readable AI benchmarks (simplified)
NVIDIA
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) has a Quality Score of 19.6, ranking 414th among 572 scored models. It has a 128k token context window. Its Reliability Score is 27.6, ranking 359th among 574 scored models, below average (total average: 36.5).
Quality Score19.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability27.6
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 128k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- not available
- Output
- not available
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 7.5
- Coding
- not available
- Agentic
- not available
- Omniscience
- -44.9
- Correct
- 20.1%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 85.0%
Correct 20.1%Incorrect 64.9%Partial / not attempted 15.0%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 7%
- GPQA Diamond
- 73%
- CritPt
- 0%
- AA-Omniscience
- 28%
Similar models
- NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIAQuality Score 20.3Value Score not available
- Llama Nemotron Super 49B v1.5 (Reasoning)NVIDIAQuality Score 20.0Value Score not available
- NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIAQuality Score 19.0Value Score 17.5
- Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIAQuality Score 18.5Value Score 15.0
- Llama 3.3 Nemotron Super 49B v1 (Reasoning)NVIDIAQuality Score 17.3Value Score not available
- Nemotron Cascade 2 30B A3BNVIDIAQuality Score 21.1Value Score not available