ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Gemma 4 12B IT vs Granite 4.2 8B vs Schematron V2 Small

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

Price in rating: Included · Exclude price

  1. Google

    Gemma 4 12B IT

    Released Jun 9, 2026

    73/100
    • ECI—
    • Price$0.05 / $0.25
    • Context262K
  2. IBM

    Granite 4.2 8B

    Released Aug 25, 2026

    65/100
    • ECI—
    • Price$0.06 / $0.15
    • Context131K
  3. Inference.net

    Schematron V2 Small

    Released Apr 16, 2026

    53/100
    • ECI—
    • Price$0.05 / $0.23
    • Context128K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Gemma 4 12B IT 73/100, Granite 4.2 8B 65/100, Schematron V2 Small 53/100) 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.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceGranite 4.2 8BGranite 4.2 8B $0.083 · Schematron V2 Small $0.095 · Gemma 4 12B IT $0.10 per 1M tokens (3:1 blend)
  • Longest contextGemma 4 12B ITGemma 4 12B IT 262,144 · Granite 4.2 8B 131,072 · Schematron V2 Small 128,000 tokens
  • Widest inputsGemma 4 12B ITGemma 4 12B IT: Text, Images · Granite 4.2 8B: Text · Schematron V2 Small: Text
  • Self-hostingGemma 4 12B IT and Granite 4.2 8BPublishes downloadable weights
How the score is built
MeasureWeightGemma 4 12B ITGranite 4.2 8BSchematron V2 Small
Price50%939794
Inputs & features30%60350
Context window20%433232
Specs & price only100%73/10065/10053/100

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. Dashes mean the data is not published.

Gemma 4 12B IT vs Granite 4.2 8B vs Schematron V2 Small specifications side by side
SpecificationGemma 4 12B ITGoogleGranite 4.2 8BIBMSchematron V2 SmallInference.net
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.05 (best)$0.06$0.05 (best)
Output$0.25$0.15 (best)$0.23
Cached input———
Blended (3:1)$0.10$0.083 (best)$0.095
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 3 providersMedian of 7 providersMedian of 5 providers
Limits
Context window262,144 tokens (best)131,072 tokens128,000 tokens
Max output32,768 tokens117,964 tokens (best)4,096 tokens
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesNo
Tool callingYesYesNo
Structured outputNoNoNo
Availability
WeightsOpenOpenProprietary
API model ID———
API providers37 (best)5
ReleasedJun 9, 2026Aug 25, 2026Apr 16, 2026
Knowledge cutoff———
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.

  • Gemma 4 12B IT$1.00
  • Granite 4.2 8B$0.90
  • Schematron V2 Small$0.96
04 — Questions

Which should you choose?

Which is better: Gemma 4 12B IT, Granite 4.2 8B or Schematron V2 Small?

There is not enough shared capability evidence to name an overall winner. The scores (Gemma 4 12B IT 73/100, Granite 4.2 8B 65/100, Schematron V2 Small 53/100) 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.

Which is cheaper, Gemma 4 12B IT, Granite 4.2 8B or Schematron V2 Small?

Granite 4.2 8B is cheaper at $0.06 input / $0.15 output per million tokens (median across 7 API providers). Schematron V2 Small costs $0.05 input / $0.23 output per million tokens (median across 5 API providers); Gemma 4 12B IT costs $0.05 input / $0.25 output per million tokens (median across 3 API providers). At a typical mix of three input tokens to one output token, that is $0.083 per million tokens for Granite 4.2 8B versus $0.095 for Schematron V2 Small (1.2× as much) and $0.10 for Gemma 4 12B IT (1.2× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Gemma 4 12B IT has not been scored yet, Granite 4.2 8B has not been scored yet and Schematron V2 Small has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Gemma 4 12B IT, Granite 4.2 8B and Schematron V2 Small yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Schematron V2 Small does not support tool calling, which most coding agents need.

Which has the bigger context window?

Gemma 4 12B IT has the largest context window at 262,144 tokens, against 131,072 for Granite 4.2 8B and 128,000 for Schematron V2 Small. Maximum output per response: Gemma 4 12B IT up to 32,768, Granite 4.2 8B up to 117,964, Schematron V2 Small up to 4,096 tokens.

Which can read images, PDFs, audio or video?

Gemma 4 12B IT accepts text and images; Granite 4.2 8B accepts text; Schematron V2 Small accepts text. Gemma 4 12B IT handles the widest range of inputs.

Are any of these open source?

Gemma 4 12B IT and Granite 4.2 8B publishes its weights and can be self-hosted; Schematron V2 Small is proprietary.

Which is newer?

Granite 4.2 8B is the newest, released Aug 25, 2026. Gemma 4 12B IT came out Jun 9, 2026; Schematron V2 Small came out Apr 16, 2026.

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 18, 2026.