The AI arena is free today

Open Superagent

Devstral Small 1.1 vs Phi-4-multimodal-instruct

Devstral Small 1.1 leads the LLM Stats Score 9.3 to 2.8. Phi-4-multimodal-instruct is 2.4x cheaper per token.

Mistral AI · Microsoft · Updated for 2026

Which is better?

Devstral Small 1.1 leads the overall LLM Stats Score 9.3 to 2.8, ranking #275 overall.

On price, Phi-4-multimodal-instruct is roughly 2.4x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Devstral Small 1.1

  • overall performance matters — it scores 9.3 and ranks #275 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you want the most recent training data — it shipped Jul 2025

Choose Phi-4-multimodal-instruct

  • cost matters — it's about 2.4x cheaper per token

At a glance

The differences that matter most.

Core performance indexes
9.3
#275
2.8
#318
9.2
#270
-0.2
#326
Cost, coverage & limits
Benchmark wins
Input price
$0.10 / M
$0.05 / M
Output price
$0.30 / M
$0.10 / M
Context window
128,000
128,000

Individual benchmarks

1 reported for Devstral Small 1.1 · 15 for Phi-4-multimodal-instruct

No common benchmarks found

Devstral Small 1.1 and Phi-4-multimodal-instructdon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Phi-4-multimodal-instruct costs less

For input processing, Devstral Small 1.1 ($0.10/1M tokens) is 2.0x more expensive than Phi-4-multimodal-instruct ($0.05/1M tokens).

For output processing, Devstral Small 1.1 ($0.30/1M tokens) is 3.0x more expensive than Phi-4-multimodal-instruct ($0.10/1M tokens).

In conclusion, Devstral Small 1.1 is more expensive than Phi-4-multimodal-instruct.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Wed Sep 23 2026 • llm-stats.com
Mistral AI
Devstral Small 1.1
Input tokens$0.10
Output tokens$0.30
Best providerMistral
Microsoft
Phi-4-multimodal-instruct
Input tokens$0.05
Output tokens$0.10
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue

Model Size

Parameter count comparison

18.4B diff

Devstral Small 1.1 has 18.4B more parameters than Phi-4-multimodal-instruct, making it 328.6% larger.

Mistral AI
Devstral Small 1.1
24.0Bparameters
Microsoft
Phi-4-multimodal-instruct
5.6Bparameters
24.0B
Devstral Small 1.1
5.6B
Phi-4-multimodal-instruct

Context Window

Maximum input and output token capacity

Both models have the same input context window of 128,000 tokens. Both models can generate responses up to 128,000 tokens.

Mistral AI
Devstral Small 1.1
Input128,000 tokens
Output128,000 tokens
Microsoft
Phi-4-multimodal-instruct
Input128,000 tokens
Output128,000 tokens
Wed Sep 23 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Phi-4-multimodal-instruct supports multimodal inputs, whereas Devstral Small 1.1 does not.

Phi-4-multimodal-instruct can handle both text and other forms of data like images, making it suitable for multimodal applications.

Devstral Small 1.1

Text
Images
Audio
Video

Phi-4-multimodal-instruct

Text
Images
Audio
Video

License

Usage and distribution terms

Devstral Small 1.1 is licensed under Apache 2.0, while Phi-4-multimodal-instruct uses MIT.

License differences may affect how you can use these models in commercial or open-source projects.

Devstral Small 1.1

Apache 2.0

Open weights

Phi-4-multimodal-instruct

MIT

Open weights

Release Timeline

When each model was launched

Devstral Small 1.1 was released on 2025-07-11, while Phi-4-multimodal-instruct was released on 2025-02-01.

Devstral Small 1.1 is 5 months newer than Phi-4-multimodal-instruct.

Devstral Small 1.1

Jul 11, 2025

1.2 years ago

5mo newer
Phi-4-multimodal-instruct

Feb 1, 2025

1.6 years ago

Knowledge Cutoff

When training data ends

Phi-4-multimodal-instruct has a documented knowledge cutoff of 2024-06-01, while Devstral Small 1.1's cutoff date is not specified.

We can confirm Phi-4-multimodal-instruct's training data extends to 2024-06-01, but cannot make a direct comparison without Devstral Small 1.1's cutoff date.

Devstral Small 1.1

Phi-4-multimodal-instruct

Jun 2024

Provider Availability

Devstral Small 1.1 is available from Mistral AI. Phi-4-multimodal-instruct is available from DeepInfra.

Devstral Small 1.1

mistral logo
Mistral
Input Price:Input: $0.10/1MOutput Price:Output: $0.30/1M

Phi-4-multimodal-instruct

deepinfra logo
Deepinfra
Input Price:Input: $0.05/1MOutput Price:Output: $0.10/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Devstral Small 1.1 and Phi-4-multimodal-instruct side-by-side, then vote on the output you prefer.

Devstral Small 1.1
✓ Preferred
Phi-4-multimodal-instruct
Open in Playground

FAQ

Common questions about Devstral Small 1.1 vs Phi-4-multimodal-instruct.

Which is better, Devstral Small 1.1 or Phi-4-multimodal-instruct?

Devstral Small 1.1 leads the LLM Stats Score 9.3 to 2.8. Devstral Small 1.1 is made by Mistral AI and Phi-4-multimodal-instruct is made by Microsoft. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Devstral Small 1.1 compare to Phi-4-multimodal-instruct in benchmarks?

Devstral Small 1.1 scores SWE-Bench Verified: 53.6%. Phi-4-multimodal-instruct scores ScienceQA Visual: 97.5%, DocVQA: 93.2%, MMBench: 86.7%, POPE: 85.6%, OCRBench: 84.4%.

Is Devstral Small 1.1 cheaper than Phi-4-multimodal-instruct?

Phi-4-multimodal-instruct is 2.0x cheaper for input tokens. Devstral Small 1.1 costs $0.10/M input and $0.30/M output via mistral. Phi-4-multimodal-instruct costs $0.05/M input and $0.10/M output via deepinfra.

What are the context window sizes for Devstral Small 1.1 and Phi-4-multimodal-instruct?

Devstral Small 1.1 supports 128K tokens and Phi-4-multimodal-instruct supports 128K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Devstral Small 1.1 and Phi-4-multimodal-instruct?

Key differences include LLM Stats Score (9.3 vs 2.8), input pricing ($0.10 vs $0.05/M), multimodal support (no vs yes), licensing (Apache 2.0 vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Devstral Small 1.1 and Phi-4-multimodal-instruct?

Devstral Small 1.1 is developed by Mistral AI and Phi-4-multimodal-instruct is developed by Microsoft.