The Model Index
Up to four models

Muse Spark 1.3 vs Muse Spark 1.2

On the index (GPT-4 = 100), Muse Spark 1.3 scores 172 and Muse Spark 1.2 168. 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 1.3
Presets
Muse Spark 1.3
172156–188
WeightsClosed
ReleasedSep 2026
Price in / out$1.25 / $4.25
Context1.05M
Core tests taken4 of 9
Muse Spark 1.2
168151–184
WeightsClosed
ReleasedAug 2026
Price in / out$1.25 / $4.25
Context1.05M
Core tests taken3 of 9

Muse Spark 1.3 leads Muse Spark 1.2 by 5 points, ahead on 2 of 3 shared core tests, at a similar price.

Test by testthird-party results

Muse Spark 1.3Muse Spark 1.2
0%25%50%75%100%REASONING & KNOWLEDGELiveBench Data AnalysisLiveBench Data AnalysisLiveBench IFLiveBench IFLiveBench LanguageLiveBench LanguageLiveBench ReasoningLiveBench ReasoningMATHSLiveBench MathematicsLiveBench MathematicsProofBench v1.1ProofBench v1.1Chess puzzlesChess puzzlesCODINGTerminal-Bench 4.0Terminal-Bench 4.0LiveBench Agentic CodingLiveBench Agentic CodingLiveBench CodingLiveBench CodingCode MigrationCode MigrationCyberBench v1.1CyberBench v1.1IOIIOIProgramBenchProgramBenchVibe Code Bench v1.1Vibe Code Bench v1.1FrontierSWEFrontierSWEAGENTSAPEX-AgentsAPEX-AgentsDTBenchDTBenchLMCALMCAPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)EMBEMBLegal Research BenchLegal Research BenchTax Agent BenchTax Agent Bench
Every result as a table
TestMuse Spark 1.3Muse Spark 1.2
Reasoning & knowledge
LiveBench Data Analysis79.6%76.5%
LiveBench IF78.0%74.3%
LiveBench Language82.8%78.6%
LiveBench Reasoning89.6%90.0%
Maths
LiveBench Mathematics96.0%91.2%
ProofBench v1.155.0%43.0%
Chess puzzles37.0%27.0%
Coding
Terminal-Bench 4.010.6%6.1%
LiveBench Agentic Coding64.1%57.6%
LiveBench Coding81.1%77.5%
Code Migration27.6%29.9%
CyberBench v1.169.4%69.5%
IOI43.9%21.8%
ProgramBench0.5%0.5%
Vibe Code Bench v1.182.9%79.1%
FrontierSWE25.8%12.0%
Agents
APEX-Agents58.6%45.4%
DTBench96.5%94.7%
LMCA53.9%48.4%
Professional work
Finance Agent (v2)58.9%60.6%
EMB62.7%57.0%
Legal Research Bench40.9%43.8%
Tax Agent Bench36.0%32.8%

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

This page as a chartDownload PNG