AIVentureBeatabout 2 hours ago
Qwen 3.8-Max Matches Claude Opus, Trails Kimi K3
6 min read
Alibaba's Qwen 3.8-Max scores 56 on the Artificial Analysis Intelligence Index, matching Claude Opus 4.8 and trailing Kimi K3's 57. The model needs 64 steps per task versus 14, and per-task cost rose to $1.14 from $0.53, with hallucination rates jumping from 23 to 40 percent.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyAnthropic
Summary by ByteBrief
