ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GLM-4.6 vs Mistral Medium 3.1 vs Relace Apply 3

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

Price in rating: Excluded · Include price

  1. Z.ai (Zhipu)

    GLM-4.6

    Released Sep 30, 2025

    37/100
    • ECI—
    • Price$0.60 / $2.20
    • Context205K
  2. Mistral AI

    Mistral Medium 3.1

    Released Aug 12, 2025

    49/100
    • ECI—
    • Price$0.44 / $2.20
    • Context131K
  3. Relace

    Relace Apply 3

    Released Sep 26, 2025

    17/100
    • ECI—
    • Price$0.85 / $1.25
    • Context256K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Mistral Medium 3.1 49/100, GLM-4.6 37/100, Relace Apply 3 17/100) 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 priceMistral Medium 3.1Mistral Medium 3.1 $0.88 · Relace Apply 3 $0.95 · GLM-4.6 $1.00 per 1M tokens (3:1 blend)
  • Longest contextRelace Apply 3Relace Apply 3 256,000 · GLM-4.6 204,800 · Mistral Medium 3.1 131,072 tokens
  • Widest inputsMistral Medium 3.1GLM-4.6: Text · Mistral Medium 3.1: Text, Images, PDFs · Relace Apply 3: Text
  • Self-hostingGLM-4.6Publishes downloadable weights
How the score is built
MeasureWeightGLM-4.6Mistral Medium 3.1Relace Apply 3
Inputs & features60%35600
Context window40%393243
Specs only100%37/10049/10017/100

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.

GLM-4.6 vs Mistral Medium 3.1 vs Relace Apply 3 specifications side by side
SpecificationGLM-4.6Z.ai (Zhipu)Mistral Medium 3.1Mistral AIRelace Apply 3Relace
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.60$0.44 (best)$0.85
Output$2.20$2.20$1.25 (best)
Cached input$0.11——
Blended (3:1)$1.00$0.88 (best)$0.95
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Z.AI APIMedian of 4 providersMedian of 3 providers
Limits
Context window204,800 tokens131,072 tokens256,000 tokens (best)
Max output131,072 tokens (best)104,857 tokens128,000 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoYesNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesNoNo
Tool callingYesYesNo
Structured outputNoNoNo
Availability
WeightsOpenProprietaryProprietary
API model IDglm-4.6——
API providers28 (best)43
ReleasedSep 30, 2025Aug 12, 2025Sep 26, 2025
Knowledge cutoffApr 2025Jun 30, 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.

  • GLM-4.6$10.40
  • Mistral Medium 3.1$8.80
  • Relace Apply 3$11.00
04 — Questions

Which should you choose?

Which is better: GLM-4.6, Mistral Medium 3.1 or Relace Apply 3?

There is not enough shared capability evidence to name an overall winner. The scores (Mistral Medium 3.1 49/100, GLM-4.6 37/100, Relace Apply 3 17/100) 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, GLM-4.6, Mistral Medium 3.1 or Relace Apply 3?

Mistral Medium 3.1 is cheaper at $0.44 input / $2.20 output per million tokens (median across 4 API providers). Relace Apply 3 costs $0.85 input / $1.25 output per million tokens (median across 3 API providers); GLM-4.6 costs $0.60 input / $2.20 output per million tokens (official Z.AI API price). At a typical mix of three input tokens to one output token, that is $0.88 per million tokens for Mistral Medium 3.1 versus $0.95 for Relace Apply 3 (1.1× as much) and $1.00 for GLM-4.6 (1.1× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. GLM-4.6 has not been scored yet, Mistral Medium 3.1 has not been scored yet and Relace Apply 3 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for GLM-4.6, Mistral Medium 3.1 and Relace Apply 3 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Relace Apply 3 does not support tool calling, which most coding agents need.

Which has the bigger context window?

Relace Apply 3 has the largest context window at 256,000 tokens, against 204,800 for GLM-4.6 and 131,072 for Mistral Medium 3.1. Maximum output per response: GLM-4.6 up to 131,072, Mistral Medium 3.1 up to 104,857, Relace Apply 3 up to 128,000 tokens.

Which can read images, PDFs, audio or video?

GLM-4.6 accepts text; Mistral Medium 3.1 accepts text, images and PDFs; Relace Apply 3 accepts text. Mistral Medium 3.1 handles the widest range of inputs.

Are any of these open source?

GLM-4.6 publishes its weights and can be self-hosted; Mistral Medium 3.1 and Relace Apply 3 is proprietary.

Which is newer?

GLM-4.6 is the newest, released Sep 30, 2025. Relace Apply 3 came out Sep 26, 2025; Mistral Medium 3.1 came out Aug 12, 2025. Knowledge cutoff: GLM-4.6 Apr 2025, Mistral Medium 3.1 Jun 30, 2025.

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.