The Model Index
Up to four models

Muse Spark 1.2 vs Muse Spark 1.1

On the index (GPT-4 = 100), Muse Spark 1.2 scores 162 and Muse Spark 1.1 161. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to Muse Spark 1.2
Presets
Muse Spark 1.2
162146–178
WeightsClosed
ReleasedAug 2026
Price in / out$1.25 / $4.25
Context1.05M
Core tests taken3 of 9
Muse Spark 1.1
161145–177
WeightsClosed
ReleasedJul 2026
Price in / out$1.25 / $4.25
Context1.05M
Core tests taken2 of 9

Muse Spark 1.2 and Muse Spark 1.1 are too close to call (1 point apart, within the uncertainty), ahead on 2 of 2 shared core tests, at a similar price.

Test by testthird-party results

Muse Spark 1.2Muse Spark 1.1
0%25%50%75%100%REASONING & KNOWLEDGELiveBench Data AnalysisLiveBench Data AnalysisLiveBench IFLiveBench IFLiveBench LanguageLiveBench LanguageLiveBench ReasoningLiveBench ReasoningMMLU ProMMLU ProMMMU ProMMMU ProSimpleQA VerifiedSimpleQA VerifiedMATHSLiveBench MathematicsLiveBench MathematicsChess puzzlesChess puzzlesCODINGLiveBench Agentic CodingLiveBench Agentic CodingLiveBench CodingLiveBench CodingCode MigrationCode MigrationProgramBenchProgramBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1DeepSWEDeepSWEAGENTSAPEX-AgentsAPEX-AgentsSkillsBenchSkillsBenchDTBenchDTBenchLMCALMCAPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)CorpFin v2CorpFin v2EMBEMBLegalBenchLegalBenchLegal Research BenchLegal Research BenchMedScribeMedScribeMortgageTaxMortgageTaxPublic Benefits Bench v1.1Public Benefits Bench v1.1TaxEval v2TaxEval v2
Every result as a table
TestMuse Spark 1.2Muse Spark 1.1
Reasoning & knowledge
LiveBench Data Analysis76.5%72.5%
LiveBench IF74.3%69.6%
LiveBench Language78.6%74.3%
LiveBench Reasoning90.0%87.7%
MMLU Pro88.3%88.7%
MMMU Pro86.1%86.6%
SimpleQA Verified60.3%57.8%
Maths
LiveBench Mathematics91.2%87.1%
Chess puzzles27.0%34.0%
Coding
LiveBench Agentic Coding57.6%58.5%
LiveBench Coding77.5%77.2%
Code Migration29.9%31.1%
ProgramBench0.5%0.0%
SWE-bench86.6%82.0%
Vibe Code Bench v1.179.1%72.2%
DeepSWE54.9%53.3%
Agents
APEX-Agents45.4%31.8%
SkillsBench53.0%59.2%
DTBench94.7%94.4%
LMCA48.4%49.9%
Professional work
Finance Agent (v2)60.6%57.2%
CorpFin v270.9%71.3%
EMB57.0%56.4%
LegalBench85.3%85.0%
Legal Research Bench43.8%38.0%
MedScribe90.1%88.9%
MortgageTax65.4%66.1%
Public Benefits Bench v1.168.5%61.3%
TaxEval v280.4%79.7%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG