Compare AI models

Specifications
Parameters
8B—
Context window
—2M
Benchmarks
LiveCodeBench
60.5%80%
AIME 2025
76.3%92%
GPQA Diamond
61.1%85.7%
Overview
CompanyDeepSeekSpaceXSI
Release dateMay 29 2025Sep 19 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok 4 Fast 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 113 days before Grok 4 Fast, so benchmark comparisons should account for the intervening progress.

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

On LiveCodeBench, Grok 4 Fast leads at 80% vs DeepSeek R1-0528 Qwen3 8B at 60.5%. On AIME 2025, Grok 4 Fast leads at 92% vs DeepSeek R1-0528 Qwen3 8B at 76.3%. On GPQA Diamond, Grok 4 Fast leads at 85.7% vs DeepSeek R1-0528 Qwen3 8B at 61.1%.