The Model Index
Up to four models

GPT-5.2 vs MiniMax-M2.1

On the index (GPT-4 = 100), GPT-5.2 scores 162 and MiniMax-M2.1 135. 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 GPT-5.2
Presets
GPT-5.2
162146–178
WeightsClosed
ReleasedDec 2025
Price in / out$1.75 / $14
Context400K
Core tests taken6 of 9
MiniMax-M2.1
135117–153
WeightsOpen
ReleasedDec 2025
Price in / out–
Context–
Core tests taken0 of 9

GPT-5.2 leads MiniMax-M2.1 by 27 points.

Test by testthird-party results

GPT-5.2MiniMax-M2.1
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProSimpleBenchSimpleBenchMATHSMGSMMGSMCODINGTerminal-Bench 2.0 (Terminus 2 runs)Terminal-Bench 2.0 (Terminus 2 runs)LiveCodeBenchLiveCodeBenchSWE-benchSWE-benchPROFESSIONAL WORKCorpFin v2CorpFin v2LegalBenchLegalBenchMedCodeMedCodeMedScribeMedScribeTaxEval v2TaxEval v2
Every result as a table
TestGPT-5.2MiniMax-M2.1
Reasoning & knowledge
GPQA Diamond (Vals AI)91.7%78.5%
MMLU Pro86.2%87.1%
SimpleBench45.8%34.7%
Maths
MGSM94.0%87.8%
Coding
Terminal-Bench 2.0 (Terminus 2 runs)54.0%29.2%
LiveCodeBench85.4%81.8%
SWE-bench75.8%74.8%
Professional work
CorpFin v265.9%58.9%
LegalBench82.8%75.4%
MedCode49.8%34.1%
MedScribe84.4%80.8%
TaxEval v275.8%66.3%
Task length · METR45 sec

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

This page as a chartDownload PNG