Gemini 1.5 Pro vs Claude 3.5 Sonnet: 2024 Models
Gemini for 1M-token context; Claude 3.5 Sonnet for SWE-bench-class coding tasks.
Gemini 1.5 Pro
The model that proved 1M-token context was practical. Video and audio native.
Use this when
Documents over 200K tokens, video analysis in 2024.
Full profile →Claude 3.5 Sonnet
The model that made Claude the coding default. Coding benchmarks beat GPT-4o at launch.
Use this when
Coding benchmark performance, mid-2024 best-in-class coding.
Full profile →Cost comparison
Gemini $3.50/$10.50 per M; Claude 3.5 Sonnet $3/$15 per M.