Compare AI models

Specifications
Parameters
—49B
Context window
1M128k
API pricing
Cheapest input
$0.0507Baidu—
Cheapest output
$0.2028Baidu—
$20.28Baidu · fp8—
Benchmarks
Humanity's Last Exam · text only, no tools
39.1%7.64%
GPQA Diamond
90.9%71.97%
Overview
CompanyDeepSeekNVIDIA
Release dateSep 10 2026Jul 25 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek-V4.1-Flash leads Llama Nemotron Super 49B v1.5 on 2 of the 2 benchmarks they both report (Humanity's Last Exam, GPQA Diamond). Llama Nemotron Super 49B v1.5 shipped 412 days before DeepSeek-V4.1-Flash, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (DeepSeek-V4.1-Flash) vs 128k (Llama Nemotron Super 49B v1.5).

On Humanity's Last Exam · text only, no tools, DeepSeek-V4.1-Flash leads at 39.1% vs Llama Nemotron Super 49B v1.5 at 7.64%. On GPQA Diamond, DeepSeek-V4.1-Flash leads at 90.9% vs Llama Nemotron Super 49B v1.5 at 71.97%.