A 32-billion-parameter open reasoning language model released in the Qwen ecosystem and trained with reinforcement learning to improve reasoning and agent capabilities.
Pricing
Model profile · Current snapshot
Input / 1M
$0.66
Output / 1M
$1.00
Blended / 1M
$0.745
Output TPS
0
TTFT (s)
0
Model Intelligence
Arena ranking
10
Benchmarkable
Yes
Model level
release
Intelligence Index
9.5
Math Index
29
MMLU Pro
0.76
GPQA
0.59
HLE
0.07
LiveCodeBench
0.63
MATH-500
0.96
AIME
0.78
AIME 2025
0.29
IFBench
0.39
LCR
0.27
Recent stories
0 linked stories
No linked stories yet.