Compare AI models

Specifications
Parameters
24B>1T
Context window
128k256k
API pricing
Cheapest input
$0.06DeepInfra—
Cheapest output
$0.16DeepInfra—
$25.00DeepInfra · fp8—
Benchmarks
GPQA Diamond
46.13%87.4%
MMLU-Pro
69.06%85.7%
Overview
CompanyMistralQwen
Release dateJun 20 2025Jan 26 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen3-Max-Thinking leads Mistral Small 3.2 on 2 of the 2 benchmarks they both report (GPQA Diamond, MMLU-Pro). Mistral Small 3.2 shipped 220 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.

Mistral Small 3.2 has 24B parameters, while Qwen3-Max-Thinking has >1T. Context windows are 128k (Mistral Small 3.2) vs 256k (Qwen3-Max-Thinking). Mistral Small 3.2 is open weight, while Qwen3-Max-Thinking is closed.

On GPQA Diamond, Qwen3-Max-Thinking leads at 87.4% vs Mistral Small 3.2 at 46.13%. On MMLU-Pro, Qwen3-Max-Thinking leads at 85.7% vs Mistral Small 3.2 at 69.06%.