Gemini 2.5 Pro
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling.
Input
Output
Context
1049K
Max Output
66K
Parameters
—
Technical Specifications
Model TypeSpeech-to-text
Context Window1.0M
Max Output Tokens66K
Parameters—
Training Cutoff—
Licenseproprietary
Capabilities
Input Modalities
textimagefileaudiovideo
Output Modalities
text
Features
code_generationfunction_callingjson_modereasoningspeech_to_textstreamingtext_generationvision
Benchmarks
Chatbot Arena
#2
Rank (Text)
+6/-6
arena text ci 95
1446
Arena Score (Text)
13,715
Votes (Text)
#2
Rank (Vision)
+12/-12
arena vision ci 95
1316
Arena Score (Vision)
3,139
Votes (Vision)
Artificial Analysis
21.1%
HLE
88.7%
AIME
84.4%
GPQA
42.8%
SciCode
96.7%
MATH 500
86.2%
MMLU Pro
87.7
Math
31.9
Coding
80.1%
LiveCodeBench
34.6
Intelligence
128
Speed (tok/s)
22.0
TTFA (s)
22.0
TTFT (s)
Resources & Links
proprietary — Proprietary - API access only
Related Tools
Data sourced from official provider APIs and documentation
Last updated: May 5, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.