Back to Mistral Large 3 in the gallery

Mistral AI

Mistral's new flagship effectively adopts the DeepSeek architecture and retunes the expert sizes.

Mistral Large 3 architecture diagram
Mistral Large 3 architecture diagram. Select the diagram to view it at full size.

Architecture and specifications

Scale
673B total, 41B active (6.1% active)
Context (tokens)
262,144
License
Apache License 2.0
Date
2025-12-02
Decoder type
Sparse MoE
Attention
MLA
Layer mix
61 MLA
KV cache / token (bf16) info
68.6 KiB · Low
Key detail
Near-clone of DeepSeek V3 with larger experts, fewer routed experts, and multimodal support.

Training and benchmarks

Pretraining data
Not disclosed The model card describes training from scratch but does not report a training-token total. Mistral Large 3 model card
Post-training methods
Instruction tuning The released model is instruction-tuned; the card does not specify its supervised, preference, or RL training stages. Mistral Large 3 model card
AA Intelligence Index v4.3.2 info
Total score 9.3 General 17.1 Scientific 2.1 Coding 18.3 Agents 0.2

Further reading and tools