Mistral Large 3 vs Mistral Large 4
Mistral Large 4 leads the LLM Stats Score 46.2 to 10.4. Mistral Large 4 is 2.7x cheaper per token.
Mistral AI · Mistral AI · Updated for 2026
Which is better?
Mistral Large 4 leads the overall LLM Stats Score 46.2 to 10.4, ranking #34 overall.
On price, Mistral Large 4 is roughly 2.7x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Mistral Large 4 also accepts a larger context window (1,000,000 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 Mistral Large 3
- you need open weights you can self-host or fine-tune
Choose Mistral Large 4
- overall performance matters — it scores 46.2 and ranks #34 on LLM Stats
- your work emphasizes reasoning — it leads those capability indexes
- cost matters — it's about 2.7x cheaper per token
- you process long inputs — it offers a 1,000,000 token context window
- you want the most recent training data — it shipped Oct 2026
At a glance
The differences that matter most.
Individual benchmarks
8 reported for Mistral Large 3 · 18 for Mistral Large 4
Mistral Large 3 and Mistral Large 4don't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, Mistral Large 3 ($2.00/1M tokens) is 2.9x more expensive than Mistral Large 4 ($0.68/1M tokens).
For output processing, Mistral Large 3 ($5.00/1M tokens) is 2.4x more expensive than Mistral Large 4 ($2.09/1M tokens).
In conclusion, Mistral Large 3 is more expensive than Mistral Large 4.*
* Using a 3:1 ratio of input to output tokens
Model Size
Parameter count comparison
Mistral Large 4 has 375.0B more parameters than Mistral Large 3, making it 55.6% larger.
Context Window
Maximum input and output token capacity
Mistral Large 4 accepts 1,000,000 input tokens compared to Mistral Large 3's 128,000 tokens. Only Mistral Large 3 specifies output context (8,192 tokens).
Input capabilities
Documented input modalities across available providers
Both Mistral Large 3 and Mistral Large 4 support multimodal inputs.
They are both capable of processing various types of data, offering versatility in application.
Mistral Large 3
Mistral Large 4
License
Usage and distribution terms
Mistral Large 3 is licensed under Apache 2.0, while Mistral Large 4 uses a proprietary license.
License differences may affect how you can use these models in commercial or open-source projects.
Apache 2.0
Open weights
Proprietary
Closed source
Release Timeline
When each model was launched
Mistral Large 3 was released on 2025-09-01, while Mistral Large 4 was released on 2026-10-06.
Mistral Large 4 is 13 months newer than Mistral Large 3.
Sep 1, 2025
1.1 years ago
Oct 6, 2026
2 days ago
1.1yr newerKnowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
Mistral Large 3 is available from Mistral AI. Mistral Large 4 is available from Mistral AI.
Mistral Large 3
Mistral Large 4
Outputs Comparison
Judge for yourself.
Run your own prompts against Mistral Large 3 and Mistral Large 4 side-by-side, then vote on the output you prefer.
FAQ
Common questions about Mistral Large 3 vs Mistral Large 4.