Llama Nemotron Super 49B v1.5 (Non-reasoning)

NVIDIA

NVIDIA Open Model License Agreement

Analysis of NVIDIA's Llama Nemotron Super 49B v1.5 (Non-reasoning) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.

Context

Release Date: Jul 25, 2025
Window: 128k

PricingPer 1M tokens

Input: $0.1
Output: $0.4
Blended 3:1: $0.175

Capabilities

Speed: 47 t/s
Input
Output
Reasoning tokens

Latency

TTFT: 1.31 ms
500 token response: 11.99 s

Benchmarks

Intelligence: ●○○○○
Math: ○○○○○
Coding: ●○○○○
MMLU Pro: 69.2%
GPQA: 48.1%
HLE: 4.3%
SciCode: 23.8%
AIME: 13.7%
MATH 500: 77.0%
LiveCodeBench: 29.0%
HumanEval: 85.6%

Analysis of NVIDIA's Llama Nemotron Super 49B v1.5 (Non-reasoning) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.