Benched.ai
View
About
Command Palette
Search for a command to run...
Models
Mixtral 8x7B Instruct
Mistral
Open
Context
Release Date
Dec 11, 2023
Window
32,768
Pricing
Per 1M tokens
Input
$0.7
Output
$0.7
Blended 3:1
$0.7
Capabilities
Speed
54 t/s
Input
Output
Reasoning tokens
Latency
TTFT
0.36 ms
500 token response
9.55 s
Benchmarks
Intelligence
●○○○○
Math
●○○○○
Coding
○○○○○
MMLU Pro
38.7%
GPQA
29.2%
HLE
4.5%
SciCode
2.8%
AIME
0.0%
MATH 500
29.9%
LiveCodeBench
6.6%
HumanEval
1.2%
Mixtral 8x7B Instruct