AI Benchmark Model

Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)

Benchmark scores, pricing, speed, and model comparisons for Llama 3.1 Nemotron Ultra 253B v1 (Reasoning).

Key scores

Intelligence15.0Index score
Coding13.1Index score
Math63.7Index score
Speed41.5Tokens/sec
Blended Cost$0.90Per 1M tokens

Review benchmark scores, pricing, performance data, and generated comparisons for this AI model.

Benchmark results

12 tracked benchmark rows for Llama 3.1 Nemotron Ultra 253B v1 (Reasoning).

MATH 500 Math
95.2%
MMLU Pro Knowledge
82.5%
AIME Math
74.7%
GPQA Reasoning
72.8%
LiveCodeBench Code
64.1%
AIME 2025 Math
63.7%
IFBench Other
38.2%
SciCode Other
34.7%
TAU2 Other
11.4%
HLE Other
8.1%
LCR Other
7.3%
TerminalBench Hard Other
2.3%

Comments (0)

No comments yet

Be the first to share your thoughts!