Compare AI models

Specifications
Parameters
—0.8B/2B/4B/9B
Context window
128k256k
API pricing
Cheapest input
$0.44Mistral—
Cheapest output
$2.20Mistral—
$198Mistral—
Benchmarks
LiveCodeBench
30.3%65.6%
IFEval
89.4%91.5%
GPQA Diamond
57.1%81.7%
MMLU-Pro
77.2%82.5%
MMMU
66.1%78.4%
Overview
CompanyMistralQwen
Release dateMay 7 2025Mar 2 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.5 Small leads Mistral Medium 3 on 5 of the 5 benchmarks they both report. Mistral Medium 3 shipped 299 days before Qwen3.5 Small, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Mistral Medium 3) vs 256k (Qwen3.5 Small). Mistral Medium 3 is closed, while Qwen3.5 Small is open weight.

On LiveCodeBench, Qwen3.5 Small leads at 65.6% vs Mistral Medium 3 at 30.3%. On IFEval, Qwen3.5 Small leads at 91.5% vs Mistral Medium 3 at 89.4%. On GPQA Diamond, Qwen3.5 Small leads at 81.7% vs Mistral Medium 3 at 57.1%. On MMLU-Pro, Qwen3.5 Small leads at 82.5% vs Mistral Medium 3 at 77.2%. On MMMU, Qwen3.5 Small leads at 78.4% vs Mistral Medium 3 at 66.1%.