Benched.ai
View
About
Command Palette
Search for a command to run...
Models
Codestral (Jan '25)
Mistral
Proprietary
Context
Release Date
Jan 13, 2025
Window
256k
Pricing
Per 1M tokens
Input
$0.3
Output
$0.9
Blended 3:1
$0.45
Capabilities
Speed
169 t/s
Input
Output
Reasoning tokens
Latency
TTFT
0.28 ms
500 token response
3.23 s
Benchmarks
Intelligence
●○○○○
Math
●●○○○
Coding
●○○○○
MMLU Pro
44.6%
GPQA
31.2%
HLE
4.5%
SciCode
24.7%
AIME
4.3%
MATH 500
60.7%
LiveCodeBench
24.3%
HumanEval
84.8%
Codestral (Jan '25)