Benched.ai
View
About
Command Palette
Search for a command to run...
Models
Mistral Medium
Mistral
Proprietary
Context
Release Date
Dec 11, 2023
Window
32,768
Pricing
Per 1M tokens
Input
$2.75
Output
$8.1
Blended 3:1
$4.0875
Capabilities
Speed
80 t/s
Input
Output
Reasoning tokens
Latency
TTFT
0.40 ms
500 token response
6.66 s
Benchmarks
Intelligence
●○○○○
Math
●○○○○
Coding
●○○○○
MMLU Pro
49.1%
GPQA
34.9%
HLE
3.4%
SciCode
11.8%
AIME
3.7%
MATH 500
40.5%
LiveCodeBench
9.9%
Mistral Medium