The Model Index
Up to four models

GPT-6 Sol vs Muse Wonder

On the index (GPT-4 = 100), GPT-6 Sol scores 178 and Muse Wonder 177. 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-6 Sol
Presets
GPT-6 Sol
178162–194
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $10
Context1.05M
Core tests taken6 of 9
Muse Wonder
177160–193
WeightsClosed
ReleasedOct 2026
Price in / out$4.0 / $20
Context1.05M
Core tests taken2 of 9

GPT-6 Sol and Muse Wonder are too close to call (1 point apart, within the uncertainty), ahead on 1 of 2 shared core tests, and costs 2.0× less.

Test by testthird-party results

GPT-6 SolMuse Wonder
0%25%50%75%100%REASONING & KNOWLEDGEEBR-benchEBR-benchMATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)AIME-style maths (OTIS mock)AIME-style maths (OTIS mock)FrontierMath (tier 4)FrontierMath (tier 4)CODINGMirrorCodeMirrorCodeAGENTSAPEX-AgentsAPEX-AgentsDTBenchDTBenchFurniture assemblyFurniture assemblyLMCALMCAMystery game puzzlesMystery game puzzles
Every result as a table
TestGPT-6 SolMuse Wonder
Reasoning & knowledge
EBR-bench53.3%31.4%
Maths
FrontierMath (tiers 1-3)89.8%82.1%
AIME-style maths (OTIS mock)100.0%99.4%
FrontierMath (tier 4)90.0%70.7%
Coding
MirrorCode48.9%45.6%
Agents
APEX-Agents54.3%66.1%
DTBench97.3%95.2%
Furniture assembly58.3%54.2%
LMCA59.1%56.8%
Mystery game puzzles56.0%51.0%

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

This page as a chartDownload PNG