The Model Index
Up to four models

Kimi K3.1 Pro vs Muse Wonder

On the index (GPT-4 = 100), Kimi K3.1 Pro scores 179 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 Kimi K3.1 Pro
Presets
Kimi K3.1 Pro
179163–195
WeightsOpen
ReleasedOct 2026
Price in / out$0.24 / $8.4
Context1.05M
Core tests taken4 of 9
Muse Wonder
177160–193
WeightsClosed
ReleasedOct 2026
Price in / out$4.0 / $20
Context1.05M
Core tests taken2 of 9

Kimi K3.1 Pro and Muse Wonder are too close to call (3 points apart, within the uncertainty), ahead on 0 of 2 shared core tests, and costs 3.5× less.

Test by testthird-party results

Kimi K3.1 ProMuse Wonder
0%25%50%75%100%MATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)AIME-style maths (OTIS mock)AIME-style maths (OTIS mock)FrontierMath (tier 4)FrontierMath (tier 4)AGENTSAPEX-AgentsAPEX-AgentsDTBenchDTBenchFurniture assemblyFurniture assemblyLMCALMCAMystery game puzzlesMystery game puzzles
Every result as a table
TestKimi K3.1 ProMuse Wonder
Maths
FrontierMath (tiers 1-3)78.3%82.1%
AIME-style maths (OTIS mock)100.0%99.4%
FrontierMath (tier 4)65.8%70.7%
Agents
APEX-Agents65.5%66.1%
DTBench93.3%95.2%
Furniture assembly55.8%54.2%
LMCA57.6%56.8%
Mystery game puzzles42.0%51.0%

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

This page as a chartDownload PNG