Benched.ai
View
About
Command Palette
Search for a command to run...
Models
Qwen2.5 Instruct 72B
Alibaba
Open
Context
Release Date
Sep 19, 2024
Window
131k
Pricing
Per 1M tokens
Input
$0
Output
$0
Blended 3:1
$0
Capabilities
Speed
58 t/s
Input
Output
Reasoning tokens
Latency
TTFT
1.27 ms
500 token response
9.88 s
Benchmarks
Intelligence
●●○○○
Math
●●●○○
Coding
●○○○○
MMLU Pro
72.0%
GPQA
49.1%
HLE
4.2%
SciCode
26.7%
AIME
16.0%
MATH 500
85.8%
LiveCodeBench
27.6%
HumanEval
88.3%