The Model Index
Up to four models

Grok 4 vs MiniMax-M3

On the index (GPT-4 = 100), Grok 4 scores 148 and MiniMax-M3 147. 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
Presets
Grok 4
148132–164
WeightsClosed
ReleasedJul 2025
Price in / out–
Context–
Core tests taken2 of 9
MiniMax-M3
147131–164
WeightsOpen
ReleasedJun 2026
Price in / out$0.30 / $1.2
Context1.05M
Core tests taken4 of 9

Grok 4 and MiniMax-M3 are too close to call (1 point apart, within the uncertainty).

Test by testthird-party results

Grok 4MiniMax-M3
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMMMU ProMMMU ProSimpleBenchSimpleBenchCODINGLiveCodeBenchLiveCodeBenchSWE-benchSWE-benchPROFESSIONAL WORKCorpFin v2CorpFin v2LegalBenchLegalBenchMedCodeMedCodeMedScribeMedScribeMortgageTaxMortgageTaxTaxEval v2TaxEval v2
Every result as a table
TestGrok 4MiniMax-M3
Reasoning & knowledge
GPQA Diamond (Vals AI)88.1%92.7%
MMLU Pro85.3%84.2%
MMMU Pro76.3%81.2%
SimpleBench60.5%45.8%
Coding
LiveCodeBench83.3%82.2%
SWE-bench57.8%75.0%
Professional work
CorpFin v266.0%68.1%
LegalBench83.2%85.4%
MedCode38.1%46.3%
MedScribe78.1%87.3%
MortgageTax44.5%68.4%
TaxEval v265.1%72.7%
Task length · METR40 sec

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

This page as a chartDownload PNG