Qwen·released 2025-04-281 source
Not yet benchmarked
Claims drawn from cited facts, not live model generation.
This model was developed by Qwen. At 4.02 billion parameters, it is a compact model released in 2025, a scale that favors efficiency and lower cost over the headroom of larger, more expensive systems.
3 cited facts
This model is not yet benchmarked, with zero tracked benchmarks on record. As a result, it holds no current top score.
2 cited facts
The average gap to the state of the art is unknown, so no points-behind reading can be given, and the model holds the top score on zero benchmarks — meaning there is no category leadership yet rather than a measured shortfall.
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
Qwen3-4B-Base is an AI model developed by Qwen, released 2025-04-28. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.