Gemini 2.5
Google DeepMind — Gemini
rich detail 16 method fields published
Evaluation
Audio understanding benchmark suite (ASR/AST)
Audio understanding evaluated with public benchmarks for ASR and AST, compared to earlier Gemini models and GPT models under comparable testing conditions (Table 5)
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.