Gemini 2.5 Flash
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater 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
fileimagetextaudiovideo
Output Modalities
text
Features
code_generationfunction_callingjson_modereasoningspeech_to_textstreamingtext_generationvision
Benchmarks
Chatbot Arena
#17
Rank (Text)
+5/-5
arena text ci 95
1396
Arena Score (Text)
18,655
Votes (Text)
#11
Rank (Vision)
+10/-10
arena vision ci 95
1254
Arena Score (Vision)
4,944
Votes (Vision)
Artificial Analysis
5.1%
HLE
50.0%
AIME
68.3%
GPQA
29.1%
SciCode
93.2%
MATH 500
80.9%
MMLU Pro
60.3
Math
17.8
Coding
49.5%
LiveCodeBench
20.6
Intelligence
200
Speed (tok/s)
0.529
TTFA (s)
0.529
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.