Benched.ai
View
About
Command Palette
Search for a command to run...
Models
Gemma 3 27B Instruct
Google
Vision Model
Open
Context
Release Date
Mar 12, 2025
Window
128k
Pricing
Per 1M tokens
Input
$0
Output
$0
Blended 3:1
$0
Capabilities
Speed
47 t/s
Input
Output
Reasoning tokens
Latency
TTFT
0.61 ms
500 token response
11.14 s
Benchmarks
Intelligence
●●○○○
Math
●●●○○
Coding
●○○○○
MMLU Pro
66.9%
GPQA
42.8%
HLE
4.7%
SciCode
21.2%
AIME
25.3%
MATH 500
88.3%
LiveCodeBench
13.7%
HumanEval
89.4%