DeepSeek·released 2025-01-201 source
Not yet benchmarked
Claims drawn from cited facts, not live model generation.
Developed by DeepSeek, this model is a compact 14.77-billion-parameter release from 2025. That scale keeps deployment efficient and comparatively inexpensive, though it offers less headroom than frontier-scale systems.
4 cited facts
This model is not yet benchmarked on any tracked benchmark. It therefore holds no current top score.
2 cited facts
Because avg sota gap is unknown, the model's standing is judged by sota leader count, which is 0: it holds the top score on none of the benchmarks, meaning it has no confirmed category leadership yet.
2 cited facts
2 facts cross-checked across data sources: 2 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: huggingface_models
DeepSeek-R1-Distill-Qwen-14B is an AI model developed by DeepSeek, released 2025-01-20. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.