ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Qwen2.5-Coder-32B-Instruct vs Ministral 8B Instruct vs Aya Expanse 32B

Ministral 8B Instruct comes out ahead, 57 to 45 and 33 on our weighted score, and it is the cheaper option too.

  1. Alibaba (Qwen)

    Qwen2.5-Coder-32B-Instruct

    Released Nov 12, 2024

    45/100
    • ECI—
    • Price$0.43 / $0.60
    • Context131K
    Full specs Remove Qwen2.5-Coder-32B-Instruct
  2. Our pick

    Mistral AI

    Ministral 8B Instruct

    Released Oct 16, 2024

    57/100
    • ECI—
    • Price$0.15 / $0.15
    • Context131K
    Full specs Remove Ministral 8B Instruct

  3. Cohere

    Aya Expanse 32B

    Released Oct 24, 2024

    33/100
    • ECI—
    • Price$0.50 / $1.50
    • Context128K
    Full specs Remove Aya Expanse 32B
01 — Verdict

Ministral 8B Instruct is our pick

Ministral 8B Instruct is the better all-round choice, scoring 57/100 against Qwen2.5-Coder-32B-Instruct (45) and Aya Expanse 32B (33). It leads on 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 priceMinistral 8B InstructMinistral 8B Instruct $0.15 · Qwen2.5-Coder-32B-Instruct $0.473 · Aya Expanse 32B $0.75 per 1M tokens (3:1 blend)
  • Longest contextQwen2.5-Coder-32B-Instruct and Ministral 8B InstructQwen2.5-Coder-32B-Instruct 131,072 · Ministral 8B Instruct 131,072 · Aya Expanse 32B 128,000 tokens
  • Widest inputsSame inputsQwen2.5-Coder-32B-Instruct: Text · Ministral 8B Instruct: Text · Aya Expanse 32B: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightQwen2.5-Coder-32B-InstructMinistral 8B InstructAya Expanse 32B
Price50%658956
Inputs & features30%25250
Context window20%242424
Overall100%45/10057/10033/100

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.

Qwen2.5-Coder-32B-Instruct vs Ministral 8B Instruct vs Aya Expanse 32B specifications side by side
SpecificationQwen2.5-Coder-32B-InstructAlibaba (Qwen)Ministral 8B InstructMistral AIAya Expanse 32BCohere
Capability
Capabilities Index (ECI)———
ECI rank———
GPQA DiamondGraduate-level science questions—27.2%—
Price per million tokens
Input$0.43$0.15 (best)$0.50
Output$0.60$0.15 (best)$1.50
Cached input———
Blended (3:1)$0.473$0.15 (best)$0.75
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 4 providersMedian of 1 providersMedian of 1 providers
Limits
Context window131,072 tokens (best)131,072 tokens (best)128,000 tokens
Max output8,192 tokens (best)8,192 tokens (best)4,000 tokens
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesNo
Structured outputNoNoNo
Availability
WeightsOpenOpenMistral Research LicenseOpenCC-BY-NC-4.0
API model ID——c4ai-aya-expanse-32b
API providers4 (best)12
ReleasedNov 12, 2024Oct 16, 2024Oct 24, 2024
Knowledge cutoff———
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.

  • Qwen2.5-Coder-32B-Instruct$5.50
  • Ministral 8B Instruct$1.80
  • Aya Expanse 32B$8.00
04 — Questions

Which should you choose?

Which is better: Qwen2.5-Coder-32B-Instruct, Ministral 8B Instruct or Aya Expanse 32B?

Ministral 8B Instruct is the better all-round choice, scoring 57/100 against Qwen2.5-Coder-32B-Instruct (45) and Aya Expanse 32B (33). It leads on 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, Qwen2.5-Coder-32B-Instruct, Ministral 8B Instruct or Aya Expanse 32B?

Ministral 8B Instruct is cheaper at $0.15 input / $0.15 output per million tokens (median across 1 API provider). Qwen2.5-Coder-32B-Instruct costs $0.43 input / $0.60 output per million tokens (median across 4 API providers); Aya Expanse 32B costs $0.50 input / $1.50 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Ministral 8B Instruct versus $0.473 for Qwen2.5-Coder-32B-Instruct (3.2× as much) and $0.75 for Aya Expanse 32B (5× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Qwen2.5-Coder-32B-Instruct has not been scored yet, Ministral 8B Instruct has not been scored yet and Aya Expanse 32B has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen2.5-Coder-32B-Instruct, Ministral 8B Instruct and Aya Expanse 32B 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-Coder-32B-Instruct and Ministral 8B Instruct have the largest context windows (131,072 and 131,072 tokens), against 128,000 for Aya Expanse 32B. Maximum output per response: Qwen2.5-Coder-32B-Instruct up to 8,192, Ministral 8B Instruct up to 8,192, Aya Expanse 32B up to 4,000 tokens.

Which can read images, PDFs, audio or video?

Qwen2.5-Coder-32B-Instruct accepts text; Ministral 8B Instruct accepts text; Aya Expanse 32B accepts text. They handle the same number of input types.

Are any of these open source?

Yes, all three publish their weights (Mistral Research License and CC-BY-NC-4.0), so you can self-host them.

Which is newer?

Qwen2.5-Coder-32B-Instruct is the newest, released Nov 12, 2024. Aya Expanse 32B came out Oct 24, 2024; Ministral 8B Instruct came out Oct 16, 2024.

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, 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 Oct 4, 2026.

05 — Keep comparing

Related comparisons