The Model Index
Up to four models

GPT-5.4 vs MiniMax-M2.5

On the index (GPT-4 = 100), GPT-5.4 scores 166 and MiniMax-M2.5 144. 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-5.4
Presets
GPT-5.4
166150–182
WeightsClosed
ReleasedMar 2026
Price in / out$2.5 / $15
Context1.05M
Core tests taken7 of 9
MiniMax-M2.5
144128–160
WeightsOpen
ReleasedFeb 2026
Price in / out$0.29 / $1.2
Context198K
Core tests taken1 of 9

GPT-5.4 leads MiniMax-M2.5 by 22 points, ahead on 1 of 1 shared core tests, at 11× the price.

Test by testthird-party results

GPT-5.4MiniMax-M2.5
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProCL-benchCL-benchCODINGLiveCodeBenchLiveCodeBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1PROFESSIONAL WORKCorpFin v2CorpFin v2LegalBenchLegalBenchTaxEval v2TaxEval v2NOVEL PROBLEMSARC-AGI-2ARC-AGI-2ARC-AGI-1ARC-AGI-1
Every result as a table
TestGPT-5.4MiniMax-M2.5
Reasoning & knowledge
GPQA Diamond (Vals AI)91.7%82.1%
MMLU Pro87.5%80.1%
CL-bench27.9%11.4%
Coding
LiveCodeBench84.1%79.2%
SWE-bench78.2%74.2%
Vibe Code Bench v1.167.4%14.8%
Professional work
CorpFin v265.3%59.6%
LegalBench86.0%80.0%
TaxEval v274.0%68.2%
Novel problems
ARC-AGI-274.0%4.9%
ARC-AGI-193.7%63.7%
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