Qwen·released 2024-09-161 source
Not yet benchmarked
Source: models.dev · See every model’s pricing →
Claims drawn from cited facts, not live model generation.
Developed by Qwen, this model is a mid-scale 14.77-billion-parameter model released in 2024, striking a balance between computational efficiency and performance.
3 cited facts
This model is not yet benchmarked.
1 cited fact
The model does not hold the top score on any benchmark, as indicated by sota leader count being 0, meaning it has no genuine category leadership. The average gap to state-of-the-art is unknown, so the model's position relative to the frontier cannot be quantified with precision.
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, modelsdev_models
Qwen2.5-14B-Instruct is an AI model developed by Qwen, released 2024-09-16. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Listed API pricing: $0.35 per million input tokens, $1.4 per million output tokens. See the pricing block for the full breakdown.