MMODELYST
Models/Llama 3.1 Nemotron Ultra 253B v1
MDL

Llama 3.1 Nemotron Ultra 253B v1

NVIDIA

Verified against Artificial Analysis · Jul 13, 2026
Capability
56
percentile index
Price /M
$0.6 / $1.8
in / out
Context
Avg score
43.7
11 benchmarks
AA Intelligence
9.1
index
Speed
52 tok/s
TTFT 0.7s
Released
Apr 7, 2025
About

Llama 3.1 Nemotron Ultra 253B v1 is a open-weights model in the Llama family from NVIDIA. Benchmarked on 11 evals, averaging 43.7.

Benchmark scores · 11
avg 43.7 — higher is better
MATH
95.2
MMLU-Pro
82.5
GPQA Diamond
72.8
LiveCodeBench
64.1
AIME
63.7
IFBench
38.2
SciCode
34.7
τ²-bench
11.4
Humanity's Last Exam
8.1
AA Long-Context Reasoning
7.3
Terminal-Bench Hard
2.3
Details
PublisherNVIDIA
FamilyLlama
Parameters
License
WeightsOpen
ReleasedApr 7, 2025
Performance & price
Output speed52 tok/s
Latency (TTFT)0.7s
First answer39s
Price in / out$0.6 / $1.8 per 1M
Blended price$0.9 / 1M
Math index63.7

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$1.8/M