Benched.ai
View
About
Command Palette
Search for a command to run...
Models
Phi-4 Mini Instruct
Microsoft Azure
Open
Context
Release Date
Feb 26, 2024
Knowledge Cutoff
Jun 01, 2024
Window
128k
Pricing
Per 1M tokens
Input
$0
Output
$0
Blended 3:1
$0
Capabilities
Speed
57 t/s
Input
Output
Reasoning tokens
Latency
TTFT
0.32 ms
500 token response
9.10 s
Benchmarks
Intelligence
●○○○○
Math
●●○○○
Coding
●○○○○
MMLU Pro
46.5%
GPQA
33.1%
HLE
4.2%
SciCode
10.8%
AIME
3.0%
MATH 500
69.6%
LiveCodeBench
12.6%
HumanEval
74.3%