Mistral: Mistral Medium 3.5

by mistralai

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...

61 claims submitted by 15 reviewers

Monitored by HumanJudge · Endpoint registered, 10 traces logged
Maintained by HumanJudge Admin
Enrolled in: AI in Healthcare | Stanford I4UI 2026
Performance
AI in Healthcare | Stanford I4UI 2026 84%
61 votes 10 flags 15 reviewers
Independent Claims
flag AI in Healthcare | Stanford I4UI 2026 8/13/2026

Didn't advice to talk to others than doctors and Didn't describe resources available

— Ekaterina Yael Lechtchiner

flag AI in Healthcare | Stanford I4UI 2026 8/6/2026

Doesn't give enough info on how to get help

— Ekaterina Yael Lechtchiner

flag AI in Healthcare | Stanford I4UI 2026 7/24/2026

The AI didn't calibrate urgency correctly or didn't even suggest medical help or urgency contact for the parent.

— Zehong Hu

flag AI in Healthcare | Stanford I4UI 2026 5/20/2026

Not very useful. Missed point of what should I do?

— Gil Lejarde

flag AI in Healthcare | Stanford I4UI 2026 5/10/2026

The response is too short and immediately went into diagnosis mode.

— Kamrul Hasan Ujjal

This evaluation was conducted independently. Mistral: Mistral Medium 3.5 did not participate in or pay for this evaluation. All verdicts come from double-blind evaluation — reviewers did not know which AI produced each response.

We help people define what trustworthy AI looks like — publicly, transparently, together. Support this mission