Mistral AI · model sentiment
Mistral Medium 3.5
Community placement across every tier-bench category#16overall community rank
Where people place it
The complete spread matters more than the average. A wide distribution usually means the model is polarising or used for very different jobs.
S
0%
A
0%
B
0%
C
0%
D
0%
E
0%
F
0%
Across the benches
Overall#160.00 community score
Chatting#160.00 community score
Math#160.00 community score
Code quality#160.00 community score
Steerability#160.00 community score
Most value#160.00 community score
What people are saying
Comments are anonymous by default. Members can deliberately attach their handle.
No comments yet. Start with what it is actually like to use this model.
Facts, for reference
Model details
Released / listedApr 30, 2026
Context262K tokens
Inputtext, image, file
OpenRouter input$1.5 / 1M
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
View source ↗