Z.ai
GLM-5.1
Zhipu's open flagship — a SWE-bench official-leaderboard regular.
Open weightstextREL 2026-04-07
Compare this model →Verified 2026-06-12
Overview
GLM-5.1 is Z.ai's (Zhipu) open-weights flagship. The GLM-5 family posts 72.8% on the official SWE-bench leaderboard, making it a credible open coding model. 202K context at $0.98/$3.08 per 1M tokens.
Benchmark scores
Methodology →Intelligence51
Coding72.8
Reasoningn/a
Mathn/a
Sources and verification
- Intelligence: Artificial Analysis Intelligence Index · checked 2026-06-12
- Catalogue and pricing: OpenRouter model record · checked 2026-06-12
Strengths and weaknesses
Strengths
- Official SWE-bench leaderboard presence
- Open weights
- Strong Chinese + English
Trade-offs
- Text-only
- Smaller context than rivals
Reach for this model when
Open-weights coding and bilingual (EN/ZH) workloads.
Run something like it locally
Self-hostable via vLLM; quantised builds run on 48GB+ setups.
