Compare AI models

Specifications
Parameters
1.5B/7B/8B/14B/32B/70B—
Context window
—128k
API pricing
Cheapest input
—$0.40Mistral
Cheapest output
—$2.00Mistral
—$180Mistral · zdr
Benchmarks
LiveCodeBench
57.5%30.3%
MATH-500
94.5%91%
GPQA Diamond
65.2%57.1%
Overview
CompanyDeepSeekMistral
Release dateJan 20 2025May 7 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 Distill leads Mistral Medium 3 on 3 of the 3 benchmarks they both report (LiveCodeBench, MATH-500, GPQA Diamond). DeepSeek R1 Distill shipped 107 days before Mistral Medium 3, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 Distill is open weight, while Mistral Medium 3 is closed.

On LiveCodeBench, DeepSeek R1 Distill leads at 57.5% vs Mistral Medium 3 at 30.3%. On MATH-500, DeepSeek R1 Distill leads at 94.5% vs Mistral Medium 3 at 91%. On GPQA Diamond, DeepSeek R1 Distill leads at 65.2% vs Mistral Medium 3 at 57.1%.