Benched.ai
View
About
Command Palette
Search for a command to run...
Models
Llama 3.3 Instruct 70B
Meta
Open
Context
Release Date
Dec 06, 2024
Knowledge Cutoff
Dec 01, 2023
Window
128k
Pricing
Per 1M tokens
Input
$0.585
Output
$0.705
Blended 3:1
$0.59
Capabilities
Speed
113 t/s
Input
Output
Reasoning tokens
Latency
TTFT
0.43 ms
500 token response
4.85 s
Benchmarks
Intelligence
●●○○○
Math
●●●○○
Coding
●○○○○
MMLU Pro
71.3%
GPQA
49.8%
HLE
4.0%
SciCode
26.0%
AIME
30.0%
MATH 500
77.3%
LiveCodeBench
28.8%
HumanEval
86.0%
Llama 3.3 Instruct 70B