ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Step 3.5 Flash 2603 vs Gemma 4 31B IT vs Gemma 4 E4B IT

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. StepFun

    Step 3.5 Flash 2603

    Released Apr 2, 2026

    65/100
    • ECI—
    • Price$0.10 / $0.30
    • Context256K
  2. Google

    Gemma 4 31B IT

    Released Apr 2, 2026

    69/100
    • ECI144.1
    • Price$0.142 / $0.40
    • Context262K
  3. Google

    Gemma 4 E4B IT

    Released Apr 2, 2026

    70/100
    • ECI—
    • Price$0.085 / $0.35
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Gemma 4 E4B IT 70/100, Gemma 4 31B IT 69/100, Step 3.5 Flash 2603 65/100) 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 priceStep 3.5 Flash 2603Step 3.5 Flash 2603 $0.15 · Gemma 4 E4B IT $0.151 · Gemma 4 31B IT $0.206 per 1M tokens (3:1 blend)
  • Longest contextGemma 4 31B ITGemma 4 31B IT 262,144 · Step 3.5 Flash 2603 256,000 · Gemma 4 E4B IT 131,072 tokens
  • Widest inputsGemma 4 E4B ITStep 3.5 Flash 2603: Text · Gemma 4 31B IT: Text, Images · Gemma 4 E4B IT: Text, Images, Audio
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightStep 3.5 Flash 2603Gemma 4 31B ITGemma 4 E4B IT
Price50%857985
Inputs & features30%457070
Context window20%434332
Specs & price only100%65/10069/10070/100

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.

Step 3.5 Flash 2603 vs Gemma 4 31B IT vs Gemma 4 E4B IT specifications side by side
SpecificationStep 3.5 Flash 2603StepFunGemma 4 31B ITGoogleGemma 4 E4B ITGoogle
Capability
Capabilities Index (ECI)—144.1—
ECI rank—#94 of 158—
GPQA DiamondGraduate-level science questions—75.8%—
OTIS Mock AIME 2024–2025Competition mathematics—73.3%—
SimpleQA VerifiedShort factual questions—10.4%—
Price per million tokens
Input$0.10$0.142$0.085 (best)
Output$0.30 (best)$0.40$0.35
Cached input$0.02——
Blended (3:1)$0.15 (best)$0.206$0.151
Long-context rateSame rateSame rateSame rate
Price sourceOfficial StepFun (Global) APIMedian of 42 providersMedian of 2 providers
Limits
Context window256,000 tokens262,144 tokens (best)131,072 tokens
Max output256,000 tokens (best)32,768 tokens8,192 tokens
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoNoNo
AudioNoNoYes
VideoNoNoNo
ReasoningYeslow · highYesYes
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsOpenOpenOpen
API model IDstep-3.5-flash-2603gemma-4-31b-it—
API providers352 (best)3
ReleasedApr 2, 2026Apr 2, 2026Apr 2, 2026
Knowledge cutoffJan 2025Jan 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.

  • Step 3.5 Flash 2603$1.60
  • Gemma 4 31B IT$2.22
  • Gemma 4 E4B IT$1.55
04 — Questions

Which should you choose?

Which is better: Step 3.5 Flash 2603, Gemma 4 31B IT or Gemma 4 E4B IT?

There is not enough shared capability evidence to name an overall winner. The scores (Gemma 4 E4B IT 70/100, Gemma 4 31B IT 69/100, Step 3.5 Flash 2603 65/100) 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, Step 3.5 Flash 2603, Gemma 4 31B IT or Gemma 4 E4B IT?

Step 3.5 Flash 2603 is cheaper at $0.10 input / $0.30 output per million tokens (official StepFun (Global) API price). Gemma 4 E4B IT costs $0.085 input / $0.35 output per million tokens (median across 2 API providers); Gemma 4 31B IT costs $0.142 input / $0.40 output per million tokens (median across 42 API providers; free on Google). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Step 3.5 Flash 2603 versus $0.151 for Gemma 4 E4B IT (1× as much) and $0.206 for Gemma 4 31B IT (1.4× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Step 3.5 Flash 2603 has not been scored yet, Gemma 4 31B IT has an ECI of 144.1 and Gemma 4 E4B IT has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Step 3.5 Flash 2603, Gemma 4 31B IT and Gemma 4 E4B IT 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 31B 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: Step 3.5 Flash 2603 up to 256,000, Gemma 4 31B IT up to 32,768, Gemma 4 E4B IT up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Step 3.5 Flash 2603 accepts text; Gemma 4 31B IT accepts text and images; Gemma 4 E4B IT accepts text, images and audio. 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?

Step 3.5 Flash 2603 is the newest, released Apr 2, 2026. Gemma 4 31B IT came out Apr 2, 2026; Gemma 4 E4B IT came out Apr 2, 2026. Knowledge cutoff: Step 3.5 Flash 2603 Jan 2025, Gemma 4 31B IT Jan 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.