Compare AI models

Specifications
Parameters
8B—
Context window
—256k
Benchmarks
LiveCodeBench
60.5%79%
AIME 2025
76.3%91.7%
GPQA Diamond
61.1%87.5%
Overview
CompanyDeepSeekSpaceXSI
Release dateMay 29 2025Jul 9 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok 4 leads DeepSeek R1-0528 Qwen3 8B on 3 of the 3 benchmarks they both report (LiveCodeBench, AIME 2025, GPQA Diamond). DeepSeek R1-0528 Qwen3 8B shipped 41 days before Grok 4, so benchmark comparisons should account for the intervening progress.

DeepSeek R1-0528 Qwen3 8B is open weight, while Grok 4 is closed.

On LiveCodeBench, Grok 4 leads at 79% vs DeepSeek R1-0528 Qwen3 8B at 60.5%. On AIME 2025, Grok 4 leads at 91.7% vs DeepSeek R1-0528 Qwen3 8B at 76.3%. On GPQA Diamond, Grok 4 leads at 87.5% vs DeepSeek R1-0528 Qwen3 8B at 61.1%.