The Model Index
Up to four models

Kimi K3 vs Muse Spark 1.1

On the index (GPT-4 = 100), Kimi K3 scores 168 and Muse Spark 1.1 161. 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
Presets
Kimi K3
168152–183
WeightsOpen
ReleasedJul 2026
Price in / out$0.19 / $16
Context1.05M
Core tests taken6 of 9
Muse Spark 1.1
161145–177
WeightsClosed
ReleasedJul 2026
Price in / out$1.25 / $4.25
Context1.05M
Core tests taken2 of 9

Kimi K3 leads Muse Spark 1.1 by 7 points, ahead on 1 of 2 shared core tests, at 2.1× the price.

Test by testthird-party results

Kimi K3Muse Spark 1.1
0%25%50%75%100%REASONING & KNOWLEDGELiveBench Data AnalysisLiveBench Data AnalysisLiveBench IFLiveBench IFLiveBench LanguageLiveBench LanguageLiveBench ReasoningLiveBench ReasoningGPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMMMU ProMMMU ProSimpleQA VerifiedSimpleQA VerifiedMATHSLiveBench MathematicsLiveBench MathematicsChess puzzlesChess puzzlesSurface Evolver BenchSurface Evolver BenchCODINGLiveBench Agentic CodingLiveBench Agentic CodingLiveBench CodingLiveBench CodingCode MigrationCode MigrationLiveCodeBenchLiveCodeBenchProgramBenchProgramBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1DeepSWEDeepSWEAGENTSAPEX-AgentsAPEX-AgentsDTBenchDTBenchLMCALMCAPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)CorpFin v2CorpFin v2EMBEMBLegalBenchLegalBenchLegal Research BenchLegal Research BenchMedScribeMedScribeMortgageTaxMortgageTaxPublic Benefits Bench v1.1Public Benefits Bench v1.1TaxEval v2TaxEval v2
Every result as a table
TestKimi K3Muse Spark 1.1
Reasoning & knowledge
LiveBench Data Analysis78.7%72.5%
LiveBench IF71.4%69.6%
LiveBench Language85.5%74.3%
LiveBench Reasoning90.7%87.7%
GPQA Diamond (Vals AI)92.9%91.2%
MMLU Pro88.0%88.7%
MMMU Pro88.1%86.6%
SimpleQA Verified50.6%57.8%
Maths
LiveBench Mathematics84.4%87.1%
Chess puzzles37.0%34.0%
Surface Evolver Bench95.0%52.5%
Coding
LiveBench Agentic Coding62.2%58.5%
LiveBench Coding81.5%77.2%
Code Migration16.1%31.1%
LiveCodeBench87.2%85.9%
ProgramBench2.0%0.0%
SWE-bench93.4%82.0%
Vibe Code Bench v1.185.0%72.2%
DeepSWE68.5%53.3%
Agents
APEX-Agents47.8%31.8%
DTBench91.2%94.4%
LMCA52.7%49.9%
Professional work
Finance Agent (v2)53.1%57.2%
CorpFin v271.6%71.3%
EMB66.7%56.4%
LegalBench86.2%85.0%
Legal Research Bench46.2%38.0%
MedScribe88.0%88.9%
MortgageTax66.3%66.1%
Public Benefits Bench v1.168.2%61.3%
TaxEval v275.7%79.7%

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

This page as a chartDownload PNG