Compare AI models

Specifications
Parameters
1.5B/7B/8B/14B/32B/70B109B
Context window
—10M
API pricing
Cheapest input
—$0.08DeepInfra
Cheapest output
—$0.24DeepInfra
—$35.00DeepInfra · fp8
Benchmarks
LiveCodeBench
57.5%32.8%
GPQA Diamond
65.2%57.2%
Overview
CompanyDeepSeekMeta
Release dateJan 20 2025Apr 5 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 Distill leads LLaMA 4 Scout on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). DeepSeek R1 Distill shipped 75 days before LLaMA 4 Scout, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 Distill has 1.5B/7B/8B/14B/32B/70B parameters, while LLaMA 4 Scout has 109B.

On LiveCodeBench, DeepSeek R1 Distill leads at 57.5% vs LLaMA 4 Scout at 32.8%. On GPQA Diamond, DeepSeek R1 Distill leads at 65.2% vs LLaMA 4 Scout at 57.2%.