Hugging Face·released 2025-06-191 source
Not yet benchmarked
Claims drawn from cited facts, not live model generation.
Developed by Hugging Face and released in 2025, this model has 3.08 billion parameters, placing it in the compact scale. This compact scale implies a trade-off of greater efficiency and lower cost, but less headroom for complex tasks than larger models.
4 cited facts
This model is not yet benchmarked, so there is no tracked score record to report. With no benchmarks tracked, it holds no current top score.
2 cited facts
No average SOTA gap is disclosed for this model, and it holds the top score on 0 benchmarks, so there is no measured points-behind-the-leader figure to band as frontier, competitive, or well behind. Taken plainly, a leader count of zero means it currently shows no benchmark on which it is the best-scoring entry — none yet, rather than genuine category leadership.
3 cited facts
2 facts cross-checked across data sources: 2 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: huggingface_models
SmolLM3-3B-Base is an AI model developed by Hugging Face, released 2025-06-19. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.