MMODELYST
Models/Llama Nemotron Super 49B v1.5
MDL

Llama Nemotron Super 49B v1.5

NVIDIA

Verified against Artificial Analysis · Jul 13, 2026
Capability
65
percentile index
Price /M
$0.4 / $0.4
in / out
Context
Avg score
50.1
11 benchmarks
AA Intelligence
12.4
index
Speed
51 tok/s
TTFT 0.2s
Released
Jul 25, 2025
About

Llama Nemotron Super 49B v1.5 is a open-weights model in the Llama family from NVIDIA. Benchmarked on 11 evals, averaging 50.1.

Benchmark scores · 11
avg 50.1 — higher is better
MATH
98.3
MMLU-Pro
81.4
AIME
76.7
GPQA Diamond
74.8
LiveCodeBench
73.7
IFBench
37
SciCode
34.8
AA Long-Context Reasoning
34
τ²-bench
28.1
Humanity's Last Exam
6.8
Terminal-Bench Hard
5.3
Details
PublisherNVIDIA
FamilyLlama
Parameters
License
WeightsOpen
ReleasedJul 25, 2025
Performance & price
Output speed51 tok/s
Latency (TTFT)0.2s
First answer40s
Price in / out$0.4 / $0.4 per 1M
Blended price$0.4 / 1M
Math index76.7

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers
Artificial Analysis$0.4/M