Catalog
Mistral
Mistral Large 3
mistral-large-latest
50Index
ClosedGenerally available256K contextTextImage
Pick this when
EU teams, data residency, and European-language work at a sane price.
Skip when
You need a million-token window or the top of the intelligence board.
Mistral stopped trying to win the frontier poster and focused on models you can actually run under EU rules. That is a product.
Price
- Input / 1M
- $0.50
- Output / 1M
- $1.50
- Measured task
- $0.32
EU-hosted option. Smaller window than the million-token pack.
Shape
- Context
- 256K
- Max output
- 32K
- Released
- 2026-03
- Tools
- Yes
- Reasoning
- Yes
Scores
Intelligence index50
GPQA Diamond76
Terminal-Bench 2.159
Agentic index29
- Arena
- —
- Speed
- 110/s
- GPQA
- 76.4%
- Term.
- 58.9%
- AA Index. The single number most people mean by “how smart.” It is a blend, so a specialist can lose here and still win the job you care about.
- GPQA. A clean test of hard reasoning. PhD experts sit around 65%. It says little about writing, tools, or taste.
- Term.. Closest public proxy for coding agents that live in a terminal. A high index score with a weak terminal score is a warning.
- Arena. Captures taste and usefulness that unit tests miss. Sample size varies by model, so treat gaps under ~100 Elo as noise.
Mistral · Paris. Europe's lab. Smaller, cheaper models with EU data residency. Large 3 is the hosted flagship. Ministral is the on-device one.