ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Command R7B Arabic vs Voxtral Small 24B 2507 vs Phi-4-multimodal-instruct

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

    Command R7B Arabic

    Released Feb 27, 2025

    67/100
    • ECI—
    • Price$0.037 / $0.15
    • Context128K
  2. Mistral AI

    Voxtral Small 24B 2507

    Released Jul 15, 2025

    57/100
    • ECI—
    • Price$0.10 / $0.40
    • Context33K
  3. Microsoft

    Phi-4-multimodal-instruct

    Released Feb 26, 2025

    73/100
    • ECI—
    • Price$0.07 / $0.11
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Phi-4-multimodal-instruct 73/100, Command R7B Arabic 67/100, Voxtral Small 24B 2507 57/100) 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 priceCommand R7B ArabicCommand R7B Arabic $0.066 · Phi-4-multimodal-instruct $0.08 · Voxtral Small 24B 2507 $0.175 per 1M tokens (3:1 blend)
  • Longest contextPhi-4-multimodal-instructPhi-4-multimodal-instruct 131,072 · Command R7B Arabic 128,000 · Voxtral Small 24B 2507 32,768 tokens
  • Widest inputsPhi-4-multimodal-instructCommand R7B Arabic: Text · Voxtral Small 24B 2507: Text, Audio · Phi-4-multimodal-instruct: Text, Images, Audio
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightCommand R7B ArabicVoxtral Small 24B 2507Phi-4-multimodal-instruct
Price50%1008298
Inputs & features30%354560
Context window20%321132
Specs & price only100%67/10057/10073/100

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.

Command R7B Arabic vs Voxtral Small 24B 2507 vs Phi-4-multimodal-instruct specifications side by side
SpecificationCommand R7B ArabicCohereVoxtral Small 24B 2507Mistral AIPhi-4-multimodal-instructMicrosoft
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.037 (best)$0.10$0.07
Output$0.15$0.40$0.11 (best)
Cached input———
Blended (3:1)$0.066 (best)$0.175$0.08
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Cohere APIOfficial Mistral APIMedian of 1 providers
Limits
Context window128,000 tokens32,768 tokens131,072 tokens (best)
Max output4,000 tokens32,768 tokens131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoNo
AudioNoYesYes
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsOpenOpenApache 2.0OpenMIT
API model IDcommand-r7b-arabic-02-2025voxtral-small-latest—
API providers19 (best)1
ReleasedFeb 27, 2025Jul 15, 2025Feb 26, 2025
Knowledge cutoffJun 1, 2024—Jun 2024
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.

  • Command R7B Arabic$0.675
  • Voxtral Small 24B 2507$1.80
  • Phi-4-multimodal-instruct$0.92
04 — Questions

Which should you choose?

Which is better: Command R7B Arabic, Voxtral Small 24B 2507 or Phi-4-multimodal-instruct?

There is not enough shared capability evidence to name an overall winner. The scores (Phi-4-multimodal-instruct 73/100, Command R7B Arabic 67/100, Voxtral Small 24B 2507 57/100) 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, Command R7B Arabic, Voxtral Small 24B 2507 or Phi-4-multimodal-instruct?

Command R7B Arabic is cheaper at $0.037 input / $0.15 output per million tokens (official Cohere API price). Phi-4-multimodal-instruct costs $0.07 input / $0.11 output per million tokens (median across 1 API provider); Voxtral Small 24B 2507 costs $0.10 input / $0.40 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.066 per million tokens for Command R7B Arabic versus $0.08 for Phi-4-multimodal-instruct (1.2× as much) and $0.175 for Voxtral Small 24B 2507 (2.7× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Command R7B Arabic has not been scored yet, Voxtral Small 24B 2507 has not been scored yet and Phi-4-multimodal-instruct has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Command R7B Arabic, Voxtral Small 24B 2507 and Phi-4-multimodal-instruct yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

Phi-4-multimodal-instruct has the largest context window at 131,072 tokens, against 128,000 for Command R7B Arabic and 32,768 for Voxtral Small 24B 2507. Maximum output per response: Command R7B Arabic up to 4,000, Voxtral Small 24B 2507 up to 32,768, Phi-4-multimodal-instruct up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Command R7B Arabic accepts text; Voxtral Small 24B 2507 accepts text and audio; Phi-4-multimodal-instruct accepts text, images and audio. Phi-4-multimodal-instruct handles the widest range of inputs.

Are any of these open source?

Yes, all three publish their weights (Apache 2.0 and MIT), so you can self-host them.

Which is newer?

Voxtral Small 24B 2507 is the newest, released Jul 15, 2025. Command R7B Arabic came out Feb 27, 2025; Phi-4-multimodal-instruct came out Feb 26, 2025. Knowledge cutoff: Command R7B Arabic Jun 1, 2024, Phi-4-multimodal-instruct Jun 2024.

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.