Benched.ai
View
About
Command Palette
Search for a command to run...
Models
Llama 3.1 Instruct 405B
Meta
Open
Context
Release Date
Jul 23, 2024
Knowledge Cutoff
Dec 01, 2023
Window
128k
Pricing
Per 1M tokens
Input
$3.5
Output
$3.5
Blended 3:1
$3.5
Capabilities
Speed
33 t/s
Input
Output
Reasoning tokens
Latency
TTFT
0.66 ms
500 token response
15.72 s
Benchmarks
Intelligence
●●○○○
Math
●●○○○
Coding
●●○○○
MMLU Pro
73.2%
GPQA
51.5%
HLE
4.2%
SciCode
29.9%
AIME
21.3%
MATH 500
70.3%
LiveCodeBench
30.5%
HumanEval
85.4%
Llama 3.1 Instruct 405B