ZMIME
Comparison · 3 models · Updated Nov 18, 2026

DeepSeek V3.2 vs Qwen3.7 Flash vs Schematron V2 Turbo

No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.

Price in rating: Excluded · Include price

  1. DeepSeek

    DeepSeek V3.2

    Released Dec 1, 2025

    34/100
    • ECI146.3
    • Price$0.28 / $0.42
    • Context128K
  2. Alibaba (Qwen)

    Qwen3.7 Flash

    Released Jul 15, 2026

    74/100
    • ECI—
    • Price$0.03 / $0.13
    • Context1M
  3. Inference.net

    Schematron V2 Turbo

    Released Apr 16, 2026

    13/100
    • 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 (Qwen3.7 Flash 74/100, DeepSeek V3.2 34/100, Schematron V2 Turbo 13/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. 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 priceQwen3.7 FlashQwen3.7 Flash $0.055 · Schematron V2 Turbo $0.06 · DeepSeek V3.2 $0.315 per 1M tokens (3:1 blend)
  • Longest contextQwen3.7 FlashQwen3.7 Flash 1,000,000 · DeepSeek V3.2 128,000 · Schematron V2 Turbo 128,000 tokens
  • Widest inputsQwen3.7 FlashDeepSeek V3.2: Text · Qwen3.7 Flash: Text, Images, Video · Schematron V2 Turbo: Text
  • Self-hostingDeepSeek V3.2Publishes downloadable weights (MIT License)
How the score is built
MeasureWeightDeepSeek V3.2Qwen3.7 FlashSchematron V2 Turbo
Inputs & features60%35800
Context window40%326432
Specs only100%34/10074/10013/100

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.

DeepSeek V3.2 vs Qwen3.7 Flash vs Schematron V2 Turbo specifications side by side
SpecificationDeepSeek V3.2DeepSeekQwen3.7 FlashAlibaba (Qwen)Schematron V2 TurboInference.net
Capability
Capabilities Index (ECI)146.3——
ECI rank#87 of 158——
GPQA DiamondGraduate-level science questions83.4% (best)82.3%—
FrontierMath Tiers 1–3Research-level mathematics—19.3%—
OTIS Mock AIME 2024–2025Competition mathematics87.8% (best)86.7%—
Price per million tokens
Input$0.28$0.03 (best)$0.03 (best)
Output$0.42$0.13 (best)$0.15
Cached input—$0.006—
Blended (3:1)$0.315$0.055 (best)$0.06
Long-context rateSame rateOver 32K: $0.10 / $0.40Same rate
Price sourceMedian of 30 providersOfficial Alibaba APIMedian of 5 providers
Limits
Context window128,000 tokens1,000,000 tokens (best)128,000 tokens
Max output64,000 tokens131,072 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoNoNo
VideoNoYesNo
ReasoningYesYesNo
Tool callingYesYesNo
Structured outputNoYesNo
Availability
WeightsOpenMIT LicenseProprietaryProprietary
API model ID—qwen3.7-flash—
API providers30 (best)155
ReleasedDec 1, 2025Jul 15, 2026Apr 16, 2026
Knowledge cutoffJul 2024——
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.

  • DeepSeek V3.2$3.64
  • Qwen3.7 Flash$0.56
  • Schematron V2 Turbo$0.60
04 — Questions

Which should you choose?

Which is better: DeepSeek V3.2, Qwen3.7 Flash or Schematron V2 Turbo?

There is not enough shared capability evidence to name an overall winner. The scores (Qwen3.7 Flash 74/100, DeepSeek V3.2 34/100, Schematron V2 Turbo 13/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, DeepSeek V3.2, Qwen3.7 Flash or Schematron V2 Turbo?

Qwen3.7 Flash is cheaper at $0.03 input / $0.13 output per million tokens (official Alibaba API price). Schematron V2 Turbo costs $0.03 input / $0.15 output per million tokens (median across 5 API providers); DeepSeek V3.2 costs $0.28 input / $0.42 output per million tokens (median across 30 API providers). At a typical mix of three input tokens to one output token, that is $0.055 per million tokens for Qwen3.7 Flash versus $0.06 for Schematron V2 Turbo (1.1× as much) and $0.315 for DeepSeek V3.2 (5.7× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. DeepSeek V3.2 has an ECI of 146.3, Qwen3.7 Flash has not been scored yet and Schematron V2 Turbo has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek V3.2, Qwen3.7 Flash 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?

Qwen3.7 Flash has the largest context window at 1,000,000 tokens, against 128,000 for DeepSeek V3.2 and 128,000 for Schematron V2 Turbo. Maximum output per response: DeepSeek V3.2 up to 64,000, Qwen3.7 Flash up to 131,072, Schematron V2 Turbo up to 8,192 tokens.

Which can read images, PDFs, audio or video?

DeepSeek V3.2 accepts text; Qwen3.7 Flash accepts text, images and video; Schematron V2 Turbo accepts text. Qwen3.7 Flash handles the widest range of inputs.

Are any of these open source?

DeepSeek V3.2 publishes its weights (MIT License) and can be self-hosted; Qwen3.7 Flash and Schematron V2 Turbo is proprietary.

Which is newer?

Qwen3.7 Flash is the newest, released Jul 15, 2026. Schematron V2 Turbo came out Apr 16, 2026; DeepSeek V3.2 came out Dec 1, 2025. Knowledge cutoff: DeepSeek V3.2 Jul 2024.

How do you decide the winner?

This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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.