ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Gemma 4 E2B IT vs GPT-5.4 nano vs Schematron V2 Turbo

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 E2B IT

    Released Apr 2, 2026

    77/100
    • ECI—
    • Price$0.04 / $0.08
    • Context131K
  2. OpenAI

    GPT-5.4 nano

    Released Mar 17, 2026

    62/100
    • ECI146.3
    • Price$0.20 / $1.25
    • Context400K
  3. Inference.net

    Schematron V2 Turbo

    Released Apr 16, 2026

    56/100
    • ECI—
    • Price$0.03 / $0.15
    • Context128K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Gemma 4 E2B IT 77/100, GPT-5.4 nano 62/100, Schematron V2 Turbo 56/100) 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 priceGemma 4 E2B ITGemma 4 E2B IT $0.05 · Schematron V2 Turbo $0.06 · GPT-5.4 nano $0.463 per 1M tokens (3:1 blend)
  • Longest contextGPT-5.4 nanoGPT-5.4 nano 400,000 · Gemma 4 E2B IT 131,072 · Schematron V2 Turbo 128,000 tokens
  • Widest inputsGemma 4 E2B ITGemma 4 E2B IT: Text, Images, Audio · GPT-5.4 nano: Text, Images · Schematron V2 Turbo: Text
  • Self-hostingGemma 4 E2B ITPublishes downloadable weights
How the score is built
MeasureWeightGemma 4 E2B ITGPT-5.4 nanoSchematron V2 Turbo
Price50%10063100
Inputs & features30%70700
Context window20%325032
Specs & price only100%77/10062/10056/100

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 E2B IT vs GPT-5.4 nano vs Schematron V2 Turbo specifications side by side
SpecificationGemma 4 E2B ITGoogleGPT-5.4 nanoOpenAISchematron V2 TurboInference.net
Capability
Capabilities Index (ECI)—146.3—
ECI rank—#86 of 158—
GPQA DiamondGraduate-level science questions—78.5%—
FrontierMath Tiers 1–3Research-level mathematics—44.9%—
OTIS Mock AIME 2024–2025Competition mathematics—87.8%—
SimpleQA VerifiedShort factual questions—11.7%—
Price per million tokens
Input$0.04$0.20$0.03 (best)
Output$0.08 (best)$1.25$0.15
Cached input—$0.02—
Blended (3:1)$0.05 (best)$0.463$0.06
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersOfficial OpenAI APIMedian of 5 providers
Limits
Context window131,072 tokens400,000 tokens (best)128,000 tokens
Max output8,192 tokens128,000 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsNoNoNo
AudioYesNoNo
VideoNoNoNo
ReasoningYesYeslow · medium · high · xhighNo
Tool callingYesYesNo
Structured outputNoYesNo
Availability
WeightsOpenProprietaryProprietary
API model ID—gpt-5.4-nano—
API providers136 (best)5
ReleasedApr 2, 2026Mar 17, 2026Apr 16, 2026
Knowledge cutoff—Aug 31, 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.

  • Gemma 4 E2B IT$0.56
  • GPT-5.4 nano$4.50
  • Schematron V2 Turbo$0.60
04 — Questions

Which should you choose?

Which is better: Gemma 4 E2B IT, GPT-5.4 nano or Schematron V2 Turbo?

There is not enough shared capability evidence to name an overall winner. The scores (Gemma 4 E2B IT 77/100, GPT-5.4 nano 62/100, Schematron V2 Turbo 56/100) 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 E2B IT, GPT-5.4 nano or Schematron V2 Turbo?

Gemma 4 E2B IT is cheaper at $0.04 input / $0.08 output per million tokens (median across 1 API provider). Schematron V2 Turbo costs $0.03 input / $0.15 output per million tokens (median across 5 API providers); GPT-5.4 nano costs $0.20 input / $1.25 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $0.05 per million tokens for Gemma 4 E2B IT versus $0.06 for Schematron V2 Turbo (1.2× as much) and $0.463 for GPT-5.4 nano (9.3× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Gemma 4 E2B IT has not been scored yet, GPT-5.4 nano has an ECI of 146.3 and Schematron V2 Turbo has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Gemma 4 E2B IT, GPT-5.4 nano and Schematron V2 Turbo yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Schematron V2 Turbo does not support tool calling, which most coding agents need.

Which has the bigger context window?

GPT-5.4 nano has the largest context window at 400,000 tokens, against 131,072 for Gemma 4 E2B IT and 128,000 for Schematron V2 Turbo. Maximum output per response: Gemma 4 E2B IT up to 8,192, GPT-5.4 nano up to 128,000, Schematron V2 Turbo up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Gemma 4 E2B IT accepts text, images and audio; GPT-5.4 nano accepts text and images; Schematron V2 Turbo accepts text. Gemma 4 E2B IT handles the widest range of inputs.

Are any of these open source?

Gemma 4 E2B IT publishes its weights and can be self-hosted; GPT-5.4 nano and Schematron V2 Turbo is proprietary.

Which is newer?

Schematron V2 Turbo is the newest, released Apr 16, 2026. Gemma 4 E2B IT came out Apr 2, 2026; GPT-5.4 nano came out Mar 17, 2026. Knowledge cutoff: GPT-5.4 nano Aug 31, 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 18, 2026.