The Model Index
Up to four models

GPT-5.6 Terra vs Muse Spark 1.3

On the index (GPT-4 = 100), GPT-5.6 Terra 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-5.6 Terra
Presets
GPT-5.6 Terra
172156–188
WeightsClosed
ReleasedJul 2026
Price in / out$2.0 / $12
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-5.6 Terra and Muse Spark 1.3 are too close to call (2 points apart, within the uncertainty), ahead on 2 of 4 shared core tests, at 2.3× the price.

Test by testthird-party results

GPT-5.6 TerraMuse 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 MathematicsProofBench v1.1ProofBench v1.1Chess puzzlesChess puzzlesFrontierMath (tier 4)FrontierMath (tier 4)CODINGTerminal-Bench 4.0Terminal-Bench 4.0LiveBench Agentic CodingLiveBench Agentic CodingLiveBench CodingLiveBench CodingCode MigrationCode MigrationCyberBench v1.1CyberBench v1.1IOIIOIProgramBenchProgramBenchVibe Code Bench v1.1Vibe Code Bench v1.1MirrorCodeMirrorCodeAGENTSAPEX-AgentsAPEX-AgentsTerminal-Bench-ScienceTerminal-Bench-ScienceDTBenchDTBenchLMCALMCAMystery 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-5.6 TerraMuse Spark 1.3
Reasoning & knowledge
LiveBench Data Analysis79.3%79.6%
LiveBench IF64.6%78.0%
LiveBench Language82.9%82.8%
LiveBench Reasoning90.6%89.6%
SimpleBench48.9%81.8%
Maths
FrontierMath (tiers 1-3)86.0%74.4%
AIME-style maths (OTIS mock)99.7%99.2%
LiveBench Mathematics94.9%96.0%
ProofBench v1.174.0%55.0%
Chess puzzles47.0%37.0%
FrontierMath (tier 4)70.7%46.3%
Coding
Terminal-Bench 4.022.7%10.6%
LiveBench Agentic Coding54.9%64.1%
LiveBench Coding78.3%81.1%
Code Migration47.8%27.6%
CyberBench v1.172.1%69.4%
IOI87.6%43.9%
ProgramBench0.5%0.5%
Vibe Code Bench v1.174.6%82.9%
MirrorCode41.1%54.4%
Agents
APEX-Agents58.2%58.6%
Terminal-Bench-Science10.0%4.3%
DTBench93.3%96.5%
LMCA54.9%53.9%
Mystery game puzzles35.0%25.0%
Professional work
Finance Agent (v2)54.4%58.9%
EMB66.2%62.7%
Legal Research Bench41.3%40.9%
Tax Agent Bench30.0%37.9%

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

This page as a chartDownload PNG