ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Codestral vs Qwen2.5-VL 72B Instruct vs Qwen2.5-VL 7B Instruct

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

Price in rating: Excluded · Include price

Retired Qwen2.5-VL 7B Instruct is no longer offered by any provider we track. Its figures are the last published listing, kept so this comparison stays available.

  1. Mistral AI

    Codestral

    Released May 29, 2024

    38/100
    • ECI—
    • Price$0.30 / $0.90
    • Context256K
  2. Alibaba (Qwen)

    Qwen2.5-VL 72B Instruct

    Released Jan 26, 2025

    43/100
    • ECI—
    • Price$1.01 / $1.01
    • Context131K
  3. Alibaba (Qwen)

    Qwen2.5-VL 7B Instruct

    Released Sep 2024Retired

    40/100
    • ECI—
    • Price$0.35 / $1.05
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Qwen2.5-VL 72B Instruct 43/100, Qwen2.5-VL 7B Instruct 40/100, Codestral 38/100) 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 priceCodestralCodestral $0.45 · Qwen2.5-VL 7B Instruct $0.525 · Qwen2.5-VL 72B Instruct $1.01 per 1M tokens (3:1 blend)
  • Longest contextCodestralCodestral 256,000 · Qwen2.5-VL 72B Instruct 131,072 · Qwen2.5-VL 7B Instruct 131,072 tokens
  • Widest inputsQwen2.5-VL 72B Instruct and Qwen2.5-VL 7B InstructCodestral: Text · Qwen2.5-VL 72B Instruct: Text, Images · Qwen2.5-VL 7B Instruct: Text, Images
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightCodestralQwen2.5-VL 72B InstructQwen2.5-VL 7B Instruct
Inputs & features60%355050
Context window40%433224
Specs only100%38/10043/10040/100

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.

Codestral vs Qwen2.5-VL 72B Instruct vs Qwen2.5-VL 7B Instruct specifications side by side
SpecificationCodestralMistral AIQwen2.5-VL 72B InstructAlibaba (Qwen)Qwen2.5-VL 7B InstructAlibaba (Qwen)
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.30 (best)$1.01$0.35
Output$0.90 (best)$1.01$1.05
Cached input$0.03——
Blended (3:1)$0.45 (best)$1.01$0.525
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Mistral APIMedian of 5 providersOfficial Alibaba API
Limits
Context window256,000 tokens (best)131,072 tokens131,072 tokens
Max output4,096 tokens8,192 tokens (best)8,192 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsOpenOpenOpen
API model IDcodestral-latest—qwen2-5-vl-7b-instruct
API providers45 (best)1
ReleasedMay 29, 2024Jan 26, 2025Sep 2024
Knowledge cutoffOct 2024Apr 2024Apr 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.

  • Codestral$4.80
  • Qwen2.5-VL 72B Instruct$12.12
  • Qwen2.5-VL 7B Instruct$5.60
04 — Questions

Which should you choose?

Which is better: Codestral, Qwen2.5-VL 72B Instruct or Qwen2.5-VL 7B Instruct?

There is not enough shared capability evidence to name an overall winner. The scores (Qwen2.5-VL 72B Instruct 43/100, Qwen2.5-VL 7B Instruct 40/100, Codestral 38/100) 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, Codestral, Qwen2.5-VL 72B Instruct or Qwen2.5-VL 7B Instruct?

Codestral is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral API price). Qwen2.5-VL 7B Instruct costs $0.35 input / $1.05 output per million tokens (official Alibaba API price); Qwen2.5-VL 72B Instruct costs $1.01 input / $1.01 output per million tokens (median across 5 API providers). At a typical mix of three input tokens to one output token, that is $0.45 per million tokens for Codestral versus $0.525 for Qwen2.5-VL 7B Instruct (1.2× as much) and $1.01 for Qwen2.5-VL 72B Instruct (2.2× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Codestral has not been scored yet, Qwen2.5-VL 72B Instruct has not been scored yet and Qwen2.5-VL 7B Instruct has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Codestral, Qwen2.5-VL 72B Instruct and Qwen2.5-VL 7B Instruct 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?

Codestral has the largest context window at 256,000 tokens, against 131,072 for Qwen2.5-VL 72B Instruct and 131,072 for Qwen2.5-VL 7B Instruct. Maximum output per response: Codestral up to 4,096, Qwen2.5-VL 72B Instruct up to 8,192, Qwen2.5-VL 7B Instruct up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Codestral accepts text; Qwen2.5-VL 72B Instruct accepts text and images; Qwen2.5-VL 7B Instruct accepts text and images. Qwen2.5-VL 72B Instruct 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?

Qwen2.5-VL 72B Instruct is the newest, released Jan 26, 2025. Qwen2.5-VL 7B Instruct came out Sep 2024; Codestral came out May 29, 2024. Knowledge cutoff: Codestral Oct 2024, Qwen2.5-VL 72B Instruct Apr 2024, Qwen2.5-VL 7B Instruct Apr 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.