Compare AI models

Specifications
Parameters
—2.4T
Context window
128k262k
API pricing
Cheapest input
$0.44Mistral—
Cheapest output
$2.20Mistral—
$198Mistral—
Benchmarks
GPQA Diamond
57.1%92.55%
Overview
CompanyMistralQwen
Release dateMay 7 2025Aug 12 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.8-2.4T-A95B leads Mistral Medium 3 on 1 of the 1 benchmark they both report (GPQA Diamond). Mistral Medium 3 shipped 462 days before Qwen3.8-2.4T-A95B, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Mistral Medium 3) vs 262k (Qwen3.8-2.4T-A95B). Mistral Medium 3 is closed, while Qwen3.8-2.4T-A95B is open weight.

On GPQA Diamond, Qwen3.8-2.4T-A95B leads at 92.55% vs Mistral Medium 3 at 57.1%.