Compare AI models

Specifications
Parameters
24B>1T
Context window
256k256k
Benchmarks
SWE-Bench Verified
68%75.3%
Overview
CompanyMistralQwen
Release dateDec 9 2025Jan 26 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen3-Max-Thinking leads Devstral Small 2 (24B) on 1 of the 1 benchmark they both report (SWE-Bench Verified). Devstral Small 2 (24B) shipped 48 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.

Devstral Small 2 (24B) has 24B parameters, while Qwen3-Max-Thinking has >1T. Context windows are 256k (Devstral Small 2 (24B)) vs 256k (Qwen3-Max-Thinking). Devstral Small 2 (24B) is open weight, while Qwen3-Max-Thinking is closed.

On SWE-Bench Verified, Qwen3-Max-Thinking leads at 75.3% vs Devstral Small 2 (24B) at 68%.