Model Comparison
K-EXAONE-236B-A23B vs Mistral Large 3Which is better in 2026?
K-EXAONE-236B-A23B significantly outperforms across most benchmarks. K-EXAONE-236B-A23B is 3.9x cheaper per token.
Verdict: K-EXAONE-236B-A23B vs Mistral Large 3 — which is better?
K-EXAONE-236B-A23B (by LG AI Research) and Mistral Large 3 (by Mistral AI) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.
K-EXAONE-236B-A23B outperforms in 1 benchmarks (MMMLU), while Mistral Large 3 is better at 0 benchmarks. K-EXAONE-236B-A23B significantly outperforms across most benchmarks.
On price, K-EXAONE-236B-A23B is roughly 3.9x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Mistral Large 3 also accepts a larger context window (128,000 input tokens), making it the stronger choice for long documents and large codebases.
Choose K-EXAONE-236B-A23B if…
- you want the strongest raw capability — it leads on 1 of 1 shared benchmarks
- cost matters — it's about 3.9x cheaper per token
- you want the most recent training data — it shipped Dec 2025
Choose Mistral Large 3 if…
- you process long inputs — it offers a 128,000 token context window
- you need open weights you can self-host or fine-tune
Performance Benchmarks
Comparative analysis across standard metrics
K-EXAONE-236B-A23B outperforms in 1 benchmarks (MMMLU), while Mistral Large 3 is better at 0 benchmarks.
K-EXAONE-236B-A23B significantly outperforms across most benchmarks.
Arena Performance
Human preference votes
Pricing Analysis
Price comparison per million tokens
For input processing, K-EXAONE-236B-A23B ($0.60/1M tokens) is 3.3x cheaper than Mistral Large 3 ($2.00/1M tokens).
For output processing, K-EXAONE-236B-A23B ($1.00/1M tokens) is 5.0x cheaper than Mistral Large 3 ($5.00/1M tokens).
In conclusion, Mistral Large 3 is more expensive than K-EXAONE-236B-A23B.*
* Using a 3:1 ratio of input to output tokens
Model Size
Parameter count comparison
Mistral Large 3 has 439.0B more parameters than K-EXAONE-236B-A23B, making it 186.0% larger.
Context Window
Maximum input and output token capacity
Mistral Large 3 accepts 128,000 input tokens compared to K-EXAONE-236B-A23B's 32,768 tokens. K-EXAONE-236B-A23B can generate longer responses up to 32,768 tokens, while Mistral Large 3 is limited to 8,192 tokens.
Input Capabilities
Supported data types and modalities
Mistral Large 3 supports multimodal inputs, whereas K-EXAONE-236B-A23B does not.
Mistral Large 3 can handle both text and other forms of data like images, making it suitable for multimodal applications.
K-EXAONE-236B-A23B
Mistral Large 3
License
Usage and distribution terms
K-EXAONE-236B-A23B is licensed under a proprietary license, while Mistral Large 3 uses Apache 2.0.
License differences may affect how you can use these models in commercial or open-source projects.
Proprietary
Closed source
Apache 2.0
Open weights
Release Timeline
When each model was launched
K-EXAONE-236B-A23B was released on 2025-12-31, while Mistral Large 3 was released on 2025-09-01.
K-EXAONE-236B-A23B is 4 months newer than Mistral Large 3.
Dec 31, 2025
5 months ago
4mo newerSep 1, 2025
9 months ago
Knowledge Cutoff
When training data ends
K-EXAONE-236B-A23B has a documented knowledge cutoff of 2025-10-01, while Mistral Large 3's cutoff date is not specified.
We can confirm K-EXAONE-236B-A23B's training data extends to 2025-10-01, but cannot make a direct comparison without Mistral Large 3's cutoff date.
Oct 2025
—
Provider Availability
K-EXAONE-236B-A23B is available from FriendliAI. Mistral Large 3 is available from Mistral AI.
K-EXAONE-236B-A23B
Mistral Large 3
Outputs Comparison
Key Takeaways
K-EXAONE-236B-A23B
View detailsLG AI Research
Mistral Large 3
View detailsMistral AI
Detailed Comparison
| Feature | | |
|---|
FAQ
Common questions about K-EXAONE-236B-A23B vs Mistral Large 3.