GLM-5.3-Flash Hits #5 in Code Arena, #2 Among Open Models
Zai_org · x · 2026-08-26
Zaiorg's GLM-5.3-Flash has landed around #5 in the Code Arena for WebDev tasks, ranking #2 among open models with an AutoEval score of 1634.
- Cost Efficiency: Priced at $0.15/$0.5 per million tokens, it reshapes the Pareto frontier for performance and cost.
- Model Specs: The model features 320B parameters with 18B active, compared to the GLM-5.3-Max variant's 753B parameters with 40B active, which currently ranks #8.
- Methodology Note: The score is an early AutoEval result where a Reward Model votes automatically based on Arena's human preference data. Scores may converge as more live human votes are collected.
Related event: GLM-5.3-Flash Ranks Top-5 in Code Arena, Second Among Open Models(2 posts)→
More from Models
- Google says teams across the company are using Gemini 4 Argon on its hardest engineering problems — CurieuxExplorer · 2026-10-15
- Perplexity's new embedding models: index with a 9B model, search with 0.6B — antoine_chaffin · 2026-10-15
- 797GB of n-gram counts in CPU RAM let 1B models match 57% more compute — PangWeiKoh · 2026-10-15
- Leak: Moonshot's Kimi flagship 'x4' done with pre-training, K3.1 in internal testing — lyraxana · 2026-10-15
- Unsloth ships GGUF quants for Nemotron 3.5: Bolt-74B runs in 24GB RAM — danielhanchen · 2026-10-15
- NVIDIA ships two open Nemotron 3.5 Bolt models: a 74B-A9B MoE and a mobile-friendly E4B — HankYeomans · 2026-10-15