Compare AI models

Specifications
Parameters
671B4B/30B/235B
Context window
128k256k
Benchmarks
LiveCodeBench
65.9%74.1%
GPQA Diamond
71.5%81.1%
MMLU-Pro
84%84.4%
Overview
CompanyDeepSeekQwen
Release dateJan 20 2025Jul 21 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3-2507 leads DeepSeek R1 on 3 of the 3 benchmarks they both report (LiveCodeBench, GPQA Diamond, MMLU-Pro). DeepSeek R1 shipped 182 days before Qwen3-2507, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 has 671B parameters, while Qwen3-2507 has 4B/30B/235B. Context windows are 128k (DeepSeek R1) vs 256k (Qwen3-2507).

On LiveCodeBench, Qwen3-2507 leads at 74.1% vs DeepSeek R1 at 65.9%. On GPQA Diamond, Qwen3-2507 leads at 81.1% vs DeepSeek R1 at 71.5%. On MMLU-Pro, Qwen3-2507 leads at 84.4% vs DeepSeek R1 at 84%.