ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Gemma 4 26B A4B IT vs Gemma 4 E4B IT vs Step 3.5 Flash 2603

Gemma 4 E4B IT comes out ahead, 76 to 71 and 62 on our weighted score, and it is the cheaper option too.

  1. Google

    Gemma 4 26B A4B IT

    Released Apr 2, 2026

    71/100
    • ECI141.9
    • Price$0.10 / $0.38
    • Context262K
  2. Our pick

    Google

    Gemma 4 E4B IT

    Released Apr 2, 2026

    76/100
    • ECI—
    • Price$0.11 / $0.15
    • Context131K
  3. StepFun

    Step 3.5 Flash 2603

    Released Apr 2, 2026

    62/100
    • ECI—
    • Price$0.10 / $0.30
    • Context256K
01 — Verdict

Gemma 4 E4B IT is our pick

Gemma 4 E4B IT is the better all-round choice, scoring 76/100 against Gemma 4 26B A4B IT (71) and Step 3.5 Flash 2603 (62). It leads on price and inputs & features. 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 E4B ITGemma 4 E4B IT $0.12 · Step 3.5 Flash 2603 $0.15 · Gemma 4 26B A4B IT $0.17 per 1M tokens (3:1 blend)
  • Longest contextGemma 4 26B A4B ITGemma 4 26B A4B IT 262,144 · Step 3.5 Flash 2603 256,000 · Gemma 4 E4B IT 131,072 tokens
  • Widest inputsGemma 4 E4B ITGemma 4 26B A4B IT: Text, Images · Gemma 4 E4B IT: Text, Images, Audio · Step 3.5 Flash 2603: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightGemma 4 26B A4B ITGemma 4 E4B ITStep 3.5 Flash 2603
Price50%869489
Inputs & features30%708035
Context window20%372436
Overall100%71/10076/10062/100

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 26B A4B IT vs Gemma 4 E4B IT vs Step 3.5 Flash 2603 specifications side by side
SpecificationGemma 4 26B A4B ITGoogleGemma 4 E4B ITGoogleStep 3.5 Flash 2603StepFun
Capability
Capabilities Index (ECI)141.9——
ECI rank#93 of 148——
GPQA DiamondGraduate-level science questions73.2%——
OTIS Mock AIME 2024–2025Competition mathematics82.2%——
Price per million tokens
Input$0.10 (best)$0.11$0.10 (best)
Output$0.38$0.15 (best)$0.30
Cached input——$0.02
Blended (3:1)$0.17$0.12 (best)$0.15
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 23 providersMedian of 2 providersOfficial StepFun (Global) API
Limits
Context window262,144 tokens (best)131,072 tokens256,000 tokens
Max output32,768 tokens8,192 tokens256,000 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsNoNoNo
AudioNoYesNo
VideoNoNoNo
ReasoningYesYesYeslow · high
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsOpenOpenOpen
API model IDgemma-4-26b-a4b-it—step-3.5-flash-2603
API providers26 (best)23
ReleasedApr 2, 2026Apr 2, 2026Apr 2, 2026
Knowledge cutoff——Jan 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 26B A4B IT$1.76
  • Gemma 4 E4B IT$1.40
  • Step 3.5 Flash 2603$1.60
04 — Questions

Which should you choose?

Which is better: Gemma 4 26B A4B IT, Gemma 4 E4B IT or Step 3.5 Flash 2603?

Gemma 4 E4B IT is the better all-round choice, scoring 76/100 against Gemma 4 26B A4B IT (71) and Step 3.5 Flash 2603 (62). It leads on price and inputs & features. 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 26B A4B IT, Gemma 4 E4B IT or Step 3.5 Flash 2603?

Gemma 4 E4B IT is cheaper at $0.11 input / $0.15 output per million tokens (median across 2 API providers). Step 3.5 Flash 2603 costs $0.10 input / $0.30 output per million tokens (official StepFun (Global) API price); Gemma 4 26B A4B IT costs $0.10 input / $0.38 output per million tokens (median across 23 API providers). At a typical mix of three input tokens to one output token, that is $0.12 per million tokens for Gemma 4 E4B IT versus $0.15 for Step 3.5 Flash 2603 (1.3× as much) and $0.17 for Gemma 4 26B A4B IT (1.4× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Gemma 4 26B A4B IT has an ECI of 141.9, Gemma 4 E4B IT has not been scored yet and Step 3.5 Flash 2603 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Gemma 4 26B A4B IT, Gemma 4 E4B IT and Step 3.5 Flash 2603 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

Gemma 4 26B A4B IT has the largest context window at 262,144 tokens, against 256,000 for Step 3.5 Flash 2603 and 131,072 for Gemma 4 E4B IT. Maximum output per response: Gemma 4 26B A4B IT up to 32,768, Gemma 4 E4B IT up to 8,192, Step 3.5 Flash 2603 up to 256,000 tokens.

Which can read images, PDFs, audio or video?

Gemma 4 26B A4B IT accepts text and images; Gemma 4 E4B IT accepts text, images and audio; Step 3.5 Flash 2603 accepts text. Gemma 4 E4B IT handles the widest range of inputs.

Are any of these open source?

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

Which is newer?

Gemma 4 26B A4B IT is the newest, released Apr 2, 2026. Gemma 4 E4B IT came out Apr 2, 2026; Step 3.5 Flash 2603 came out Apr 2, 2026. Knowledge cutoff: Step 3.5 Flash 2603 Jan 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.