench 23,774—

Reasoning Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.7 (#9), Muse Spark 1.3: 52.9 (#27)

BenchmarkGemini 3.1 Pro PreviewMuse Spark 1.3
NYT Connections (extended)97.4%85.1%
CritPt17.7%24.9%
Chess Puzzles55%38%
LMArena Hard Prompts14841503
Mystery Game Puzzles34%25%
DTBench97.1%96.5%
LMCA53.8%53.9%
Epoch Capabilities Index154.92156.89
ARC-AGI-277.1%—
SimpleBench79.6%—
ARC-AGI-198%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
Bench to the Future 3—0.14
ForecastBench59—

Math Muse Spark 1.3 leads

Gemini 3.1 Pro Preview: 61.8 (#28), Muse Spark 1.3: 72.4 (#16)

BenchmarkGemini 3.1 Pro PreviewMuse Spark 1.3
FrontierMath (Tiers 1-3)59.6%74.4%
FrontierMath Tier 426.8%46.3%
OTIS Mock AIME 2024-202595.6%99.2%
LMArena Math14851497
MathArena Final-Answer Competitions86.5%—
ProofBench26%—
FrontierMath (Feb 2025 set)36.9%—
FrontierMath Tier 4 (v1)16.7%—

Knowledge Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.8 (#3), Muse Spark 1.3: 42.0 (#92)

BenchmarkGemini 3.1 Pro PreviewMuse Spark 1.3
LMArena Expert14841516
GPQA Diamond94.4%—
Humanity's Last Exam46.4%—
SimpleQA Verified73.5%—
Vectara Hallucination Rate10.4%—

Multimodal Muse Spark 1.3 leads

Gemini 3.1 Pro Preview: 38.1 (#60), Muse Spark 1.3: 43.0 (#21)

BenchmarkGemini 3.1 Pro PreviewMuse Spark 1.3
LMArena Vision12961310
LMArena Document14441471
Blueprint-Bench 226.5%—
Furniture Assembly26.7%—

Multilingual Too close to call

Gemini 3.1 Pro Preview: 57.1 (#11), Muse Spark 1.3: 57.8 (#6)

BenchmarkGemini 3.1 Pro PreviewMuse Spark 1.3
LMArena Non-English14751485
LMArena Chinese15281527
LMArena French14881534
LMArena Korean14581513
LMArena Russian14961491
LMArena Spanish14801485
LMArena German1491—
LMArena Japanese1494—

Instruction Following Too close to call

Gemini 3.1 Pro Preview: 77.1 (#31), Muse Spark 1.3: 77.8 (#14)

BenchmarkGemini 3.1 Pro PreviewMuse Spark 1.3
LMArena Instruction Following14651481

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.3 (#17), Muse Spark 1.3: 45.7 (#29)

BenchmarkGemini 3.1 Pro PreviewMuse Spark 1.3
LMArena Longer Query14821491
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Muse Spark 1.3 leads

Gemini 3.1 Pro Preview: 66.3 (#36), Muse Spark 1.3: 73.7 (#10)

BenchmarkGemini 3.1 Pro PreviewMuse Spark 1.3
LMArena Text14801490
LMArena Creative Writing14821450
EQ-Bench Creative Writing14911906
LMArena Multi-Turn14861486
EQ-Bench 41142—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than Muse Spark 1.3?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 54.4 on the Noometry Index. Muse Spark 1.3 costs 2.3× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Which is cheaper, Gemini 3.1 Pro Preview 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; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or Muse Spark 1.3 better for coding?

Muse Spark 1.3 scores higher on coding benchmarks: 56.1 versus 42.7 in the Noometry coding category.

Which has the bigger context window?

Both accept 1.05M tokens.

How many benchmarks do Gemini 3.1 Pro Preview and Muse Spark 1.3 share?

32 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Muse Spark 1.3 has 34.

Related comparisons

Go deeper