ZMIME
Comparison · 2 models · Updated Nov 22, 2026

Granite-4.0-H-Small vs Mistral Small 4

No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.

  1. IBM

    Granite-4.0-H-Small

    Released Oct 2, 2025

    62/100
    • ECI—
    • Price$0.064 / $0.265
    • Context131K
  2. Mistral AI

    Mistral Small 4

    Released Mar 16, 2026Latest

    67/100
    • ECI—
    • Price$0.15 / $0.60
    • Context256K
  3. IBM

    Granite-4.0-H-Small

    Released Oct 2, 2025

    34/100
    • ECI—
    • Price$0.064 / $0.265
    • Context131K
  4. Mistral AI

    Mistral Small 4

    Released Mar 16, 2026Latest

    59/100
    • ECI—
    • Price$0.15 / $0.60
    • Context256K
  5. Add a model

    Make it a three-way comparison.

01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Mistral Small 4 67/100, Granite-4.0-H-Small 62/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (Mistral Small 4 59/100, Granite-4.0-H-Small 34/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceGranite-4.0-H-SmallGranite-4.0-H-Small $0.114 · Mistral Small 4 $0.263 per 1M tokens (3:1 blend)
  • Longest contextMistral Small 4Mistral Small 4 256,000 · Granite-4.0-H-Small 131,072 tokens
  • Widest inputsMistral Small 4Granite-4.0-H-Small: Text · Mistral Small 4: Text, Images
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightGranite-4.0-H-SmallMistral Small 4
Price50%9074
Inputs & features30%3570
Context window20%3243
Specs & price only100%62/10067/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

How the score is built
MeasureWeightGranite-4.0-H-SmallMistral Small 4
Inputs & features60%3570
Context window40%3243
Specs only100%34/10059/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.

Granite-4.0-H-Small vs Mistral Small 4 specifications side by side
SpecificationGranite-4.0-H-SmallIBMMistral Small 4Mistral AI
Capability
Capabilities Index (ECI)Not publishedNot published
ECI rankNot publishedNot published
ECI confidence intervalNot publishedNot published
ECI evaluation dateNot publishedNot published
Documented capabilitiesOpen-weight hybrid model for enterprise chat, coding, retrieval-augmented generation, and tool-calling workloadsFast Mistral production model for chat, extraction, and cost-sensitive agents
Model parametersNot publishedNot published
Output modalitiesTextText
Publisher-reported benchmarks
Artificial Analysis Coding IndexPublisher-reported resultNot published24.3indexReported resultJun 1, 2026
SciCodePublisher-reported resultNot published38percent correctReported resultJun 1, 2026
Terminal-Bench HardPublisher-reported resultNot published17.4success rateReported resultJun 1, 2026
Price per million tokens
Input$0.064 (best)$0.15
Output$0.265 (best)$0.60
Cached inputNot published$0.015
Blended (3:1)$0.114 (best)$0.263
Long-context rateSame rateSame rate
Price sourceOfficial watsonx.ai APIOfficial Mistral API
Limits
Context window131,072 tokens256,000 tokens (best)
Max inputNot publishedNot published
Max output131,072 tokens256,000 tokens (best)
Inputs and features
TextYesYes
ImagesNoYes
PDFsNoNo
AudioNoNo
VideoNoNo
ReasoningNoYeshigh
Tool callingYesYes
Structured outputYesYes
File attachmentsNoYes
Temperature controlYesYes
Reasoning controlNot publishedeffort
Availability
WeightsOpenOpen
API model IDibm/granite-4-h-smallmistral-small-2603
API providers120 (best)
ReleasedOct 2, 2025Mar 16, 2026
Knowledge cutoffNot publishedJun 2025
Publisher documentationPublisher documentation · Model weightsPublisher documentation · Model weights
Source metadata updatedOct 2, 2025Mar 16, 2026
Data sourcesmodels.dev · Epoch AImodels.dev · Epoch AI
Catalog checkedNov 22, 2026Nov 22, 2026
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.

  • Granite-4.0-H-Small$1.17
  • Mistral Small 4$2.70
04 — Questions

Which should you choose?

Which is better: Granite-4.0-H-Small or Mistral Small 4?

There is not enough shared capability evidence to name an overall winner. The scores (Mistral Small 4 67/100, Granite-4.0-H-Small 62/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (Mistral Small 4 59/100, Granite-4.0-H-Small 34/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Granite-4.0-H-Small or Mistral Small 4?

Granite-4.0-H-Small is cheaper at $0.064 input / $0.265 output per million tokens (official watsonx.ai API price). Mistral Small 4 costs $0.15 input / $0.60 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.114 per million tokens for Granite-4.0-H-Small versus $0.263 for Mistral Small 4 (2.3× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers both models yet. Granite-4.0-H-Small has not been scored yet and Mistral Small 4 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Granite-4.0-H-Small and Mistral Small 4 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Both support tool calling for agent workflows.

Which has the bigger context window?

Mistral Small 4 has the largest context window at 256,000 tokens, against 131,072 for Granite-4.0-H-Small. Maximum output per response: Granite-4.0-H-Small up to 131,072, Mistral Small 4 up to 256,000 tokens.

Which can read images, PDFs, audio or video?

Granite-4.0-H-Small accepts text; Mistral Small 4 accepts text and images. Mistral Small 4 handles the widest range of inputs.

Are any of these open source?

Yes, both publish their weights, so you can self-host them.

Which is newer?

Mistral Small 4 is the newest, released Mar 16, 2026. Granite-4.0-H-Small came out Oct 2, 2025. Knowledge cutoff: Mistral Small 4 Jun 2025.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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 Nov 22, 2026.This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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 Nov 22, 2026.