ZMIME
Comparison · 2 models · Updated Oct 4, 2026

GPT-4o mini vs Mistral Medium 3

GPT-4o mini comes out ahead, 56 to 53 on our weighted score, and it is the cheaper option too.

  1. Our pick

    OpenAI

    GPT-4o mini

    Released Jul 18, 2024

    56/100
    • ECI126.6
    • Price$0.15 / $0.60
    • Context128K
    Full specs Remove GPT-4o mini

  2. Mistral AI

    Mistral Medium 3

    Released May 7, 2025

    53/100
    • ECI134.1
    • Price$0.40 / $2.00
    • Context131K
    Full specs Remove Mistral Medium 3

  3. Add a model

    Make it a three-way comparison.

01 — Verdict

GPT-4o mini is our pick

GPT-4o mini is the better all-round choice, scoring 56/100 against Mistral Medium 3 (53). It leads on price and inputs & features. Mistral Medium 3 wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityMistral Medium 3Capabilities Index (ECI): Mistral Medium 3 134.1 · GPT-4o mini 126.6
  • Lowest priceGPT-4o miniGPT-4o mini $0.263 · Mistral Medium 3 $0.80 per 1M tokens (3:1 blend)
  • Longest contextMistral Medium 3Mistral Medium 3 131,072 · GPT-4o mini 128,000 tokens
  • Widest inputsGPT-4o miniGPT-4o mini: Text, Images, PDFs · Mistral Medium 3: Text, Images
  • Self-hostingNo open weightsBoth are available only through APIs
How the score is built
MeasureWeightGPT-4o miniMistral Medium 3
CapabilityCapabilities Index (ECI)50%4958
Price25%7754
Inputs & features15%7050
Context window10%2424
Overall100%56/10053/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

GPT-4o mini vs Mistral Medium 3 specifications side by side
SpecificationGPT-4o miniOpenAIMistral Medium 3Mistral AI
Capability
Capabilities Index (ECI)126.6134.1 (best)
ECI rank#135 of 148#117 of 148 (best)
GPQA DiamondGraduate-level science questions37.7%59.5% (best)
FrontierMath Tiers 1–3Research-level mathematics0.7%—
OTIS Mock AIME 2024–2025Competition mathematics6.9%32.2% (best)
SimpleQA VerifiedShort factual questions8.3%—
Price per million tokens
Input$0.15 (best)$0.40
Output$0.60 (best)$2.00
Cached input$0.075—
Blended (3:1)$0.263 (best)$0.80
Long-context rateSame rateSame rate
Price sourceOfficial OpenAI APIOfficial Mistral API
Limits
Context window128,000 tokens131,072 tokens (best)
Max output16,384 tokens131,072 tokens (best)
Inputs and features
TextYesYes
ImagesYesYes
PDFsYesNo
AudioNoNo
VideoNoNo
ReasoningNoNo
Tool callingYesYes
Structured outputYesNo
Availability
WeightsProprietaryProprietary
API model IDgpt-4o-minimistral-medium-2505
API providers21 (best)5
ReleasedJul 18, 2024May 7, 2025
Knowledge cutoffSep 2023May 2025
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • GPT-4o mini$2.70
  • Mistral Medium 3$8.00
04 — Questions

Which should you choose?

Which is better: GPT-4o mini or Mistral Medium 3?

GPT-4o mini is the better all-round choice, scoring 56/100 against Mistral Medium 3 (53). It leads on price and inputs & features. Mistral Medium 3 wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, GPT-4o mini or Mistral Medium 3?

GPT-4o mini is cheaper at $0.15 input / $0.60 output per million tokens (official OpenAI API price). Mistral Medium 3 costs $0.40 input / $2.00 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.263 per million tokens for GPT-4o mini versus $0.80 for Mistral Medium 3 (3× as much).

Which scores higher on benchmarks?

Mistral Medium 3 scores higher on the Capabilities Index (ECI): Mistral Medium 3 134.1 (#117 of 148) and GPT-4o mini 126.6 (#135 of 148). Their confidence ranges do not overlap (130.5–135.6 vs 120.5–128.5), so the gap is a real one. On individual benchmarks: GPQA Diamond — Mistral Medium 3 59.5%, GPT-4o mini 37.7%; OTIS Mock AIME 2024–2025 — Mistral Medium 3 32.2%, GPT-4o mini 6.9%.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-4o mini and Mistral Medium 3 yet, so there is no like-for-like coding score. On overall capability, Mistral Medium 3 leads, which tends to carry over to coding, but test on your own codebase. Both support tool calling for agent workflows.

Which has the bigger context window?

Mistral Medium 3 has the largest context window at 131,072 tokens, against 128,000 for GPT-4o mini. Maximum output per response: GPT-4o mini up to 16,384, Mistral Medium 3 up to 131,072 tokens.

Which can read images, PDFs, audio or video?

GPT-4o mini accepts text, images and PDFs; Mistral Medium 3 accepts text and images. GPT-4o mini handles the widest range of inputs.

Are any of these open source?

No. GPT-4o mini and Mistral Medium 3 are proprietary and only available through APIs and apps.

Which is newer?

Mistral Medium 3 is the newest, released May 7, 2025. GPT-4o mini came out Jul 18, 2024. Knowledge cutoff: GPT-4o mini Sep 2023, Mistral Medium 3 May 2025.

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.

05 — Keep comparing

Related comparisons