ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Aya Expanse 32B vs Codestral 25.08 vs Qwen2.5 14B Instruct

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

Price in rating: Included · Exclude price

Retired Qwen2.5 14B Instruct is no longer offered by any provider we track. Its figures are the last published listing, kept so this comparison stays available.

  1. Cohere

    Aya Expanse 32B

    Released Oct 24, 2024

    33/100
    • ECI—
    • Price$0.50 / $1.50
    • Context128K
  2. Mistral AI

    Codestral 25.08

    Released Jul 30, 2025

    49/100
    • ECI—
    • Price$0.30 / $0.90
    • Context128K
  3. Alibaba (Qwen)

    Qwen2.5 14B Instruct

    Released Sep 2024Retired

    42/100
    • ECI—
    • Price$0.35 / $1.40
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Codestral 25.08 49/100, Qwen2.5 14B Instruct 42/100, Aya Expanse 32B 33/100) 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 priceCodestral 25.08Codestral 25.08 $0.45 · Qwen2.5 14B Instruct $0.613 · Aya Expanse 32B $0.75 per 1M tokens (3:1 blend)
  • Longest contextQwen2.5 14B InstructQwen2.5 14B Instruct 131,072 · Aya Expanse 32B 128,000 · Codestral 25.08 128,000 tokens
  • Widest inputsSame inputsAya Expanse 32B: Text · Codestral 25.08: Text · Qwen2.5 14B Instruct: Text
  • Self-hostingAya Expanse 32B and Qwen2.5 14B InstructPublishes downloadable weights (CC-BY-NC-4.0)
How the score is built
MeasureWeightAya Expanse 32BCodestral 25.08Qwen2.5 14B Instruct
Price50%536360
Inputs & features30%03525
Context window20%323224
Specs & price only100%33/10049/10042/100

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.

Aya Expanse 32B vs Codestral 25.08 vs Qwen2.5 14B Instruct specifications side by side
SpecificationAya Expanse 32BCohereCodestral 25.08Mistral AIQwen2.5 14B InstructAlibaba (Qwen)
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.50$0.30 (best)$0.35
Output$1.50$0.90 (best)$1.40
Cached input—$0.03—
Blended (3:1)$0.75$0.45 (best)$0.613
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Cohere APIOfficial Mistral APIOfficial Alibaba API
Limits
Context window128,000 tokens128,000 tokens131,072 tokens (best)
Max output4,000 tokens8,192 tokens (best)8,192 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingNoYesYes
Structured outputNoYesNo
Availability
WeightsOpenCC-BY-NC-4.0ProprietaryOpen
API model IDc4ai-aya-expanse-32bcodestral-2508qwen2-5-14b-instruct
API providers211 (best)1
ReleasedOct 24, 2024Jul 30, 2025Sep 2024
Knowledge cutoff——Apr 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.

  • Aya Expanse 32B$8.00
  • Codestral 25.08$4.80
  • Qwen2.5 14B Instruct$6.30
04 — Questions

Which should you choose?

Which is better: Aya Expanse 32B, Codestral 25.08 or Qwen2.5 14B Instruct?

There is not enough shared capability evidence to name an overall winner. The scores (Codestral 25.08 49/100, Qwen2.5 14B Instruct 42/100, Aya Expanse 32B 33/100) 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, Aya Expanse 32B, Codestral 25.08 or Qwen2.5 14B Instruct?

Codestral 25.08 is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral API price). Qwen2.5 14B Instruct costs $0.35 input / $1.40 output per million tokens (official Alibaba API price); Aya Expanse 32B costs $0.50 input / $1.50 output per million tokens (official Cohere API price). At a typical mix of three input tokens to one output token, that is $0.45 per million tokens for Codestral 25.08 versus $0.613 for Qwen2.5 14B Instruct (1.4× as much) and $0.75 for Aya Expanse 32B (1.7× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Aya Expanse 32B has not been scored yet, Codestral 25.08 has not been scored yet and Qwen2.5 14B Instruct has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Aya Expanse 32B, Codestral 25.08 and Qwen2.5 14B Instruct yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Aya Expanse 32B does not support tool calling, which most coding agents need.

Which has the bigger context window?

Qwen2.5 14B Instruct has the largest context window at 131,072 tokens, against 128,000 for Aya Expanse 32B and 128,000 for Codestral 25.08. Maximum output per response: Aya Expanse 32B up to 4,000, Codestral 25.08 up to 8,192, Qwen2.5 14B Instruct up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Aya Expanse 32B accepts text; Codestral 25.08 accepts text; Qwen2.5 14B Instruct accepts text. They handle the same number of input types.

Are any of these open source?

Aya Expanse 32B and Qwen2.5 14B Instruct publishes its weights (CC-BY-NC-4.0) and can be self-hosted; Codestral 25.08 is proprietary.

Which is newer?

Codestral 25.08 is the newest, released Jul 30, 2025. Aya Expanse 32B came out Oct 24, 2024; Qwen2.5 14B Instruct came out Sep 2024. Knowledge cutoff: Qwen2.5 14B Instruct Apr 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.