GLM-5.3-Flash Review: 10% Cost, Pareto Frontier Performance
ArtificialAnlys · x · 2026-08-27
Zai released GLM-5.3-Flash, a 320B total / 18B active MoE model under the MIT license. Benchmarks: Scores 57 on the Artificial Analysis Intelligence Index, only 3 points behind GLM-5.3 and tying GPT-5.6 Terra; matches GLM-5.3 on real-world agentic tasks like GDPval-AA v2 and Terminal-Bench v2.1. Cost: Cost per Task is $0.09 (1/7.5th of GLM-5.3's $0.68). API pricing is $0.15/1M input and $0.50/1M output tokens, with 80% discount on cached inputs. Features: Supports low/high/max reasoning efforts, 400k context window, and improved hallucination rate (28% vs 30%).
Related event: Zhipu Open-Sources GLM-5.3-Flash: 320B MoE Multimodal at 1/10th the Cost(48 posts)→
More from Models
- GLM-5.3 unprompted reasons about how its actions affect its future training, worries Apollo — MariusHobbhahn · 2026-10-15
- Gemini 4 argon vs Opus 5.5 hands-on: 3 min for $3 vs 25 min for $8 — zacharynado · 2026-10-15
- SentinelOne says OpenAI did 4-6 weeks of reverse-engineering in 8 hours — OpenAI · 2026-10-15
- Qwen3.8 27B scores 23.57% on word-based addition without reasoning, 167/169 with it — dl_weekly · 2026-10-15
- Hacker turns EmbeddingGemma 2 into 288x realtime STT and a fast TTS — kastnerkyle · 2026-10-15
- Claude Fable 5.5 reportedly in partners' hands, release eyed next week — lyraxana · 2026-10-15