ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Aya Expanse 32B vs Hermes 3 70B 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. Nous Research

    Hermes 3 70B Instruct

    Released Aug 18, 2024

    13/100
    • ECI—
    • Price$0.70 / $0.70
    • 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 (Sonar Deep Research 19/100, Hermes 3 70B Instruct 13/100, 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 priceHermes 3 70B InstructHermes 3 70B Instruct $0.70 · Aya Expanse 32B $0.75 · Sonar Deep Research $3.50 per 1M tokens (3:1 blend)
  • Longest contextHermes 3 70B InstructHermes 3 70B Instruct 131,072 · Aya Expanse 32B 128,000 · Sonar Deep Research 128,000 tokens
  • Widest inputsSame inputsAya Expanse 32B: Text · Hermes 3 70B Instruct: Text · Sonar Deep Research: Text
  • Self-hostingAya Expanse 32B and Hermes 3 70B InstructPublishes downloadable weights (CC-BY-NC-4.0)
How the score is built
MeasureWeightAya Expanse 32BHermes 3 70B InstructSonar Deep Research
Inputs & features60%0010
Context window40%323232
Specs only100%13/10013/10019/100

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 Hermes 3 70B Instruct vs Sonar Deep Research specifications side by side
SpecificationAya Expanse 32BCohereHermes 3 70B InstructNous ResearchSonar Deep ResearchPerplexity
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.50 (best)$0.70$2.00
Output$1.50$0.70 (best)$8.00
Cached input———
Blended (3:1)$0.75$0.70 (best)$3.50
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Cohere APIMedian of 1 providersOfficial Perplexity API
Limits
Context window128,000 tokens131,072 tokens (best)128,000 tokens
Max output4,000 tokens16,384 tokens32,768 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoYesminimal · low · medium · high
Tool callingNoNoNo
Structured outputNoNoNo
Availability
WeightsOpenCC-BY-NC-4.0OpenProprietary
API model IDc4ai-aya-expanse-32b—sonar-deep-research
API providers215 (best)
ReleasedOct 24, 2024Aug 18, 2024Feb 1, 2025
Knowledge cutoff—Dec 31, 2023Jan 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
  • Hermes 3 70B Instruct$8.40
  • Sonar Deep Research$36.00
04 — Questions

Which should you choose?

Which is better: Aya Expanse 32B, Hermes 3 70B Instruct or Sonar Deep Research?

There is not enough shared capability evidence to name an overall winner. The scores (Sonar Deep Research 19/100, Hermes 3 70B Instruct 13/100, 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, Hermes 3 70B Instruct or Sonar Deep Research?

Hermes 3 70B Instruct is cheaper at $0.70 input / $0.70 output per million tokens (median across 1 API provider). 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 $0.70 per million tokens for Hermes 3 70B Instruct versus $0.75 for Aya Expanse 32B (1.1× as much) and $3.50 for Sonar Deep Research (5× 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, Hermes 3 70B 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, Hermes 3 70B 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, Hermes 3 70B Instruct and Sonar Deep Research does not support tool calling, which most coding agents need.

Which has the bigger context window?

Hermes 3 70B 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, Hermes 3 70B Instruct up to 16,384, Sonar Deep Research up to 32,768 tokens.

Which can read images, PDFs, audio or video?

Aya Expanse 32B accepts text; Hermes 3 70B 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 Hermes 3 70B 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. Aya Expanse 32B came out Oct 24, 2024; Hermes 3 70B Instruct came out Aug 18, 2024. Knowledge cutoff: Hermes 3 70B Instruct Dec 31, 2023, 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.