ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Aya Expanse 32B vs Hermes 3 70B Instruct vs Vision Large

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. Cohere

    Aya Expanse 32B

    Released Oct 24, 2024

    33/100
    • ECI—
    • Price$0.50 / $1.50
    • Context128K
  2. Nous Research

    Hermes 3 70B Instruct

    Released Aug 18, 2024

    34/100
    • ECI—
    • Price$0.70 / $0.70
    • Context131K
  3. Vispark

    Vision Large

    Released May 15, 2024

    43/100
    • ECI—
    • Price$7.37 / $22.11
    • Context1M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Vision Large 43/100, Hermes 3 70B Instruct 34/100, 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 priceHermes 3 70B InstructHermes 3 70B Instruct $0.70 · Aya Expanse 32B $0.75 · Vision Large $11.05 per 1M tokens (3:1 blend)
  • Longest contextVision LargeVision Large 1,000,000 · Hermes 3 70B Instruct 131,072 · Aya Expanse 32B 128,000 tokens
  • Widest inputsVision LargeAya Expanse 32B: Text · Hermes 3 70B Instruct: Text · Vision Large: Text, Images, PDFs, Audio, Video
  • 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 InstructVision Large
Price50%53550
Inputs & features30%00100
Context window20%323264
Specs & price only100%33/10034/10043/100

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 Vision Large specifications side by side
SpecificationAya Expanse 32BCohereHermes 3 70B InstructNous ResearchVision LargeVispark
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.50 (best)$0.70$7.37
Output$1.50$0.70 (best)$22.11
Cached input———
Blended (3:1)$0.75$0.70 (best)$11.05
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Cohere APIMedian of 1 providersOfficial Vispark API
Limits
Context window128,000 tokens131,072 tokens1,000,000 tokens (best)
Max output4,000 tokens16,384 tokens65,536 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoYes
AudioNoNoYes
VideoNoNoYes
ReasoningNoNoYes
Tool callingNoNoYes
Structured outputNoNoYes
Availability
WeightsOpenCC-BY-NC-4.0OpenProprietary
API model IDc4ai-aya-expanse-32b—vispark/vision-large
API providers2 (best)11
ReleasedOct 24, 2024Aug 18, 2024May 15, 2024
Knowledge cutoff—Dec 31, 2023—
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
  • Vision Large$117.92
04 — Questions

Which should you choose?

Which is better: Aya Expanse 32B, Hermes 3 70B Instruct or Vision Large?

There is not enough shared capability evidence to name an overall winner. The scores (Vision Large 43/100, Hermes 3 70B Instruct 34/100, 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, Hermes 3 70B Instruct or Vision Large?

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); Vision Large costs $7.37 input / $22.11 output per million tokens (official Vispark 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 $11.05 for Vision Large (16× 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 Vision Large 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 Vision Large 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 Hermes 3 70B Instruct does not support tool calling, which most coding agents need.

Which has the bigger context window?

Vision Large has the largest context window at 1,000,000 tokens, against 131,072 for Hermes 3 70B Instruct and 128,000 for Aya Expanse 32B. Maximum output per response: Aya Expanse 32B up to 4,000, Hermes 3 70B Instruct up to 16,384, Vision Large up to 65,536 tokens.

Which can read images, PDFs, audio or video?

Aya Expanse 32B accepts text; Hermes 3 70B Instruct accepts text; Vision Large accepts text, images, PDFs, audio and video. Vision Large handles the widest range of inputs.

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; Vision Large is proprietary.

Which is newer?

Aya Expanse 32B is the newest, released Oct 24, 2024. Hermes 3 70B Instruct came out Aug 18, 2024; Vision Large came out May 15, 2024. Knowledge cutoff: Hermes 3 70B Instruct Dec 31, 2023.

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.