Back

NVIDIA

Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)

ReasoningOpen weights
Intelligence
7.5
Rank 533 of 744 measured models
Context window
128K
Rank 773 of 1199 measured models

Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) scores 7.5 on the Artificial Analysis Intelligence Index, ranking 533rd of 744 measured models. The closest models on this index are Devstral Small 2 (7.5), ERNIE 4.5 300B A47B (7.5), and Nous: Hermes 4 405B (7.5).

Artificial Analysis Indices
Intelligence7.5
Rank 533 of 744 measured models
Math63.7
Rank 109 of 270 measured models
Standard Benchmarks
MMLU Pro82.5%
Rank 68 of 349 measured models
GPQA Diamond72.8%
Rank 294 of 619 measured models
HLE7.4%
Rank 380 of 664 measured models
LiveCodeBench64.1%
Rank 101 of 343 measured models
MATH-50095.2%
Rank 41 of 202 measured models
AIME 202474.7%
Rank 32 of 194 measured models
AIME 202563.7%
Rank 109 of 270 measured models
IFBench38.2%
Rank 296 of 450 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy