The Model Index
Up to four models

GPT-5.5 vs Muse Spark 1.3

On the index (GPT-4 = 100), GPT-5.5 scores 172 and Muse Spark 1.3 169. 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 GPT-5.5
Presets
GPT-5.5
172156–188
WeightsClosed
ReleasedApr 2026
Price in / out$5.0 / $30
Context1.05M
Core tests taken6 of 9
Muse Spark 1.3
169153–186
WeightsClosed
ReleasedSep 2026
Price in / out$1.25 / $4.25
Context1.05M
Core tests taken4 of 9

GPT-5.5 and Muse Spark 1.3 are too close to call (3 points apart, within the uncertainty), ahead on 1 of 3 shared core tests, at 5.6× the price.

Test by testthird-party results

GPT-5.5Muse Spark 1.3
0%25%50%75%100%REASONING & KNOWLEDGELiveBench Data AnalysisLiveBench Data AnalysisLiveBench IFLiveBench IFLiveBench LanguageLiveBench LanguageLiveBench ReasoningLiveBench ReasoningSimpleBenchSimpleBenchMATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)AIME-style maths (OTIS mock)AIME-style maths (OTIS mock)LiveBench MathematicsLiveBench MathematicsChess puzzlesChess puzzlesFrontierMath (tier 4)FrontierMath (tier 4)CODINGLiveBench Agentic CodingLiveBench Agentic CodingLiveBench CodingLiveBench CodingCode MigrationCode MigrationProgramBenchProgramBenchVibe Code Bench v1.1Vibe Code Bench v1.1MirrorCodeMirrorCodeAGENTSAPEX-AgentsAPEX-AgentsDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)EMBEMBLegal Research BenchLegal Research BenchTax Agent BenchTax Agent Bench
Every result as a table
TestGPT-5.5Muse Spark 1.3
Reasoning & knowledge
LiveBench Data Analysis81.6%79.6%
LiveBench IF70.7%78.0%
LiveBench Language87.4%82.8%
LiveBench Reasoning89.6%89.6%
SimpleBench69.0%81.8%
Maths
FrontierMath (tiers 1-3)85.3%74.4%
AIME-style maths (OTIS mock)100.0%99.2%
LiveBench Mathematics95.9%96.0%
Chess puzzles63.0%37.0%
FrontierMath (tier 4)72.5%46.3%
Coding
LiveBench Agentic Coding54.0%64.1%
LiveBench Coding82.2%81.1%
Code Migration45.2%27.6%
ProgramBench0.5%0.5%
Vibe Code Bench v1.169.8%82.9%
MirrorCode23.3%54.4%
Agents
APEX-Agents55.1%58.6%
DTBench96.0%96.5%
LMCA54.3%53.9%
Mystery game puzzles56.0%25.0%
Professional work
Finance Agent (v2)51.8%58.9%
EMB64.5%62.7%
Legal Research Bench40.4%40.9%
Tax Agent Bench21.8%37.9%

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

This page as a chartDownload PNG