Benched.ai
View
About
Command Palette
Search for a command to run...
Models
Qwen2.5 Coder Instruct 32B
Alibaba
Open
Context
Release Date
Nov 11, 2024
Window
131k
Pricing
Per 1M tokens
Input
$0.135
Output
$0.18
Blended 3:1
$0.14625
Capabilities
Speed
53 t/s
Input
Output
Reasoning tokens
Latency
TTFT
0.38 ms
500 token response
9.87 s
Benchmarks
Intelligence
●●○○○
Math
●●○○○
Coding
●○○○○
MMLU Pro
63.5%
GPQA
41.7%
HLE
3.8%
SciCode
27.1%
AIME
12.0%
MATH 500
76.7%
LiveCodeBench
29.5%
HumanEval
90.2%