ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Qwen Plus vs Qwen2.5-VL 72B Instruct vs Codestral

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. Alibaba (Qwen)

    Qwen Plus

    Released Jan 25, 2024

    55/100
    • ECI—
    • Price$0.40 / $1.20
    • Context1M
  2. Alibaba (Qwen)

    Qwen2.5-VL 72B Instruct

    Released Jan 26, 2025

    45/100
    • ECI—
    • Price$1.01 / $1.01
    • Context131K
  3. Mistral AI

    Codestral

    Released May 29, 2024

    51/100
    • ECI—
    • Price$0.30 / $0.90
    • Context256K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Qwen Plus 55/100, Codestral 51/100, Qwen2.5-VL 72B Instruct 45/100) 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 priceCodestralCodestral $0.45 · Qwen Plus $0.60 · Qwen2.5-VL 72B Instruct $1.01 per 1M tokens (3:1 blend)
  • Longest contextQwen PlusQwen Plus 1,000,000 · Codestral 256,000 · Qwen2.5-VL 72B Instruct 131,072 tokens
  • Widest inputsQwen2.5-VL 72B InstructQwen Plus: Text · Qwen2.5-VL 72B Instruct: Text, Images · Codestral: Text
  • Self-hostingQwen2.5-VL 72B Instruct and CodestralPublishes downloadable weights
How the score is built
MeasureWeightQwen PlusQwen2.5-VL 72B InstructCodestral
Price50%584863
Inputs & features30%455035
Context window20%643243
Specs & price only100%55/10045/10051/100

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.

Qwen Plus vs Qwen2.5-VL 72B Instruct vs Codestral specifications side by side
SpecificationQwen PlusAlibaba (Qwen)Qwen2.5-VL 72B InstructAlibaba (Qwen)CodestralMistral AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.40$1.01$0.30 (best)
Output$1.20$1.01$0.90 (best)
Cached input$0.08—$0.03 (best)
Blended (3:1)$0.60$1.01$0.45 (best)
Long-context rateOver 256K: $1.20 / $3.60Same rateSame rate
Price sourceOfficial Alibaba APIMedian of 5 providersOfficial Mistral API
Limits
Context window1,000,000 tokens (best)131,072 tokens256,000 tokens
Max output32,768 tokens (best)8,192 tokens4,096 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesNoNo
Tool callingYesYesYes
Structured outputYesNoYes
Availability
WeightsProprietaryOpenOpen
API model IDqwen-plus—codestral-latest
API providers10 (best)54
ReleasedJan 25, 2024Jan 26, 2025May 29, 2024
Knowledge cutoffApr 2024Apr 2024Oct 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.

  • Qwen Plus$6.40
  • Qwen2.5-VL 72B Instruct$12.12
  • Codestral$4.80
04 — Questions

Which should you choose?

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

There is not enough shared capability evidence to name an overall winner. The scores (Qwen Plus 55/100, Codestral 51/100, Qwen2.5-VL 72B Instruct 45/100) 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, Qwen Plus, Qwen2.5-VL 72B Instruct or Codestral?

Codestral is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral API price). Qwen Plus costs $0.40 input / $1.20 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 $0.60 for Qwen Plus (1.3× 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. Qwen Plus has not been scored yet, Qwen2.5-VL 72B Instruct has not been scored yet and Codestral has not been scored yet.

Which is better for coding?

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

Qwen Plus has the largest context window at 1,000,000 tokens, against 256,000 for Codestral and 131,072 for Qwen2.5-VL 72B Instruct. Maximum output per response: Qwen Plus up to 32,768, Qwen2.5-VL 72B Instruct up to 8,192, Codestral up to 4,096 tokens.

Which can read images, PDFs, audio or video?

Qwen Plus accepts text; Qwen2.5-VL 72B Instruct accepts text and images; Codestral accepts text. Qwen2.5-VL 72B Instruct handles the widest range of inputs.

Are any of these open source?

Qwen2.5-VL 72B Instruct and Codestral publishes its weights and can be self-hosted; Qwen Plus is proprietary.

Which is newer?

Qwen2.5-VL 72B Instruct is the newest, released Jan 26, 2025. Codestral came out May 29, 2024; Qwen Plus came out Jan 25, 2024. Knowledge cutoff: Qwen Plus Apr 2024, Qwen2.5-VL 72B Instruct Apr 2024, Codestral Oct 2024.

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.