Benched.ai
View
About
Command Palette
Search for a command to run...
Models
Qwen2.5 Max
Alibaba
Proprietary
Context
Release Date
Jan 28, 2025
Window
32,000
Pricing
Per 1M tokens
Input
$1.6
Output
$6.4
Blended 3:1
$2.8
Capabilities
Speed
42 t/s
Input
Output
Reasoning tokens
Latency
TTFT
1.36 ms
500 token response
13.36 s
Benchmarks
Intelligence
●●○○○
Math
●●●○○
Coding
●●○○○
MMLU Pro
76.2%
GPQA
58.7%
HLE
4.5%
SciCode
33.7%
AIME
23.3%
MATH 500
83.5%
LiveCodeBench
35.9%
HumanEval
92.9%