Benched.ai
View
About
Command Palette
Search for a command to run...
Models
Qwen3 235B A22B (Reasoning)
Alibaba
Frontier Model
Reasoning
Open
Context
Release Date
Apr 28, 2025
Window
128k
Pricing
Per 1M tokens
Input
$0.7
Output
$8.4
Blended 3:1
$2.625
Capabilities
Speed
70 t/s
Input
Output
Reasoning tokens
Latency
TTFT
1.23 ms
500 token response
36.72 s
Benchmarks
Reasoning
●●●○○
Math
●●●●○
Coding
●●●○○
MMLU Pro
82.8%
GPQA
70.0%
HLE
11.7%
SciCode
39.9%
AIME
84.0%
MATH 500
93.0%
LiveCodeBench
62.2%