Compare AI models

Specifications
Parameters
671B—
Context window
128k—
API pricing
Cheapest input
$0.27SiliconFlow—
Cheapest output
$0.41SiliconFlow—
$74.50SiliconFlow · fp8—
Benchmarks
SWE-Bench Multilingual
57.9%65.9%
Overview
CompanyDeepSeekSpaceXSI
Release dateSep 29 2025Feb 9 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Composer 1.5 leads DeepSeek V3.2 Exp on 1 of the 1 benchmark they both report (SWE-Bench Multilingual). DeepSeek V3.2 Exp shipped 133 days before Composer 1.5, so benchmark comparisons should account for the intervening progress.

DeepSeek V3.2 Exp is open weight, while Composer 1.5 is closed.

On SWE-Bench Multilingual, Composer 1.5 leads at 65.9% vs DeepSeek V3.2 Exp at 57.9%.