Better than 62% of all models
Context
N/A
Input $/1M
TBD
Output $/1M
TBD
Type
text
License
Proprietary
Benchmarks
7 tested
Data updated today
About
Tested on 7 benchmarks with 53.4% average. Top scores: HellaSwag (76.5%), PIQA (64.8%), Winogrande (56.0%).
Capabilities
reasoning
44.9
#55 globally
math
46.0
#90 globally
knowledge
56.6
#71 globally
Benchmark Scores
Compare AllTested on 7 benchmarks · Ranked across 3 categories
Score Distribution (all 233 models)
0255075100
▲ You are here
reasoningCompare reasoning →
BBH
44.9—BIG-Bench Hard. 23 challenging tasks from BIG-Bench where prior language models fell below average human performance.
mathCompare math →
GSM8K
46.0—Grade school math word problems. 8,500 problems testing multi-step arithmetic reasoning. A foundational math benchmark.
knowledgeCompare knowledge →
HellaSwag
76.5—Sentence completion requiring commonsense reasoning about physical and social situations. Tests real-world understanding.
PIQA
64.8—Physical Intuition QA. Tests understanding of everyday physical interactions and commonsense physics.
Winogrande
56.0—Commonsense coreference resolution. Tests understanding of pronoun references in ambiguous sentences.
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Research
Documentation
Community
BenchGecko API
nemotron-4-15b
Specifications
- Typetext
- ContextN/A
- ReleasedJan 2024
- LicenseProprietary
- Statusbenchmark-only
Available On
U
UnknownTBDLearn More
Share & Export
Frequently Asked Questions
Nemotron-4 15B is a proprietary text AI model by Unknown, released in January 2024. It has an average benchmark score of 56.0.