ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Vision Large vs Hermes 2 Pro Llama 3 8B vs Codestral-22B-v0.1

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

Price in rating: Included · Exclude price

  1. Vispark

    Vision Large

    Released May 15, 2024

    86/100
    • ECI—
    • Price$7.37 / $22.11
    • Context1M
  2. Nous Research

    Hermes 2 Pro Llama 3 8B

    Released Apr 30, 2024

    15/100
    • ECI—
    • Price$0.14 / $0.14
    • Context8K
  3. Mistral AI

    Codestral-22B-v0.1

    Released May 29, 2024

    4/100
    • ECI—
    • Price—
    • Context33K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Vision Large 86/100, Hermes 2 Pro Llama 3 8B 15/100, Codestral-22B-v0.1 4/100) compare the available specifications and price. 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 2 Pro Llama 3 8BHermes 2 Pro Llama 3 8B $0.14 · Vision Large $11.05 per 1M tokens (3:1 blend) · Codestral-22B-v0.1 unpriced
  • Longest contextVision LargeVision Large 1,000,000 · Codestral-22B-v0.1 32,768 · Hermes 2 Pro Llama 3 8B 8,192 tokens
  • Widest inputsVision LargeVision Large: Text, Images, PDFs, Audio, Video · Hermes 2 Pro Llama 3 8B: Text · Codestral-22B-v0.1: Text
  • Self-hostingHermes 2 Pro Llama 3 8B and Codestral-22B-v0.1Publishes downloadable weights (Llama 3 Community License and Mistral AI Non-Production License)
How the score is built
MeasureWeightVision LargeHermes 2 Pro Llama 3 8BCodestral-22B-v0.1
Inputs & features60%100250
Context window40%64011
Specs & price only100%86/10015/1004/100

Left out because at least one model lacks the data: capability and price. 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.

Vision Large vs Hermes 2 Pro Llama 3 8B vs Codestral-22B-v0.1 specifications side by side
SpecificationVision LargeVisparkHermes 2 Pro Llama 3 8BNous ResearchCodestral-22B-v0.1Mistral AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$7.37$0.14 (best)—
Output$22.11$0.14 (best)—
Cached input———
Blended (3:1)$11.05$0.14 (best)—
Long-context rateSame rateSame rate—
Price sourceOfficial Vispark APIMedian of 2 providers—
Limits
Context window1,000,000 tokens (best)8,192 tokens32,768 tokens
Max output65,536 tokens (best)8,192 tokens8,192 tokens
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsYesNoNo
AudioYesNoNo
VideoYesNoNo
ReasoningYesNoNo
Tool callingYesYesNo
Structured outputYesNoNo
Availability
WeightsProprietaryOpenLlama 3 Community LicenseOpenMistral AI Non-Production License
API model IDvispark/vision-large——
API providers12 (best)—
ReleasedMay 15, 2024Apr 30, 2024May 29, 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.

  • Vision Large$117.92
  • Hermes 2 Pro Llama 3 8B$1.68
  • Codestral-22B-v0.1—
04 — Questions

Which should you choose?

Which is better: Vision Large, Hermes 2 Pro Llama 3 8B or Codestral-22B-v0.1?

There is not enough shared capability evidence to name an overall winner. The scores (Vision Large 86/100, Hermes 2 Pro Llama 3 8B 15/100, Codestral-22B-v0.1 4/100) compare the available specifications and price. 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, Vision Large, Hermes 2 Pro Llama 3 8B or Codestral-22B-v0.1?

Hermes 2 Pro Llama 3 8B is cheaper at $0.14 input / $0.14 output per million tokens (median across 2 API providers). 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 $0.14 per million tokens for Hermes 2 Pro Llama 3 8B versus $11.05 for Vision Large (79× as much). Codestral-22B-v0.1 has no published per-token price.

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Vision Large has not been scored yet, Hermes 2 Pro Llama 3 8B has not been scored yet and Codestral-22B-v0.1 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Vision Large, Hermes 2 Pro Llama 3 8B and Codestral-22B-v0.1 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Codestral-22B-v0.1 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 32,768 for Codestral-22B-v0.1 and 8,192 for Hermes 2 Pro Llama 3 8B. Maximum output per response: Vision Large up to 65,536, Hermes 2 Pro Llama 3 8B up to 8,192, Codestral-22B-v0.1 up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Vision Large accepts text, images, PDFs, audio and video; Hermes 2 Pro Llama 3 8B accepts text; Codestral-22B-v0.1 accepts text. Vision Large handles the widest range of inputs.

Are any of these open source?

Hermes 2 Pro Llama 3 8B and Codestral-22B-v0.1 publishes its weights (Llama 3 Community License and Mistral AI Non-Production License) and can be self-hosted; Vision Large is proprietary.

Which is newer?

Codestral-22B-v0.1 is the newest, released May 29, 2024. Vision Large came out May 15, 2024; Hermes 2 Pro Llama 3 8B came out Apr 30, 2024.

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.