TAU2
Measured May 29, 2026Source
Score
0.11
Models15 0 
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
NVIDIANVIDIAUnited States
A large-scale reasoning model from NVIDIA's Nemotron family, built upon the Llama 3.1 architecture. It is optimized for complex, multi-step reasoning tasks and is designed to deliver high accuracy in logical inference and problem-solving.
ReasoningCoding
Input / 1M tokens
$0.60Output / 1M tokens
$1.80Output tokens/s
52.49First-token seconds
0.75sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 29, 2026Source
Score
0.02
Lcr
Measured May 29, 2026Source
Score
0.07
Ifbench
Measured May 29, 2026Source
Score
0.38
Aime 25
Measured May 29, 2026Source
Score
0.64
Aime
Measured May 29, 2026Source
Score
0.75
Math 500
Measured May 29, 2026Source
Score
0.95
Scicode
Measured May 29, 2026Source
Score
0.35
Livecodebench
Measured May 29, 2026Source
Score
0.64
Hle
Measured May 29, 2026Source
Score
0.08
Gpqa
Measured May 29, 2026Source
Score
0.73
Mmlu Pro
Measured May 29, 2026Source
Score
0.83
Artificial Analysis Math Index
Measured May 29, 2026Source
Score
63.7
Artificial Analysis Coding Index
Measured May 29, 2026Source
Score
13.1
Artificial Analysis Intelligence Index
Measured May 29, 2026Source
Score
15
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
User ratings
Loading ratings...
Discussion
Thinking... Make sure you are connected to GitHub server