Compare AI models

Specifications
Parameters
671B4B/30B/235B
Context window
128k256k
API pricing
Cheapest input
$0.27SiliconFlow—
Cheapest output
$0.41SiliconFlow—
$74.50SiliconFlow · fp8—
Benchmarks
LiveCodeBench
74.1%74.1%
AIME 2025
89.3%92.3%
GPQA Diamond
79.9%81.1%
MMLU-Pro
85%84.4%
Overview
CompanyDeepSeekQwen
Release dateSep 29 2025Jul 21 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3-2507 leads DeepSeek V3.2 Exp on 2 of the 4 benchmarks they both report (LiveCodeBench, AIME 2025, GPQA Diamond, MMLU-Pro). Qwen3-2507 shipped 70 days before DeepSeek V3.2 Exp, so benchmark comparisons should account for the intervening progress.

DeepSeek V3.2 Exp has 671B parameters, while Qwen3-2507 has 4B/30B/235B. Context windows are 128k (DeepSeek V3.2 Exp) vs 256k (Qwen3-2507).

On LiveCodeBench, both models score 74.1%. On AIME 2025, Qwen3-2507 leads at 92.3% vs DeepSeek V3.2 Exp at 89.3%. On GPQA Diamond, Qwen3-2507 leads at 81.1% vs DeepSeek V3.2 Exp at 79.9%. On MMLU-Pro, DeepSeek V3.2 Exp leads at 85% vs Qwen3-2507 at 84.4%.