Compare AI models

Specifications
Parameters
671B27B
Context window
128k262k
API pricing
Cheapest input
—$0.035Darkbloom
Cheapest output
—$0.457PrimeIntellect
—$35.65PrimeIntellect · fp8
Benchmarks
LiveCodeBench
88.7%90.3%
GPQA Diamond
85.7%89.2%
Overview
CompanyDeepSeekQwen
Release dateDec 1 2025Aug 14 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.8-27B leads DeepSeek-V3.2-Speciale on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). DeepSeek-V3.2-Speciale shipped 256 days before Qwen3.8-27B, so benchmark comparisons should account for the intervening progress.

DeepSeek-V3.2-Speciale has 671B parameters, while Qwen3.8-27B has 27B. Context windows are 128k (DeepSeek-V3.2-Speciale) vs 262k (Qwen3.8-27B).

On LiveCodeBench, Qwen3.8-27B leads at 90.3% vs DeepSeek-V3.2-Speciale at 88.7%. On GPQA Diamond, Qwen3.8-27B leads at 89.2% vs DeepSeek-V3.2-Speciale at 85.7%.