Compare AI models

Specifications
Parameters
671B—
Context window
128k1M
Benchmarks
SWE-Bench Verified
49.2%12.5%
LiveCodeBench
65.9%28.9%
GPQA Diamond
71.5%51.5%
SimpleQA
30.1%21.7%
MMLU-Pro
84%71.6%
Overview
CompanyDeepSeekGoogle
Release dateJan 20 2025Feb 5 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads Gemini 2.0 Flash-Lite on 5 of the 5 benchmarks they both report. DeepSeek R1 shipped 16 days before Gemini 2.0 Flash-Lite, so benchmark comparisons should account for the intervening progress.

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

On SWE-Bench Verified, DeepSeek R1 leads at 49.2% vs Gemini 2.0 Flash-Lite at 12.5%. On LiveCodeBench, DeepSeek R1 leads at 65.9% vs Gemini 2.0 Flash-Lite at 28.9%. On GPQA Diamond, DeepSeek R1 leads at 71.5% vs Gemini 2.0 Flash-Lite at 51.5%. On SimpleQA, DeepSeek R1 leads at 30.1% vs Gemini 2.0 Flash-Lite at 21.7%. On MMLU-Pro, DeepSeek R1 leads at 84% vs Gemini 2.0 Flash-Lite at 71.6%.