The Model Index
Up to four models

Magistral Small 1.2 vs Llama 4 Maverick

On the index (GPT-4 = 100), Magistral Small 1.2 scores 117 and Llama 4 Maverick 116. 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 Magistral Small 1.2
Presets
Magistral Small 1.2
117101–133
WeightsOpen
ReleasedSep 2025
Price in / out–
Context–
Core tests taken1 of 9
Llama 4 Maverick
116100–132
WeightsOpen
ReleasedApr 2025
Price in / out$0.35 / $1.0
Context524K
Core tests taken3 of 9

Magistral Small 1.2 and Llama 4 Maverick are too close to call (1 point apart, within the uncertainty), ahead on 0 of 1 shared core tests.

Test by testthird-party results

Magistral Small 1.2Llama 4 Maverick
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 ProMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)MGSMMGSMCODINGLiveCodeBenchLiveCodeBenchAGENTSDTBenchDTBenchPROFESSIONAL WORKCorpFin v2CorpFin v2LegalBenchLegalBenchMortgageTaxMortgageTaxTaxEval v2TaxEval v2
Every result as a table
TestMagistral Small 1.2Llama 4 Maverick
Reasoning & knowledge
GPQA Diamond (Epoch AI)47.6%67.0%
GPQA Diamond (Vals AI)58.3%69.4%
MMLU Pro62.1%79.4%
MMMU Pro65.2%71.7%
Maths
AIME-style maths (OTIS mock)28.1%20.6%
MGSM86.3%92.4%
Coding
LiveCodeBench72.1%47.3%
Agents
DTBench61.3%61.9%
Professional work
CorpFin v244.0%49.7%
LegalBench40.0%77.8%
MortgageTax62.1%58.5%
TaxEval v260.3%66.6%

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

This page as a chartDownload PNG