Compare AI models

Specifications
Parameters
671B397B
Context window
128k256k
API pricing
Input price
—$0.60
Output price
—$3.60
Cheapest input
$0.256DeepInfra$0.36DeepInfra
Cheapest output
$0.712DeepInfra$2.34Alibaba
$103StreamLake$195Alibaba
Benchmarks
SWE-Bench Verified
42%76.4%
GPQA Diamond
59.1%88.4%
Overview
CompanyDeepSeekQwen
Release dateDec 26 2024Feb 16 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.5 leads DeepSeek V3 on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). Only Qwen3.5 has a verified first-party price for an available API: $0.60 per million input tokens and $3.60 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek V3. DeepSeek V3 shipped 417 days before Qwen3.5, so benchmark comparisons should account for the intervening progress.

DeepSeek V3 has 671B parameters, while Qwen3.5 has 397B. Context windows are 128k (DeepSeek V3) vs 256k (Qwen3.5).

On SWE-Bench Verified, Qwen3.5 leads at 76.4% vs DeepSeek V3 at 42%. On GPQA Diamond, Qwen3.5 leads at 88.4% vs DeepSeek V3 at 59.1%.