Compare AI models

Specifications
Parameters
24B27B
Context window
256k256k
Benchmarks
SWE-Bench Verified
68%77.2%
SWE-Bench Multilingual
55.7%71.3%
Terminal-Bench 2.0
22.5%59.3%
Overview
CompanyMistralQwen
Release dateDec 9 2025Apr 22 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.6-27B leads Devstral Small 2 (24B) on 3 of the 3 benchmarks they both report (SWE-Bench Verified, SWE-Bench Multilingual, Terminal-Bench 2.0). Devstral Small 2 (24B) shipped 134 days before Qwen3.6-27B, so benchmark comparisons should account for the intervening progress.

Devstral Small 2 (24B) has 24B parameters, while Qwen3.6-27B has 27B. Context windows are 256k (Devstral Small 2 (24B)) vs 256k (Qwen3.6-27B).

On SWE-Bench Verified, Qwen3.6-27B leads at 77.2% vs Devstral Small 2 (24B) at 68%. On SWE-Bench Multilingual, Qwen3.6-27B leads at 71.3% vs Devstral Small 2 (24B) at 55.7%. On Terminal-Bench 2.0, Qwen3.6-27B leads at 59.3% vs Devstral Small 2 (24B) at 22.5%.