Compare AI models

Specifications
Parameters
284B4B
Context window
1M256k
API pricing
Cheapest input
$0.0383Relace—
Cheapest output
$0.0806Baidu—
$12.09Baidu · fp8—
Benchmarks
GPQA Diamond
88.1%53.2%
Overview
CompanyDeepSeekNVIDIA
Release dateApr 24 2026Mar 16 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek-V4-Flash leads Nemotron 3 Nano 4B on 1 of the 1 benchmark they both report (GPQA Diamond). Nemotron 3 Nano 4B shipped 39 days before DeepSeek-V4-Flash, so benchmark comparisons should account for the intervening progress.

DeepSeek-V4-Flash has 284B parameters, while Nemotron 3 Nano 4B has 4B. Context windows are 1M (DeepSeek-V4-Flash) vs 256k (Nemotron 3 Nano 4B).

On GPQA Diamond, DeepSeek-V4-Flash leads at 88.1% vs Nemotron 3 Nano 4B at 53.2%.