Qwen·released 2025-07-311 source
Not yet benchmarked
Source: models.dev, OpenRouter · See every model’s pricing →
Claims drawn from cited facts, not live model generation.
Developed by Qwen and released in 2025, this model is a mid-size system with 30.53 billion parameters. That mid-size scale implies a balance between efficiency and lower cost at the smaller end and more headroom, along with greater expense, at the larger end.
4 cited facts
This model is not yet benchmarked: it is scored on no tracked benchmarks and holds no current top score.
2 cited facts
With an average SOTA gap that is unknown, the position cannot be quantified in points; what is clear is that it holds the top score on none of its benchmarks (sota leader count of 0), which means no genuine category leadership yet.
2 cited facts
6 facts cross-checked across data sources: 2 corroborated, 2 single-source, 2 disputed.
Source facts, citations, and refresh stamp for this record.
Sources: huggingface_models, modelsdev_models, openrouter_models
Qwen3-Coder-30B-A3B-Instruct is an AI model developed by Qwen, released 2025-07-31. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Listed API pricing: $0.45 per million input tokens, $2.25 per million output tokens (prices disputed across sources). See the pricing block for the full breakdown.