Benched.ai
View
About
Command Palette
Search for a command to run...
Models
Llama 3.2 Instruct 3B
Meta
Open
Context
Release Date
Sep 25, 2024
Knowledge Cutoff
Dec 01, 2023
Window
128k
Pricing
Per 1M tokens
Input
$0.045
Output
$0.055
Blended 3:1
$0.0475
Capabilities
Speed
115 t/s
Input
Output
Reasoning tokens
Latency
TTFT
0.37 ms
500 token response
4.73 s
Benchmarks
Intelligence
●○○○○
Math
●○○○○
Coding
○○○○○
MMLU Pro
34.7%
GPQA
25.5%
HLE
5.2%
SciCode
5.2%
AIME
6.7%
MATH 500
48.9%
LiveCodeBench
8.3%
HumanEval
55.7%
Llama 3.2 Instruct 3B