Qwen·released 2024-11-061 source
Not yet benchmarked
Claims drawn from cited facts, not live model generation.
This model was developed by Qwen and released in 2024 as a compact 3.09-billion-parameter system. That compact scale buys efficiency and lower serving cost, at the price of the extra headroom that larger models command.
4 cited facts
This model is not yet scored on any tracked benchmarks. With no tracked benchmark results on record, it holds no current top score.
2 cited facts
The average gap to state of the art is not disclosed, so no figure can be given for how many points this model trails the leading score on its benchmarks. It holds the top score on 0 of its benchmarks, which means there is no benchmark here where it currently sits at the front of the pack.
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
Qwen2.5-Coder-3B-Instruct is an AI model developed by Qwen, released 2024-11-06. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.