ZMIME
Comparison · 3 models · Updated Oct 4, 2026

GPT-5.4 mini vs Mistral Medium 3 vs Grok 4.3

Grok 4.3 comes out ahead, 67 to 63 and 53 on our weighted score, though Mistral Medium 3 is 2× cheaper per token.

  1. OpenAI

    GPT-5.4 mini

    Released Mar 17, 2026

    63/100
    • ECI148.8
    • Price$0.75 / $4.50
    • Context400K
    Full specs Remove GPT-5.4 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. Our pick

    xAI

    Grok 4.3

    Released Apr 17, 2026

    67/100
    • ECI149.2
    • Price$1.25 / $2.50
    • Context1M
    Full specs Remove Grok 4.3
01 — Verdict

Grok 4.3 is our pick

Grok 4.3 is the better all-round choice, scoring 67/100 against GPT-5.4 mini (63) and Mistral Medium 3 (53). It leads on inputs & features and context window. Mistral Medium 3 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityGrok 4.3Capabilities Index (ECI): Grok 4.3 149.2 · GPT-5.4 mini 148.8 · Mistral Medium 3 134.1
  • Lowest priceMistral Medium 3Mistral Medium 3 $0.80 · Grok 4.3 $1.56 · GPT-5.4 mini $1.69 per 1M tokens (3:1 blend)
  • Longest contextGrok 4.3Grok 4.3 1,000,000 · GPT-5.4 mini 400,000 · Mistral Medium 3 131,072 tokens
  • Widest inputsGrok 4.3GPT-5.4 mini: Text, Images · Mistral Medium 3: Text, Images · Grok 4.3: Text, Images, PDFs
  • Self-hostingNo open weightsAll three are available only through APIs
How the score is built
MeasureWeightGPT-5.4 miniMistral Medium 3Grok 4.3
CapabilityCapabilities Index (ECI)50%775877
Price25%395441
Inputs & features15%705080
Context window10%442460
Overall100%63/10053/10067/100
02 — Side by side

Every spec in one table

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

GPT-5.4 mini vs Mistral Medium 3 vs Grok 4.3 specifications side by side
SpecificationGPT-5.4 miniOpenAIMistral Medium 3Mistral AIGrok 4.3xAI
Capability
Capabilities Index (ECI)148.8134.1149.2 (best)
ECI rank#56 of 148#117 of 148#55 of 148 (best)
GPQA DiamondGraduate-level science questions86.9%59.5%88.8% (best)
FrontierMath Tiers 1–3Research-level mathematics51.2% (best)—42.8%
OTIS Mock AIME 2024–2025Competition mathematics88.9%32.2%93.3% (best)
SimpleQA VerifiedShort factual questions29.4%—33.2% (best)
Price per million tokens
Input$0.75$0.40 (best)$1.25
Output$4.50$2.00 (best)$2.50
Cached input$0.075 (best)—$0.20
Blended (3:1)$1.69$0.80 (best)$1.56
Long-context rateSame rateSame rateOver 200K: $2.50 / $5.00
Price sourceOfficial OpenAI APIOfficial Mistral APIOfficial xAI API
Limits
Context window400,000 tokens131,072 tokens1,000,000 tokens (best)
Max output128,000 tokens131,072 tokens (best)30,000 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoNoYes
AudioNoNoNo
VideoNoNoNo
ReasoningYeslow · medium · high · xhighNoYeslow · medium · high
Tool callingYesYesYes
Structured outputYesNoYes
Availability
WeightsProprietaryProprietaryProprietary
API model IDgpt-5.4-minimistral-medium-2505grok-4.3
API providers29 (best)527
ReleasedMar 17, 2026May 7, 2025Apr 17, 2026
Knowledge cutoffAug 31, 2025May 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-5.4 mini$16.50
  • Mistral Medium 3$8.00
  • Grok 4.3$17.50
04 — Questions

Which should you choose?

Which is better: GPT-5.4 mini, Mistral Medium 3 or Grok 4.3?

Grok 4.3 is the better all-round choice, scoring 67/100 against GPT-5.4 mini (63) and Mistral Medium 3 (53). It leads on inputs & features and context window. Mistral Medium 3 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, GPT-5.4 mini, Mistral Medium 3 or Grok 4.3?

Mistral Medium 3 is cheaper at $0.40 input / $2.00 output per million tokens (official Mistral API price). Grok 4.3 costs $1.25 input / $2.50 output per million tokens (official xAI API price); GPT-5.4 mini costs $0.75 input / $4.50 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $0.80 per million tokens for Mistral Medium 3 versus $1.56 for Grok 4.3 (2× as much) and $1.69 for GPT-5.4 mini (2.1× as much).

Which scores higher on benchmarks?

Grok 4.3 scores higher on the Capabilities Index (ECI): Grok 4.3 149.2 (#55 of 148), GPT-5.4 mini 148.8 (#56 of 148) and Mistral Medium 3 134.1 (#117 of 148). The confidence ranges of the top two overlap (147.6–150.8 vs 147.1–150.5), so treat the gap as small. On individual benchmarks: GPQA Diamond — Grok 4.3 88.8%, GPT-5.4 mini 86.9%, Mistral Medium 3 59.5%; OTIS Mock AIME 2024–2025 — Grok 4.3 93.3%, GPT-5.4 mini 88.9%, Mistral Medium 3 32.2%.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-5.4 mini, Mistral Medium 3 and Grok 4.3 yet, so there is no like-for-like coding score. On overall capability, Grok 4.3 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.

Which has the bigger context window?

Grok 4.3 has the largest context window at 1,000,000 tokens, against 400,000 for GPT-5.4 mini and 131,072 for Mistral Medium 3. Maximum output per response: GPT-5.4 mini up to 128,000, Mistral Medium 3 up to 131,072, Grok 4.3 up to 30,000 tokens.

Which can read images, PDFs, audio or video?

GPT-5.4 mini accepts text and images; Mistral Medium 3 accepts text and images; Grok 4.3 accepts text, images and PDFs. Grok 4.3 handles the widest range of inputs.

Are any of these open source?

No. GPT-5.4 mini, Mistral Medium 3 and Grok 4.3 are proprietary and only available through APIs and apps.

Which is newer?

Grok 4.3 is the newest, released Apr 17, 2026. GPT-5.4 mini came out Mar 17, 2026; Mistral Medium 3 came out May 7, 2025. Knowledge cutoff: GPT-5.4 mini Aug 31, 2025, 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