Model Comparison
Devstral Medium vs Qwen3 VL 235B A22B ThinkingWhich is better in 2026?
Comparing Devstral Medium and Qwen3 VL 235B A22B Thinking across benchmarks, pricing, and capabilities.
Verdict: Devstral Medium vs Qwen3 VL 235B A22B Thinking — which is better?
Devstral Medium (by Mistral AI) and Qwen3 VL 235B A22B Thinking (by Alibaba Cloud / Qwen Team) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.
On price, Devstral Medium is roughly 1.5x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Qwen3 VL 235B A22B Thinking also accepts a larger context window (262,144 input tokens), making it the stronger choice for long documents and large codebases.
Choose Devstral Medium if…
- cost matters — it's about 1.5x cheaper per token
Choose Qwen3 VL 235B A22B Thinking if…
- you process long inputs — it offers a 262,144 token context window
- you want the most recent training data — it shipped Sep 2025
- you need open weights you can self-host or fine-tune
Performance Benchmarks
Comparative analysis across standard metrics
Devstral Medium and Qwen3 VL 235B A22B Thinkingdon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.
Arena Performance
Human preference votes
Pricing Analysis
Price comparison per million tokens
For input processing, Devstral Medium ($0.40/1M tokens) is 1.1x cheaper than Qwen3 VL 235B A22B Thinking ($0.45/1M tokens).
For output processing, Devstral Medium ($2.00/1M tokens) is 1.7x cheaper than Qwen3 VL 235B A22B Thinking ($3.49/1M tokens).
In conclusion, Qwen3 VL 235B A22B Thinking is more expensive than Devstral Medium.*
* Using a 3:1 ratio of input to output tokens
Context Window
Maximum input and output token capacity
Qwen3 VL 235B A22B Thinking accepts 262,144 input tokens compared to Devstral Medium's 128,000 tokens. Qwen3 VL 235B A22B Thinking can generate longer responses up to 262,144 tokens, while Devstral Medium is limited to 128,000 tokens.
Input Capabilities
Supported data types and modalities
Qwen3 VL 235B A22B Thinking supports multimodal inputs, whereas Devstral Medium does not.
Qwen3 VL 235B A22B Thinking can handle both text and other forms of data like images, making it suitable for multimodal applications.
Devstral Medium
Qwen3 VL 235B A22B Thinking
License
Usage and distribution terms
Devstral Medium is licensed under a proprietary license, while Qwen3 VL 235B A22B Thinking uses Apache 2.0.
License differences may affect how you can use these models in commercial or open-source projects.
Proprietary
Closed source
Apache 2.0
Open weights
Release Timeline
When each model was launched
Devstral Medium was released on 2025-07-10, while Qwen3 VL 235B A22B Thinking was released on 2025-09-22.
Qwen3 VL 235B A22B Thinking is 2 months newer than Devstral Medium.
Jul 10, 2025
1.0 years ago
Sep 22, 2025
10 months ago
2mo newerKnowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
Devstral Medium is available from Mistral AI. Qwen3 VL 235B A22B Thinking is available from DeepInfra, Novita.
Devstral Medium
Qwen3 VL 235B A22B Thinking
Outputs Comparison
Key Takeaways
Devstral Medium
View detailsMistral AI
Qwen3 VL 235B A22B Thinking
View detailsAlibaba Cloud / Qwen Team
Detailed Comparison
Interactive Arena
Judge for yourself.
Run your own prompts against Devstral Medium and Qwen3 VL 235B A22B Thinking side-by-side, then vote on the output you prefer.
| Feature | | |
|---|
FAQ
Common questions about Devstral Medium vs Qwen3 VL 235B A22B Thinking.