Compare AI models

Specifications
Parameters
—27B/35B/122B
Context window
128k256k
API pricing
Cheapest input
$0.44Mistral—
Cheapest output
$2.20Mistral—
$198Mistral—
Benchmarks
GPQA Diamond
65.7%86.6%
IFBench
40.8%76.1%
MMLU-Pro
76.8%86.7%
MMMU-Pro
43.8%76.9%
Overview
CompanyMistralQwen
Release dateAug 12 2025Feb 24 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.5 Medium leads Mistral Medium 3.1 on 4 of the 4 benchmarks they both report (GPQA Diamond, IFBench, MMLU-Pro, MMMU-Pro). Mistral Medium 3.1 shipped 196 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Mistral Medium 3.1) vs 256k (Qwen3.5 Medium). Mistral Medium 3.1 is closed, while Qwen3.5 Medium is open weight.

On GPQA Diamond, Qwen3.5 Medium leads at 86.6% vs Mistral Medium 3.1 at 65.7%. On IFBench, Qwen3.5 Medium leads at 76.1% vs Mistral Medium 3.1 at 40.8%. On MMLU-Pro, Qwen3.5 Medium leads at 86.7% vs Mistral Medium 3.1 at 76.8%. On MMMU-Pro, Qwen3.5 Medium leads at 76.9% vs Mistral Medium 3.1 at 43.8%.