ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Gemma 4 31B IT vs Hy-MT2-1.8B vs Qwen3.5 Flash

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 31B IT

    Released Apr 2, 2026

    69/100
    • ECI144.1
    • Price$0.142 / $0.40
    • Context262K
  2. Tencent

    Hy-MT2-1.8B

    Released May 21, 2026

    49/100
    • ECI—
    • Price$0.044 / $0.177
    • Context8K
  3. Alibaba (Qwen)

    Qwen3.5 Flash

    Released Feb 23, 2026

    78/100
    • ECI143.9
    • Price$0.10 / $0.40
    • Context1M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Qwen3.5 Flash 78/100, Gemma 4 31B IT 69/100, Hy-MT2-1.8B 49/100) 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 priceHy-MT2-1.8BHy-MT2-1.8B $0.077 · Qwen3.5 Flash $0.175 · Gemma 4 31B IT $0.206 per 1M tokens (3:1 blend)
  • Longest contextQwen3.5 FlashQwen3.5 Flash 1,000,000 · Gemma 4 31B IT 262,144 · Hy-MT2-1.8B 8,192 tokens
  • Widest inputsQwen3.5 FlashGemma 4 31B IT: Text, Images · Hy-MT2-1.8B: Text · Qwen3.5 Flash: Text, Images, Video
  • Self-hostingGemma 4 31B IT and Hy-MT2-1.8BPublishes downloadable weights
How the score is built
MeasureWeightGemma 4 31B ITHy-MT2-1.8BQwen3.5 Flash
Price50%799882
Inputs & features30%70080
Context window20%43064
Specs & price only100%69/10049/10078/100

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 31B IT vs Hy-MT2-1.8B vs Qwen3.5 Flash specifications side by side
SpecificationGemma 4 31B ITGoogleHy-MT2-1.8BTencentQwen3.5 FlashAlibaba (Qwen)
Capability
Capabilities Index (ECI)144.1 (best)—143.9
ECI rank#94 of 158 (best)—#97 of 158
GPQA DiamondGraduate-level science questions75.8%—82.3% (best)
FrontierMath Tiers 1–3Research-level mathematics——18.3%
OTIS Mock AIME 2024–2025Competition mathematics73.3%—84.4% (best)
SimpleQA VerifiedShort factual questions10.4%—20.3% (best)
Price per million tokens
Input$0.142$0.044 (best)$0.10
Output$0.40$0.177 (best)$0.40
Cached input——$0.01
Blended (3:1)$0.206$0.077 (best)$0.175
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 42 providersMedian of 3 providersOfficial Alibaba API
Limits
Context window262,144 tokens8,192 tokens1,000,000 tokens (best)
Max output32,768 tokens4,096 tokens65,536 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoYes
ReasoningYesNoYes
Tool callingYesNoYes
Structured outputYesNoYes
Availability
WeightsOpenOpenProprietary
API model IDgemma-4-31b-it—qwen3.5-flash
API providers52 (best)310
ReleasedApr 2, 2026May 21, 2026Feb 23, 2026
Knowledge cutoffJan 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 31B IT$2.22
  • Hy-MT2-1.8B$0.794
  • Qwen3.5 Flash$1.80
04 — Questions

Which should you choose?

Which is better: Gemma 4 31B IT, Hy-MT2-1.8B or Qwen3.5 Flash?

There is not enough shared capability evidence to name an overall winner. The scores (Qwen3.5 Flash 78/100, Gemma 4 31B IT 69/100, Hy-MT2-1.8B 49/100) 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 31B IT, Hy-MT2-1.8B or Qwen3.5 Flash?

Hy-MT2-1.8B is cheaper at $0.044 input / $0.177 output per million tokens (median across 3 API providers). Qwen3.5 Flash costs $0.10 input / $0.40 output per million tokens (official Alibaba API price); 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 $0.077 per million tokens for Hy-MT2-1.8B versus $0.175 for Qwen3.5 Flash (2.3× as much) and $0.206 for Gemma 4 31B IT (2.7× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Gemma 4 31B IT has an ECI of 144.1, Hy-MT2-1.8B has not been scored yet and Qwen3.5 Flash has an ECI of 143.9.

Which is better for coding?

There are no published SWE-bench Verified results for Gemma 4 31B IT, Hy-MT2-1.8B and Qwen3.5 Flash yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Hy-MT2-1.8B does not support tool calling, which most coding agents need.

Which has the bigger context window?

Qwen3.5 Flash has the largest context window at 1,000,000 tokens, against 262,144 for Gemma 4 31B IT and 8,192 for Hy-MT2-1.8B. Maximum output per response: Gemma 4 31B IT up to 32,768, Hy-MT2-1.8B up to 4,096, Qwen3.5 Flash up to 65,536 tokens.

Which can read images, PDFs, audio or video?

Gemma 4 31B IT accepts text and images; Hy-MT2-1.8B accepts text; Qwen3.5 Flash accepts text, images and video. Qwen3.5 Flash handles the widest range of inputs.

Are any of these open source?

Gemma 4 31B IT and Hy-MT2-1.8B publishes its weights and can be self-hosted; Qwen3.5 Flash is proprietary.

Which is newer?

Hy-MT2-1.8B is the newest, released May 21, 2026. Gemma 4 31B IT came out Apr 2, 2026; Qwen3.5 Flash came out Feb 23, 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.