Devstral Medium vs GLM-4.6
Devstral Medium and GLM-4.6 are closely matched at 13.6 and 29.0 on the LLM Stats Score. Devstral Medium is 1.1x cheaper per token.
Mistral AI · Zhipu AI · Updated for 2026
Which is better?
Devstral Medium and GLM-4.6 are closely matched on the overall LLM Stats Score at 13.6 and 29.0.
In the 1 individual benchmarks reported for both models, GLM-4.6 wins 1; this is a narrower head-to-head signal than the composite indexes.
On price, Devstral Medium is roughly 1.1x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
GLM-4.6 also accepts a larger context window (202,752 input tokens), making it the stronger choice for long documents and large codebases.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose Devstral Medium
- cost matters — it's about 1.1x cheaper per token
Choose GLM-4.6
- you value its reported benchmark strengths — it wins 1 of 1 exact shared results
- you process long inputs — it offers a 202,752 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
At a glance
The differences that matter most.
Individual benchmarks
1 reported for Devstral Medium · 7 for GLM-4.6
Devstral Medium outperforms in 0 benchmarks, while GLM-4.6 is better at 1 benchmark (SWE-Bench Verified).
GLM-4.6 significantly outperforms across most benchmarks.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, Devstral Medium ($0.40/1M tokens) is 1.3x cheaper than GLM-4.6 ($0.50/1M tokens).
For output processing, Devstral Medium ($2.00/1M tokens) costs the same as GLM-4.6 ($2.00/1M tokens).
In conclusion, GLM-4.6 is more expensive than Devstral Medium.*
* Using a 3:1 ratio of input to output tokens
Context Window
Maximum input and output token capacity
GLM-4.6 accepts 202,752 input tokens compared to Devstral Medium's 128,000 tokens. GLM-4.6 can generate longer responses up to 202,752 tokens, while Devstral Medium is limited to 128,000 tokens.
Input capabilities
Documented input modalities across available providers
GLM-4.6 supports multimodal inputs, whereas Devstral Medium does not.
GLM-4.6 can handle both text and other forms of data like images, making it suitable for multimodal applications.
Devstral Medium
GLM-4.6
License
Usage and distribution terms
Devstral Medium is licensed under a proprietary license, while GLM-4.6 uses MIT.
License differences may affect how you can use these models in commercial or open-source projects.
Proprietary
Closed source
MIT
Open weights
Release Timeline
When each model was launched
Devstral Medium was released on 2025-07-10, while GLM-4.6 was released on 2025-09-30.
GLM-4.6 is 3 months newer than Devstral Medium.
Jul 10, 2025
1.2 years ago
Sep 30, 2025
11 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. GLM-4.6 is available from DeepInfra, Fireworks.
Devstral Medium
GLM-4.6
Outputs Comparison
Judge for yourself.
Run your own prompts against Devstral Medium and GLM-4.6 side-by-side, then vote on the output you prefer.
FAQ
Common questions about Devstral Medium vs GLM-4.6.