ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Schematron V2 Small vs Gemma 4 31B IT vs Reka Edge

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. Inference.net

    Schematron V2 Small

    Released Apr 16, 2026

    53/100
    • ECI—
    • Price$0.05 / $0.23
    • Context128K
  2. Google

    Gemma 4 31B IT

    Released Apr 2, 2026

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

    Reka Edge

    Released Mar 11, 2026

    64/100
    • ECI—
    • Price$0.102 / $0.102
    • Context16K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Gemma 4 31B IT 69/100, Reka Edge 64/100, 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 priceSchematron V2 SmallSchematron V2 Small $0.095 · Reka Edge $0.102 · Gemma 4 31B IT $0.206 per 1M tokens (3:1 blend)
  • Longest contextGemma 4 31B ITGemma 4 31B IT 262,144 · Schematron V2 Small 128,000 · Reka Edge 16,384 tokens
  • Widest inputsReka EdgeSchematron V2 Small: Text · Gemma 4 31B IT: Text, Images · Reka Edge: Text, Images, Video
  • Self-hostingGemma 4 31B IT and Reka EdgePublishes downloadable weights
How the score is built
MeasureWeightSchematron V2 SmallGemma 4 31B ITReka Edge
Price50%947993
Inputs & features30%07060
Context window20%32430
Specs & price only100%53/10069/10064/100

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.

Schematron V2 Small vs Gemma 4 31B IT vs Reka Edge specifications side by side
SpecificationSchematron V2 SmallInference.netGemma 4 31B ITGoogleReka EdgeReka AI
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$0.05 (best)$0.142$0.102
Output$0.23$0.40$0.102 (best)
Cached input———
Blended (3:1)$0.095 (best)$0.206$0.102
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 5 providersMedian of 42 providersMedian of 4 providers
Limits
Context window128,000 tokens262,144 tokens (best)16,384 tokens
Max output4,096 tokens32,768 tokens (best)14,745 tokens
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoYes
ReasoningNoYesNo
Tool callingNoYesYes
Structured outputNoYesNo
Availability
WeightsProprietaryOpenOpen
API model ID—gemma-4-31b-it—
API providers552 (best)4
ReleasedApr 16, 2026Apr 2, 2026Mar 11, 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.

  • Schematron V2 Small$0.96
  • Gemma 4 31B IT$2.22
  • Reka Edge$1.23
04 — Questions

Which should you choose?

Which is better: Schematron V2 Small, Gemma 4 31B IT or Reka Edge?

There is not enough shared capability evidence to name an overall winner. The scores (Gemma 4 31B IT 69/100, Reka Edge 64/100, 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, Schematron V2 Small, Gemma 4 31B IT or Reka Edge?

Schematron V2 Small is cheaper at $0.05 input / $0.23 output per million tokens (median across 5 API providers). Reka Edge costs $0.102 input / $0.102 output per million tokens (median across 4 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 $0.095 per million tokens for Schematron V2 Small versus $0.102 for Reka Edge (1.1× as much) and $0.206 for Gemma 4 31B IT (2.2× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Schematron V2 Small has not been scored yet, Gemma 4 31B IT has an ECI of 144.1 and Reka Edge has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Schematron V2 Small, Gemma 4 31B IT and Reka Edge 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 31B IT has the largest context window at 262,144 tokens, against 128,000 for Schematron V2 Small and 16,384 for Reka Edge. Maximum output per response: Schematron V2 Small up to 4,096, Gemma 4 31B IT up to 32,768, Reka Edge up to 14,745 tokens.

Which can read images, PDFs, audio or video?

Schematron V2 Small accepts text; Gemma 4 31B IT accepts text and images; Reka Edge accepts text, images and video. Reka Edge handles the widest range of inputs.

Are any of these open source?

Gemma 4 31B IT and Reka Edge publishes its weights and can be self-hosted; Schematron V2 Small is proprietary.

Which is newer?

Schematron V2 Small is the newest, released Apr 16, 2026. Gemma 4 31B IT came out Apr 2, 2026; Reka Edge came out Mar 11, 2026. Knowledge cutoff: 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.