The Model Index
Up to four models

Kimi K2.6 vs Grok 4.3

On the index (GPT-4 = 100), Kimi K2.6 scores 152 and Grok 4.3 135. 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 K2.6
Presets
Kimi K2.6
152136–169
WeightsOpen
ReleasedApr 2026
Price in / out$0.65 / $3.41
Context262K
Core tests taken4 of 9
Grok 4.3
135115–156
WeightsClosed
ReleasedApr 2026
Price in / out$1.25 / $2.5
Context1M
Core tests taken1 of 9

Kimi K2.6 leads Grok 4.3 by 17 points, ahead on 1 of 1 shared core tests, at a similar price.

Test by testthird-party results

Kimi K2.6Grok 4.3
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 ProMATHSLiveBench MathematicsLiveBench MathematicsCODINGLiveBench Agentic CodingLiveBench Agentic CodingLiveBench CodingLiveBench CodingCode MigrationCode MigrationLiveCodeBenchLiveCodeBenchProgramBenchProgramBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1PROFESSIONAL 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 K2.6Grok 4.3
Reasoning & knowledge
LiveBench Data Analysis65.1%55.8%
LiveBench IF64.4%62.7%
LiveBench Language75.1%73.6%
LiveBench Reasoning79.4%70.8%
GPQA Diamond (Vals AI)89.1%91.4%
MMLU Pro87.6%85.8%
MMMU Pro86.3%83.1%
Maths
LiveBench Mathematics84.3%84.3%
Coding
LiveBench Agentic Coding46.9%18.5%
LiveBench Coding78.6%69.9%
Code Migration27.8%6.8%
LiveCodeBench86.8%84.5%
ProgramBench0.0%0.0%
SWE-bench76.2%71.4%
Vibe Code Bench v1.137.9%19.4%
Professional work
Finance Agent (v2)44.9%37.7%
CorpFin v266.7%68.5%
EMB57.9%18.4%
LegalBench84.7%84.5%
Legal Research Bench15.9%15.4%
MedCode40.1%38.1%
MedScribe78.1%74.4%
MortgageTax65.8%48.3%
Public Benefits Bench v1.156.6%51.7%
Tax Agent Bench12.4%6.2%
TaxEval v274.7%70.8%

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

This page as a chartDownload PNG