Mistral Large 3
Released 2025-12 · chat · 256K tokens · 8 benchmarks · Open weight
Editorial notes
MoE 41B activos / 675B totales. Apache 2.0. #2 OSS non-reasoning en LMArena.
Spec sheet
- Company
- Mistral AI
- Country
- FR
- Type
- chat
- Release
- 2025-12
- Context
- 256K tokens
- Params total
- 675B
- Params active (MoE)
- 41B
- License
- apache-2.0
- Quants
- BF16, Q8_0, Q5_K_M, Q4_K_M, Q3_K_M
- Pricing (mistral)
- $2/$6/M
- Slug
- mistral-large-3
Benchmarks (8)
Reasoning 3
Math 3
Knowledge 1
Cite this model
BibTeX · APA
BibTeX
@misc{frontier-mistral-large-3,
title = {Mistral Large 3},
author = {{Mistral AI}},
year = {2025},
note = {Frontier Benchmarks AI atlas. Accessed 2026-05-08},
url = {https://frontierbenchmarks.com/models/mistral-large-3}
} APA
Mistral AI (2025). Mistral Large 3 [Large language model]. Frontier Benchmarks AI. Retrieved 2026-05-08, from https://frontierbenchmarks.com/models/mistral-large-3
Citation reflects the atlas page, not the original model paper. For the paper, see the "Resources" section above.