Benched.ai
View
About
Command Palette
Search for a command to run...
Models
Mixtral 8x22B Instruct
Mistral
Open
Context
Release Date
Apr 17, 2024
Window
65,384
Pricing
Per 1M tokens
Input
$2
Output
$6
Blended 3:1
$3
Capabilities
Speed
44 t/s
Input
Output
Reasoning tokens
Latency
TTFT
0.33 ms
500 token response
11.66 s
Benchmarks
Intelligence
●○○○○
Math
●○○○○
Coding
●○○○○
MMLU Pro
53.7%
GPQA
33.2%
HLE
4.1%
SciCode
18.8%
AIME
0.0%
MATH 500
54.5%
LiveCodeBench
14.8%
HumanEval
72.1%