DeepSeek·released 2024-01-251 source
Not yet benchmarked
Claims drawn from cited facts, not live model generation.
Developed by DeepSeek, this model was released in 2024 with a mid-size scale of 6.91 billion parameters. That mid-size scale offers a practical balance — more headroom than compact models while remaining less expensive and more efficient than frontier-scale systems.
4 cited facts
This model is not yet benchmarked on any tracked benchmark, so it holds no current top score.
2 cited facts
The model holds the top score on none of the tracked benchmarks (sota leader count of 0), so it has no category leadership yet. Because its average gap to the SOTA score is unknown, no frontier or competitive band can be stated.
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
deepseek-coder-7b-instruct-v1.5 is an AI model developed by DeepSeek, released 2024-01-25. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.