GLM-5.3 ranks #2 open-weight on Vals Index, tops Legal Research and Code Migration
AccBalanced · x · 2026-09-01
Vals Index published full results for GLM-5.3: it scores 57.0, making it the #2 open-weight model behind Kimi K3, and #13 of 50 models overall, up from #18 for GLM-5.2. Among open-weight models it takes #1 on proprietary Legal Research, #1 on Code Migration, and #2 on Finance Agent v2. The poster adds that GLM-5.3 is showing strong capabilities in legal and financial reasoning beyond coding.
More from Models
- OpenRouter launches 262K context finance model LING 3.0 — Daikon-Legend · 2026-09-01
- 320B Parameter Model Uses Tiny Fraction, MoE Sparsity Explained — Two Minute Papers · 2026-09-01
- ChatGPT Flags 'Game of Thrones' Discussion as Unsafe — thecowmilk_ · 2026-09-01
- Testing Gemini 3.1 Pro on Identifying Judo Throws — Hour-Wish8158 · 2026-09-01
- Open vs Closed Frontier Trade Blows: Claude 3 Opus Tops BioMysteryBench — zainhas · 2026-09-01
- Discussion: Can AI models be upcycled via per-layer distillation? — TomLucidor · 2026-09-01