Mistral Medium 3.5
Frontier-class multimodal model from Mistral optimized for agentic and coding use cases.
Our editorial assessment, based on the public sources listed below. Last reviewed .
- Overall rank
- #27
- Tier
- A
- Score
- 83.6
- Main category
- Coding
Strengths
- Optimized for agentic and coding workflows
- Multimodal input support
- Recent v26.04 release with active updates
Considerations
- Less third-party benchmark coverage than frontier leaders
- Open-weight license carves out very large companies, which need a separate commercial agreement
Price
Open weights (Modified MIT); API $1.50 input / $7.50 output per 1M tokens via Mistral
Shown for reference — price is not part of the score.
Score breakdown
- Performance
- 84.0
- 55% of score
- Reputation
- 81.0
- 35% of score
- Recency
- 90.0
- 10% of score
The overall score combines these sub-scores using the weights shown. How we score →
Verification status
Each field carries its own re-verification date. Amber means older than 90 days — treat those figures as stale until re-checked.
Checked against the sources listed below.
Sources
- Mistral Models Overview (opens in a new tab)Accessed:
- AI Frontier Model Tracker — DemandSphere (opens in a new tab)Accessed:
- Mistral Docs — Models Overview (opens in a new tab)Accessed:
- Mistral Docs — Open-weight models (opens in a new tab)Accessed:
- Mistral — Bringing open AI models to the frontier (opens in a new tab)Accessed:
Show 6 more sources
- Mistral — Models (Medium 3.5) (opens in a new tab)Accessed:
- Mistral Docs (opens in a new tab)Accessed:
- Mistral AI (opens in a new tab)Accessed:
- Best AI Models May 2026 (opens in a new tab)Accessed:
- AI Model Rankings 2026 by Cost Effectiveness (opens in a new tab)Accessed:
- Mistral AI (opens in a new tab)Accessed:
Similar models
- Claude Sonnet 5Anthropic#20 · Tier A · Score 84.8Compare
- GPT-5.5OpenAI#23 · Tier A · Score 84.0Compare
- DeepSeek V4 ProDeepSeek#30 · Tier A · Score 83.0Compare
- GPT-5.3 CodexOpenAI#31 · Tier A · Score 82.9Compare