CorX Labs

Head to head

Mistral Medium 3 vs GPT-4.1 mini

Mistral Medium 3 from Mistral AI against GPT-4.1 mini from OpenAI — specification, price and every benchmark both makers have published, in one table.

Benchmarks

GPT-4.1 mini leads

GPT-4.1 mini wins 2 of the 2 benchmarks both models report, Mistral Medium 3 wins 0, consistently. The average gap across shared tests is 4.6 points.

Price

GPT-4.1 mini is cheaper

On a 3:1 input-to-output mix, GPT-4.1 mini costs $0.70 per million tokens against $0.80 for Mistral Medium 3 — a small difference.

What actually differs

  • GPT-4.1 mini takes 1M tokens of context against 131K — 8.0× more room for long documents or a large codebase.

Scorecard

Which is better at what

Maths, coding, reasoning and the rest — one line each, averaged over the benchmarks both models actually report.

Which model scores higher in each capability category, averaged over the benchmarks all of them report.
CategoryMistral Medium 3GPT-4.1 miniBetter at this
ReasoningGPQA Diamond62.4%65.0%GPT-4.1 mini+2.6
MathsNeither model reports thisNot comparable
CodingOnly one model reports thisNot comparable
KnowledgeOnly one model reports thisNot comparable
MultimodalMMMU66.1%72.7%GPT-4.1 mini+6.6
Instruction followingNeither model reports thisNot comparable
Human preferenceNeither model reports thisNot comparable
Categories wonOut of 2 comparable02GPT-4.1 mini

Each category averages only the benchmarks every model here reports, so no one is credited for a test the other did not run. A category with no shared test is marked Not comparable rather than guessed at.

Side by side

Mistral Medium 3 and GPT-4.1 mini, row by row

AttributeMistral Medium 3Mistral AIGPT-4.1 miniOpenAI
Specification
MakerWho built itMistral AIOpenAI
Released2025-052025-04
Context windowHow much can go in at once131,072 tokens1,047,576 tokens
Max output8,192 tokens32,768 tokens
InputText, ImageText, Image
ReasoningSpends extra tokens thinking before it answersNoNo
Tool callingYesYes
Knowledge cutoffNot reported2024-06
LicenceProprietaryProprietary
Open weightsCan you download and run it yourselfNoNo
Price
Input priceUSD per million tokens in$0.40$0.40
Output priceUSD per million tokens out$2.00$1.60
Cached inputNot reported$0.10
Blended 3:1A 3-in-to-1-out million-token mix — a fairer single number than input price alone$0.80$0.70Cheapest
Published benchmarks
MMLU-Pro12,000 reasoning-heavy multiple-choice questions across 14 academic subjects, with ten options instead of four. The harder successor to MMLU.76%Not reported
GPQA Diamond198 graduate-level physics, chemistry and biology questions written to be Google-proof. PhD holders in the matching field score about 65%.62.4%65%Best
SWE-bench Verified500 human-validated GitHub issues from real Python repositories. The model must produce a patch that makes the project's own tests pass.Not reported23.6%
HumanEval164 short Python functions written from a docstring. Saturated at the frontier — kept here for continuity with older models.92.1%Not reported
MMMUCollege-level questions that require reading charts, diagrams, tables and photographs alongside the text.66.1%72.7%Best
LinksFull pageFull page
Row verified2026-082026-08

Where these numbers come from

Every score on this page is a published figure, taken from the model's own card, system card, technical report or release post, or from a public leaderboard. CorX Labs did not run these evaluations. Most are self-reported by the lab that built the model, which means they were produced under that lab's own choice of prompt, scaffold and number of attempts — so treat them as a starting point for a shortlist, not as a settled ranking.

A score someone other than the model's maker measured is marked Independent and names its measurer. Those are the stronger numbers on this page — an outside harness has no reason to flatter anyone — and there are not many of them.

Where a figure has not been published, the cell reads Not reported rather than an estimate. Nothing here is inferred, interpolated or guessed. Each model records the month its row was last checked. Full method and caveats.

Questions

Mistral Medium 3 or GPT-4.1 mini?

Is Mistral Medium 3 better than GPT-4.1 mini?

GPT-4.1 mini wins 2 of the 2 benchmarks both models report, Mistral Medium 3 wins 0, consistently. The average gap across shared tests is 4.6 points.

Which is cheaper, Mistral Medium 3 or GPT-4.1 mini?

On a 3:1 input-to-output mix, GPT-4.1 mini costs $0.70 per million tokens against $0.80 for Mistral Medium 3 — a small difference.

What is the difference between Mistral Medium 3 and GPT-4.1 mini?

GPT-4.1 mini takes 1M tokens of context against 131K — 8.0× more room for long documents or a large codebase.