For Developers/Models/Gemini 2.5 Pro
Closed SourceGoogle DeepMindReleased 2025-03

Gemini 2.5 Pro

Google's most capable model with a 1M token context and top science benchmark scores

Context window

1M

Input / 1M tokens

$1.25

Output / 1M tokens

$10.00

Provider

Google DeepMind

$1.25/1M for first 200K tokens; $2.50/1M beyond

Gemini 2.5 Pro holds the top position on GPQA Diamond (86.4%), reflecting genuine strength on graduate-level science and math. Its 1M context window is the largest of any commercial model, making it the go-to choice for tasks involving large codebases, long documents, or multi-hour video analysis. Pricing is competitive with Claude Sonnet despite higher raw capability.

Strengths

  • Largest commercial context window (1M tokens)
  • Top benchmark scores on science and math
  • Strong multimodal: video, audio, images
  • Competitive pricing for the capability tier
  • Native Google Search and code execution tools

Best for developers who...

Very long document analysisVideo and multimodal understandingScientific research tasksLarge codebase comprehension

Benchmarks

BenchmarkScoreNotes
GPQA Diamond86.4%State-of-the-art on expert science
MMLU90.9%Top generalist knowledge
SWE-bench Verified63.2%Best coding benchmark at launch

Source: Google DeepMind Gemini 2.5 Pro

Tools powered by Gemini 2.5 Pro

Compare Gemini 2.5 Pro with

All model comparisons →

Learn the concepts