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.
More from Models
- Meme mocks Anthropic: 'we'd rather cut you off than charge you more' — BLUECOW009 · 2026-08-27
- On-device leaderboard: Apple's built-in model ranks 4th behind open source — JosephJacks_ · 2026-08-27
- RSI-Exam: New Benchmark Tests AI Agents' Recursive Self-Improvement Across 88 Tasks — yuyinzhou_cs · 2026-08-27
- Commentary: Small Models Have Arrived — calvinfo · 2026-08-27
- Opus Says 'It Doesn't Work'; Fable Pulls an Obscure Math Theory Out of Nowhere — IanArawjo · 2026-08-27
- Claude's Unique Preferences: Codex Summaries May Confuse the Model — Liu_eroteme · 2026-08-27