The Model Index
Up to four models

GPT-4o mini vs Mistral Large

On the index (GPT-4 = 100), GPT-4o mini scores 104 and Mistral Large 100. 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-4o mini
Presets
GPT-4o mini
10487–120
WeightsClosed
ReleasedJul 2024
Price in / out$0.15 / $0.60
Context128K
Core tests taken3 of 9
Mistral Large
10084–117
WeightsClosed
ReleasedFeb 2024
Price in / out$2.0 / $6.0
Context128K
Core tests taken1 of 9

GPT-4o mini and Mistral Large are too close to call (3 points apart, within the uncertainty), ahead on 0 of 1 shared core tests, and costs 11× less.

Test by testthird-party results

GPT-4o miniMistral Large
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MMLU (HELM runs)MMLU (HELM runs)GPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)MATH (level 5)MATH (level 5)MATH 500MATH 500MGSMMGSMCODINGLiveCodeBenchLiveCodeBenchAGENTSDTBenchDTBenchPROFESSIONAL WORKTaxEval v2TaxEval v2
Every result as a table
TestGPT-4o miniMistral Large
Reasoning & knowledge
GPQA Diamond (Epoch AI)37.7%38.8%
MMLU (HELM runs)76.7%68.8%
GPQA Diamond (Vals AI)44.2%47.7%
MMLU Pro62.7%69.7%
Maths
AIME-style maths (OTIS mock)6.9%1.9%
MATH (level 5)52.6%24.5%
MATH 50072.6%74.4%
MGSM86.2%87.2%
Coding
LiveCodeBench26.4%37.1%
Agents
DTBench54.4%55.9%
Professional work
TaxEval v260.6%63.8%

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

This page as a chartDownload PNG