ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Aya Expanse 32B vs Qwen2.5-Coder-32B-Instruct vs Sonar Deep Research

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

Price in rating: Excluded · Include price

  1. Cohere

    Aya Expanse 32B

    Released Oct 24, 2024

    13/100
    • ECI—
    • Price$0.50 / $1.50
    • Context128K
  2. Alibaba (Qwen)

    Qwen2.5-Coder-32B-Instruct

    Released Nov 12, 2024

    28/100
    • ECI—
    • Price$0.66 / $1.00
    • Context131K
  3. Perplexity

    Sonar Deep Research

    Released Feb 1, 2025Deprecated

    19/100
    • ECI—
    • Price$2.00 / $8.00
    • Context128K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Qwen2.5-Coder-32B-Instruct 28/100, Sonar Deep Research 19/100, Aya Expanse 32B 13/100) 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 priceQwen2.5-Coder-32B-InstructQwen2.5-Coder-32B-Instruct $0.745 · Aya Expanse 32B $0.75 · Sonar Deep Research $3.50 per 1M tokens (3:1 blend)
  • Longest contextQwen2.5-Coder-32B-InstructQwen2.5-Coder-32B-Instruct 131,072 · Aya Expanse 32B 128,000 · Sonar Deep Research 128,000 tokens
  • Widest inputsSame inputsAya Expanse 32B: Text · Qwen2.5-Coder-32B-Instruct: Text · Sonar Deep Research: Text
  • Self-hostingAya Expanse 32B and Qwen2.5-Coder-32B-InstructPublishes downloadable weights (CC-BY-NC-4.0)
How the score is built
MeasureWeightAya Expanse 32BQwen2.5-Coder-32B-InstructSonar Deep Research
Inputs & features60%02510
Context window40%323232
Specs only100%13/10028/10019/100

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 Qwen2.5-Coder-32B-Instruct vs Sonar Deep Research specifications side by side
SpecificationAya Expanse 32BCohereQwen2.5-Coder-32B-InstructAlibaba (Qwen)Sonar Deep ResearchPerplexity
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.50 (best)$0.66$2.00
Output$1.50$1.00 (best)$8.00
Cached input———
Blended (3:1)$0.75$0.745 (best)$3.50
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Cohere APIMedian of 7 providersOfficial Perplexity API
Limits
Context window128,000 tokens131,072 tokens (best)128,000 tokens
Max output4,000 tokens8,192 tokens32,768 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoYesminimal · low · medium · high
Tool callingNoYesNo
Structured outputNoNoNo
Availability
WeightsOpenCC-BY-NC-4.0OpenProprietary
API model IDc4ai-aya-expanse-32b—sonar-deep-research
API providers27 (best)5
ReleasedOct 24, 2024Nov 12, 2024Feb 1, 2025
Knowledge cutoff——Jan 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.

  • Aya Expanse 32B$8.00
  • Qwen2.5-Coder-32B-Instruct$8.60
  • Sonar Deep Research$36.00
04 — Questions

Which should you choose?

Which is better: Aya Expanse 32B, Qwen2.5-Coder-32B-Instruct or Sonar Deep Research?

There is not enough shared capability evidence to name an overall winner. The scores (Qwen2.5-Coder-32B-Instruct 28/100, Sonar Deep Research 19/100, Aya Expanse 32B 13/100) 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, Aya Expanse 32B, Qwen2.5-Coder-32B-Instruct or Sonar Deep Research?

Qwen2.5-Coder-32B-Instruct is cheaper at $0.66 input / $1.00 output per million tokens (median across 7 API providers). Aya Expanse 32B costs $0.50 input / $1.50 output per million tokens (official Cohere API price); Sonar Deep Research costs $2.00 input / $8.00 output per million tokens (official Perplexity API price). At a typical mix of three input tokens to one output token, that is $0.745 per million tokens for Qwen2.5-Coder-32B-Instruct versus $0.75 for Aya Expanse 32B (1× as much) and $3.50 for Sonar Deep Research (4.7× 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, Qwen2.5-Coder-32B-Instruct has not been scored yet and Sonar Deep Research has not been scored yet.

Which is better for coding?

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

Which has the bigger context window?

Qwen2.5-Coder-32B-Instruct has the largest context window at 131,072 tokens, against 128,000 for Aya Expanse 32B and 128,000 for Sonar Deep Research. Maximum output per response: Aya Expanse 32B up to 4,000, Qwen2.5-Coder-32B-Instruct up to 8,192, Sonar Deep Research up to 32,768 tokens.

Which can read images, PDFs, audio or video?

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

Are any of these open source?

Aya Expanse 32B and Qwen2.5-Coder-32B-Instruct publishes its weights (CC-BY-NC-4.0) and can be self-hosted; Sonar Deep Research is proprietary.

Which is newer?

Sonar Deep Research is the newest, released Feb 1, 2025. Qwen2.5-Coder-32B-Instruct came out Nov 12, 2024; Aya Expanse 32B came out Oct 24, 2024. Knowledge cutoff: Sonar Deep Research Jan 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.