Compare AI models

Specifications
Parameters
671B4B/30B/235B
Context window
128k256k
API pricing
Cheapest input
$0.25DeepInfra—
Cheapest output
$0.95DeepInfra—
$97.50DeepInfra · fp4—
Benchmarks
LiveCodeBench
74.8%74.1%
Humanity's Last Exam · text only, no tools
15.9%18.2%
AIME 2025
88.4%92.3%
GPQA Diamond
80.1%81.1%
MMLU-Pro
84.8%84.4%
Overview
CompanyDeepSeekQwen
Release dateAug 21 2025Jul 21 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3-2507 leads DeepSeek V3.1 on 3 of the 5 benchmarks they both report. Qwen3-2507 shipped 31 days before DeepSeek V3.1, so benchmark comparisons should account for the intervening progress.

DeepSeek V3.1 has 671B parameters, while Qwen3-2507 has 4B/30B/235B. Context windows are 128k (DeepSeek V3.1) vs 256k (Qwen3-2507).

On LiveCodeBench, DeepSeek V3.1 leads at 74.8% vs Qwen3-2507 at 74.1%. On Humanity's Last Exam · text only, no tools, Qwen3-2507 leads at 18.2% vs DeepSeek V3.1 at 15.9%. On AIME 2025, Qwen3-2507 leads at 92.3% vs DeepSeek V3.1 at 88.4%. On GPQA Diamond, Qwen3-2507 leads at 81.1% vs DeepSeek V3.1 at 80.1%. On MMLU-Pro, DeepSeek V3.1 leads at 84.8% vs Qwen3-2507 at 84.4%.