← All benchmarks

Llama Nemotron Super 49B v1.5 (Reasoning)

NVIDIA · Released 2025-07-25 · Independent benchmark scores from Artificial Analysis

Intelligence Index
12.4
Output speed
78.7
tokens/sec
Blended price
$0.40
per 1M tokens
Time to first token
5.39s

Model metadata

Model IDe1cfa926-9e2b-4a0d-8c31-48366a5041c5
Slugllama-nemotron-super-49b-v1-5-reasoning
Release date2025-07-25
ProviderNVIDIA
Provider slugnvidia
Output speed78.7 tok/s
Time to first token5.39s
Time to first answer30.82s
Blended price ($/1M)$0.40
Input price ($/1M)$0.40
Output price ($/1M)$0.40

All evaluation scores (17)

aime86.0%
aime 2576.7%
artificial analysis coding index
artificial analysis intelligence index12.40
artificial analysis math index76.70
gpqa74.8%
hle6.8%
ifbench37.0%
lcr34.0%
livecodebench73.7%
math 50098.3%
mmlu pro81.4%
scicode34.8%
tau banking
tau228.1%
terminalbench hard5.3%
terminalbench v2 1

Source: artificialanalysis.ai/models/llama-nemotron-super-49b-v1-5-reasoning

Benchmark data from Artificial Analysis.