Benched.ai
View
About
Command Palette
Search for a command to run...
Models
Llama 3 Instruct 70B
Meta
Open
Context
Release Date
Apr 18, 2024
Knowledge Cutoff
Dec 01, 2023
Window
8,192
Pricing
Per 1M tokens
Input
$0.7250000000000001
Output
$0.8400000000000001
Blended 3:1
$0.8400000000000001
Capabilities
Speed
45 t/s
Input
Output
Reasoning tokens
Latency
TTFT
0.44 ms
500 token response
11.47 s
Benchmarks
Intelligence
●○○○○
Math
●○○○○
Coding
●○○○○
MMLU Pro
57.4%
GPQA
37.9%
HLE
4.4%
SciCode
18.9%
AIME
0.0%
MATH 500
48.3%
LiveCodeBench
19.8%
HumanEval
79.0%
Llama 3 Instruct 70B