Compare AI models

Specifications
Parameters
24B27B
Context window
128k256k
API pricing
Cheapest input
$0.06DeepInfra—
Cheapest output
$0.16DeepInfra—
$25.00DeepInfra · fp8—
Benchmarks
GPQA Diamond
46.13%87.8%
MMLU-Pro
69.06%86.2%
MMMU-Pro
49.1%75.8%
MMMU
62.5%82.9%
Overview
CompanyMistralQwen
Release dateJun 20 2025Apr 22 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.6-27B leads Mistral Small 3.2 on 4 of the 4 benchmarks they both report (GPQA Diamond, MMLU-Pro, MMMU-Pro, MMMU). Mistral Small 3.2 shipped 306 days before Qwen3.6-27B, so benchmark comparisons should account for the intervening progress.

Mistral Small 3.2 has 24B parameters, while Qwen3.6-27B has 27B. Context windows are 128k (Mistral Small 3.2) vs 256k (Qwen3.6-27B).

On GPQA Diamond, Qwen3.6-27B leads at 87.8% vs Mistral Small 3.2 at 46.13%. On MMLU-Pro, Qwen3.6-27B leads at 86.2% vs Mistral Small 3.2 at 69.06%. On MMMU-Pro, Qwen3.6-27B leads at 75.8% vs Mistral Small 3.2 at 49.1%. On MMMU, Qwen3.6-27B leads at 82.9% vs Mistral Small 3.2 at 62.5%.