Report
DeepSeek-V4.1-Flash-20261017 (Max) ranks No. 1 among open models in Agent Arena and Code Arena: WebDev
Arena places the model 11th overall in Agent Arena, with a 5.1% net improvement across 7,500-plus real-world sessions.
TLDR
Arena says DeepSeek-V4.1-Flash-20261017 (Max) ranks first among open models in Agent Arena and Code Arena: WebDev. It places the model 11th overall in Agent Arena, with a 5.1% net improvement across 7,500-plus real-world sessions, and 12th overall in Code Arena: WebDev with 1,670 points. Arena says it surpassed Kimi K3 (Max) in WebDev at 10 times lower cost.
Combined views
22.8K
2 Sources, first seen ago
