Compare AI models

Specifications
Parameters
671B—
Context window
128k1M
API pricing
Input price
—$2.50
Output price
—$7.50
Cheapest input
$0.256DeepInfra$1.475Alibaba
Cheapest output
$0.712DeepInfra$4.425Alibaba
$103StreamLake$516Alibaba
Benchmarks
SWE-Bench Verified
42%80.4%
LiveCodeBench
40.5%91.6%
GPQA Diamond
59.1%92.4%
Overview
CompanyDeepSeekQwen
Release dateDec 26 2024May 20 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen3.7-Max leads DeepSeek V3 on 3 of the 3 benchmarks they both report (SWE-Bench Verified, LiveCodeBench, GPQA Diamond). Only Qwen3.7-Max has a verified first-party price for an available API: $2.50 per million input tokens and $7.50 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek V3. DeepSeek V3 shipped 510 days before Qwen3.7-Max, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V3) vs 1M (Qwen3.7-Max). DeepSeek V3 is open weight, while Qwen3.7-Max is closed.

On SWE-Bench Verified, Qwen3.7-Max leads at 80.4% vs DeepSeek V3 at 42%. On LiveCodeBench, Qwen3.7-Max leads at 91.6% vs DeepSeek V3 at 40.5%. On GPQA Diamond, Qwen3.7-Max leads at 92.4% vs DeepSeek V3 at 59.1%.