Benched.ai
View
About
Command Palette
Search for a command to run...
Models
Gemini 2.5 Pro Preview 0325
Google
Frontier Model
Reasoning
Vision Model
Proprietary
Context
Release Date
Mar 25, 2025
Knowledge Cutoff
Jan 01, 2025
Window
1M
Pricing
Per 1M tokens
Input
$1.25
Output
$10
Blended 3:1
$3.4375
Capabilities
Speed
153 t/s
Input
Output
Reasoning tokens
Latency
TTFT
41.22 ms
500 token response
44.49 s
Benchmarks
Reasoning
●●●○○
Math
●●●●●
Coding
●●●○○
MMLU Pro
85.8%
GPQA
83.6%
HLE
17.1%
SciCode
39.5%
AIME
87.0%
MATH 500
98.0%
LiveCodeBench
77.8%
HumanEval
98.5%
Preview checkpoint, see latest.