Compare AI models

Specifications
Parameters
—110B
Context window
128k32k
API pricing
Cheapest input
$0.44Mistral—
Cheapest output
$2.20Mistral—
$198Mistral—
Benchmarks
HumanEval
92.1%52.4%
Overview
CompanyMistralQwen
Release dateMay 7 2025Apr 25 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Medium 3 leads Qwen1.5-110B on 1 of the 1 benchmark they both report (HumanEval). Qwen1.5-110B shipped 377 days before Mistral Medium 3, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Mistral Medium 3) vs 32k (Qwen1.5-110B). Mistral Medium 3 is closed, while Qwen1.5-110B is open weight.

On HumanEval, Mistral Medium 3 leads at 92.1% vs Qwen1.5-110B at 52.4%.