#29
Gemini 2.5 Flash
gemini-2.5-flash

Gemini 2.5 Flash is Google's balanced workhorse model for high-volume tasks at scale. With strong scores on MMLU (~85%) and solid reasoning capabilities, it delivers reliable multimodal processing across text, images, video, and audio. The model excels at code execution, function calling, and search grounding while maintaining fast inference speeds for production applications.

Performance Metrics

Helpfulness
Instruction Following
Comprehension
Empathy
Creative Writing
80.40
Helpfulness
85
Empathy
74
Instruction Following
87
Creative Writing
70
Comprehension
86
Speed
Avg 92 tok/s

Model Specifications

Release Date
March 2025
Lab
Google
Type
Proprietary
Context Size
1M
Max Output Tokens
65.5K
Cost per 1M tokens
$0.30 / $2.50
Model Inputs
Text, Audio, Images, Video, PDFs
Model Outputs
Text
Tool Calling
Enabled

Compare With Similar Models