The Model Index
Up to four models

Kimi K3 vs Kimi K2.6

On the index (GPT-4 = 100), Kimi K3 scores 168 and Kimi K2.6 152. 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
Kimi K2.6
152136–169
WeightsOpen
ReleasedApr 2026
Price in / out$0.65 / $3.41
Context262K
Core tests taken4 of 9

Kimi K3 leads Kimi K2.6 by 15 points, ahead on 3 of 3 shared core tests, at 3.1× the price.

Test by testthird-party results

Kimi K3Kimi K2.6
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)LiveBench Data AnalysisLiveBench Data AnalysisLiveBench IFLiveBench IFLiveBench LanguageLiveBench LanguageLiveBench ReasoningLiveBench ReasoningGPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMMMU ProMMMU ProSimpleQA VerifiedSimpleQA VerifiedMATHSFrontierMath (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 MigrationLiveCodeBenchLiveCodeBenchProgramBenchProgramBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1WeirdMLWeirdMLAGENTSDTBenchDTBenchFurniture assemblyFurniture assemblyLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)CorpFin v2CorpFin v2EMBEMBLegalBenchLegalBenchLegal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribeMortgageTaxMortgageTaxPublic Benefits Bench v1.1Public Benefits Bench v1.1Tax Agent BenchTax Agent BenchTaxEval v2TaxEval v2
Every result as a table
TestKimi K3Kimi K2.6
Reasoning & knowledge
GPQA Diamond (Epoch AI)93.1%90.8%
LiveBench Data Analysis78.7%65.1%
LiveBench IF71.4%64.4%
LiveBench Language85.5%75.1%
LiveBench Reasoning90.7%79.4%
GPQA Diamond (Vals AI)92.9%89.1%
MMLU Pro88.0%87.6%
MMMU Pro88.1%86.3%
SimpleQA Verified50.6%34.9%
Maths
FrontierMath (tiers 1-3)72.2%57.2%
AIME-style maths (OTIS mock)97.2%96.1%
LiveBench Mathematics84.4%84.3%
Chess puzzles37.0%20.0%
FrontierMath (tier 4)39.0%25.6%
Coding
LiveBench Agentic Coding62.2%46.9%
LiveBench Coding81.5%78.6%
Code Migration16.1%27.8%
LiveCodeBench87.2%86.8%
ProgramBench2.0%0.0%
SWE-bench93.4%76.2%
Vibe Code Bench v1.185.0%37.9%
WeirdML82.6%55.9%
Agents
DTBench91.2%90.9%
Furniture assembly34.2%21.7%
LMCA52.7%37.3%
Mystery game puzzles26.0%18.0%
Professional work
Finance Agent (v2)53.1%44.9%
CorpFin v271.6%66.7%
EMB66.7%57.9%
LegalBench86.2%84.7%
Legal Research Bench46.2%15.9%
MedCode49.4%40.1%
MedScribe88.0%78.1%
MortgageTax66.3%65.8%
Public Benefits Bench v1.168.2%56.6%
Tax Agent Bench33.4%12.4%
TaxEval v275.7%74.7%

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

This page as a chartDownload PNG