Qwen·released 2025-07-281 source
Not yet benchmarked
Claims drawn from cited facts, not live model generation.
Developed by Qwen and released in 2025, this model is a mid-size system with about 30.5 billion parameters — enough headroom for substantial tasks, yet more efficient and less costly than frontier-scale models.
3 cited facts
This model is not yet benchmarked on any tracked benchmark, so it holds no current top scores.
2 cited facts
With sota leader count equal to 0, this model currently holds no top score on any benchmark, so there is no category leadership to report. Because avg sota gap is unknown, no frontier gap can be stated.
2 cited facts
6 facts cross-checked across data sources: 6 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: huggingface_models, openrouter_models
Qwen3-30B-A3B-Instruct-2507 is an AI model developed by Qwen, released 2025-07-28. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.