Phi-4-multimodal-instruct vs Voxtral Small 24B 2507 vs Command R7B Arabic
No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.
Price in rating: Included · Exclude price
Microsoft
Phi-4-multimodal-instruct
73/100- ECI—
- Price$0.07 / $0.11
- Context131K
Mistral AI
Voxtral Small 24B 2507
57/100- ECI—
- Price$0.10 / $0.40
- Context33K
Cohere
Command R7B Arabic
67/100- ECI—
- Price$0.037 / $0.15
- Context128K
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-instructPhi-4-multimodal-instruct: Text, Images, Audio · Voxtral Small 24B 2507: Text, Audio · Command R7B Arabic: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Phi-4-multimodal-instruct | Voxtral Small 24B 2507 | Command R7B Arabic |
|---|---|---|---|---|
| Price | 50% | 98 | 82 | 100 |
| Inputs & features | 30% | 60 | 45 | 35 |
| Context window | 20% | 32 | 11 | 32 |
| Specs & price only | 100% | 73/100 | 57/100 | 67/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.07 | $0.10 | $0.037 (best) |
| Output | $0.11 (best) | $0.40 | $0.15 |
| Cached input | — | — | — |
| Blended (3:1) | $0.08 | $0.175 | $0.066 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Official Mistral API | Official Cohere API |
| Limits | |||
| Context window | 131,072 tokens (best) | 32,768 tokens | 128,000 tokens |
| Max output | 131,072 tokens (best) | 32,768 tokens | 4,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | No | No | No |
| Audio | Yes | Yes | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | Yes |
| Availability | |||
| Weights | OpenMIT | OpenApache 2.0 | Open |
| API model ID | — | voxtral-small-latest | command-r7b-arabic-02-2025 |
| API providers | 1 | 9 (best) | 1 |
| Released | Feb 26, 2025 | Jul 15, 2025 | Feb 27, 2025 |
| Knowledge cutoff | Jun 2024 | — | Jun 1, 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Phi-4-multimodal-instruct$0.92
Voxtral Small 24B 2507$1.80
Command R7B Arabic$0.675
Which should you choose?
Which is better: Phi-4-multimodal-instruct, Voxtral Small 24B 2507 or Command R7B Arabic?
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, Phi-4-multimodal-instruct, Voxtral Small 24B 2507 or Command R7B Arabic?
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. Phi-4-multimodal-instruct has not been scored yet, Voxtral Small 24B 2507 has not been scored yet and Command R7B Arabic has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Phi-4-multimodal-instruct, Voxtral Small 24B 2507 and Command R7B Arabic 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: Phi-4-multimodal-instruct up to 131,072, Voxtral Small 24B 2507 up to 32,768, Command R7B Arabic up to 4,000 tokens.
Which can read images, PDFs, audio or video?
Phi-4-multimodal-instruct accepts text, images and audio; Voxtral Small 24B 2507 accepts text and audio; Command R7B Arabic accepts text. Phi-4-multimodal-instruct handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (MIT and Apache 2.0), 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: Phi-4-multimodal-instruct Jun 2024, Command R7B Arabic Jun 1, 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.