The Model Index
Up to four models

Grok 4.20 vs Kimi K2.5

On the index (GPT-4 = 100), Grok 4.20 scores 156 and Kimi K2.5 145. 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 Grok 4.20
Presets
Grok 4.20
156140–172
WeightsClosed
ReleasedFeb 2026
Price in / out$1.25 / $2.5
Context2M
Core tests taken4 of 9
Kimi K2.5
145130–161
WeightsOpen
ReleasedJan 2026
Price in / out$0.50 / $2.5
Context262K
Core tests taken5 of 9

Grok 4.20 leads Kimi K2.5 by 11 points, ahead on 2 of 3 shared core tests, at 1.6× the price.

Test by testthird-party results

Grok 4.20Kimi K2.5
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)GPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMMMU ProMMMU ProCL-benchCL-benchSimpleQA VerifiedSimpleQA VerifiedMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)CODINGCode MigrationCode MigrationLiveCodeBenchLiveCodeBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1WeirdMLWeirdMLPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)CorpFin v2CorpFin v2EMBEMBLegal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribeMortgageTaxMortgageTaxTaxEval v2TaxEval v2NOVEL PROBLEMSARC-AGI-2ARC-AGI-2ARC-AGI-1ARC-AGI-1
Every result as a table
TestGrok 4.20Kimi K2.5
Reasoning & knowledge
GPQA Diamond (Epoch AI)89.3%87.6%
GPQA Diamond (Vals AI)88.6%84.1%
MMLU Pro86.3%85.9%
MMMU Pro83.5%84.3%
CL-bench22.2%19.3%
SimpleQA Verified30.2%34.3%
Maths
AIME-style maths (OTIS mock)92.2%92.2%
Coding
Code Migration0.3%7.0%
LiveCodeBench84.3%83.9%
SWE-bench72.2%70.0%
Vibe Code Bench v1.14.1%17.5%
WeirdML52.3%45.6%
Professional work
Finance Agent (v2)28.5%35.8%
CorpFin v263.7%68.3%
EMB11.7%28.5%
Legal Research Bench13.9%15.9%
MedCode32.2%39.3%
MedScribe63.4%76.4%
MortgageTax45.4%66.5%
TaxEval v274.1%74.2%
Novel problems
ARC-AGI-265.1%11.8%
ARC-AGI-189.5%65.3%

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

This page as a chartDownload PNG