Gemini 2.0 Flash

Published

Dec 11, 2024

Gemini 2.0 Flash is an AI model developed by Google DeepMind and Google (United States), first published in December 2024. It works in the language, vision, audio and 3 more domain, on tasks such as language modeling/generation, question answering, visual question answering and 9 more.

Epoch AI has no training-compute estimate for this model. Training ran on Google TPU v6e Trillium.

Access: API access. Its weights are not openly released.

Full record

Organization: Google DeepMind, Google
Country of organization: United States
Domain: Language, Vision, Audio, Speech, Video, Multimodal
Task: Language modeling/generation, Question answering, Visual question answering, Speech recognition (ASR), Code generation, Quantitative reasoning, Video description, Translation, Chat, Table tasks, Search, Text summarization
Training hardware: Google TPU v6e Trillium
Model accessibility: API access
Open weights: No

Benchmark results

01

Epoch Capabilities Index

ECI Score

135.8