Benched.ai
View
About
Command Palette
Search for a command to run...
Models
Mistral Small (Feb '24)
Mistral
Proprietary
Context
Release Date
Feb 26, 2024
Window
32,768
Pricing
Per 1M tokens
Input
$1
Output
$3
Blended 3:1
$1.5
Capabilities
Speed
155 t/s
Input
Output
Reasoning tokens
Latency
TTFT
0.26 ms
500 token response
3.47 s
Benchmarks
Intelligence
●○○○○
Math
●○○○○
Coding
●○○○○
MMLU Pro
41.9%
GPQA
30.2%
HLE
4.4%
SciCode
13.4%
AIME
0.7%
MATH 500
56.2%
LiveCodeBench
11.1%
HumanEval
79.0%