Compare AI models

Specifications
Parameters
671B—
Context window
128k1M
Benchmarks
SWE-Bench Verified
49.2%21.4%
LiveCodeBench
65.9%35.1%
GPQA Diamond
71.5%62.1%
MMLU-Pro
84%76.4%
Overview
CompanyDeepSeekGoogle
Release dateJan 20 2025Dec 11 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads Gemini 2.0 Flash on 4 of the 4 benchmarks they both report (SWE-Bench Verified, LiveCodeBench, GPQA Diamond, MMLU-Pro). Gemini 2.0 Flash shipped 40 days before DeepSeek R1, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek R1) vs 1M (Gemini 2.0 Flash). DeepSeek R1 is open weight, while Gemini 2.0 Flash is closed.

On SWE-Bench Verified, DeepSeek R1 leads at 49.2% vs Gemini 2.0 Flash at 21.4%. On LiveCodeBench, DeepSeek R1 leads at 65.9% vs Gemini 2.0 Flash at 35.1%. On GPQA Diamond, DeepSeek R1 leads at 71.5% vs Gemini 2.0 Flash at 62.1%. On MMLU-Pro, DeepSeek R1 leads at 84% vs Gemini 2.0 Flash at 76.4%.