GLM-5.3-Flash hits eval arena; DeepSeek-V4-pro found unfit for AI reviewing

ChenhaoTan · x · 2026-08-27

Zhipu officially released GLM-5.3-Flash: a 320B-A18B open model under MIT license, natively multimodal with a 1M-token context window, previously previewed as Ox Alpha and running entirely on Chinese AI chips. Weights, API, coding plan and chat are now available. The sailab arena has added GLM-5.3-Flash and found that DeepSeek-V4-pro performs poorly for AI reviewing; free AI reviews are available on the arena.

Original post →

More from Models

Models channel →