Google DeepMind·released 2024-07-161 source
Not yet benchmarked
Claims drawn from cited facts, not live model generation.
This model was developed by Google DeepMind and released in 2024. With 2.61 billion parameters, it is a compact-scale model, a size that favors efficiency and lower cost over the additional headroom of larger systems.
3 cited facts
This model has not yet been benchmarked on any tracked evaluation, and it accordingly holds no current top score.
2 cited facts
With no known average gap to the leader, this model holds the top score on 0 tracked benchmarks, meaning it shows no category leadership on any evaluated benchmark.
1 cited fact
2 facts cross-checked across data sources: 2 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: huggingface_models
gemma-2-2b-it is an AI model developed by Google DeepMind, released 2024-07-16. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.