#63
Mistral Large 3
mistral-large-2512
0.0
Helpfulness
Instruction Following
Comprehension
Empathy
Creative Writing
Helpfulness
0.0
Instruction Following
0.0
Comprehension
0.0
Empathy
0.0
Creative Writing
0.0
Speed
Avg 78 tok/s
Overall Assistant Score
An average score combining the 5 main categories.
85.80 pts
Rank #63
39th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
Mistral Large 3 is Mistral's December 2nd, 2025 Apache-2.0 flagship at $0.50/$1.50. Our tests score helpfulness 89.0, instruction following 88.5, and comprehension 87.5 — solid practical help, short of DeepSeek V4 Flash's 90.5/91.5/92.5. Empathy is 80.5: polite, not intimate. Creative writing is 83.5: cleaner prose than most coding-leaning opens. Speed is 78.0. A capable open generalist when you want European-hosted help without frontier prices.

Overall Score vs Price

Price axis is logarithmic (USD per 1M input tokens) · Higher score and lower price is better

Ringed point is this model

Anthropic
Baidu
Bytedance
DeepSeek
Google
Meta
Minimax
Mistral
Moonshot
OpenAI
Qwen
SpaceX AI
Tencent
Xiaomi
Zhipu AI

Compare this model

Intelligence

Overall Score · Higher is better

chatio

The benchmark for real-world helpfulness. Evaluating LLMs on practical, everyday tasks that provide a clear picture of their real-world capabilities.

Designed and developed by Alex Tyh Wang

© Chatio 2026. All rights reserved.