Mistral Large 3

Mistral Large 3

Mistral · Released Dec 2, 2025 Efficient
Intelligence #159 / 525
46.7 Our Score
Speed #181 / 244
56.2 tokens / sec
Input #346 / 525
$0.500 per 1M tokens
Output #327 / 525
$1.50 per 1M tokens
Context
Not reported

Analysis Summary

Mistral Large 3 sits in the Efficient tier on our leaderboard, ranked #159 of 525 published models on overall intelligence. At $0.500 input and $1.50 output per 1M tokens, it is among the most expensive on the market.

Editorial notes

Mistral Large 3 shows moderate reasoning and coding capability with reasonable pricing, but benchmark scores fall well below current mid-tier models, limiting its appeal for demanding business workflows.

Assessed April 26, 2026

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence4.4Technical3.5Value6.5Content4.5
Intelligence 4.4/10
Technical 3.5/10
Content 4.5/10
Value 6.5/10

Performance Indices

Source: Artificial Analysis

22.8 Intelligence Index
22.7 Coding Index
20.3 Agentic Index
38 Math Index

Benchmark Scores

Intelligence

GPQA Diamond 68% Graduate-level scientific reasoning
HLE 4.1% Humanity's Last Exam
MMLU Pro 80.7% Multi-task language understanding
AIME 2025 38% Competition mathematics (2025)
SciCode 36.2% Scientific computing

Technical

LiveCodeBench 46.5% Live coding evaluation
TerminalBench Hard 15.9% Agentic terminal tasks
τ²-Bench 24.6% Conversational agent benchmark

Content

IFBench 36.2% Instruction following
LCR 34.7% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does Mistral Large 3 stack up?

Compare side-by-side with other efficient models.

Compare Models

Model Information

ProviderMistral
Release Date December 2, 2025
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.50 $0.000500
Output $1.50 $0.001500

Leaderboard Categories

SEO