Current flagship is GLM 5.3, and that is the Continuum hosted id. GLM 5.2 carried the week tokens (4.34T, +18% week-over-week, not share) and the DeepSWE row; it has its own card. We do not paste a 5.2 score onto 5.3.
OpenRouter This Week LLM Leaderboard tokens (prompt plus completion) through 18 Aug 2026: 4.34T on GLM 5.2 (+18% week-over-week, not share). Fetched 2026-08-19. OpenRouter This Week tokens are prompt plus completion. The percent next to a row is week-over-week change, not share of the week. Market share on this page is text request share by author, a different number.
Current API SKU. Hosted id glm-5.3. glm-latest aliases here (18 Aug 2026). DeepSWE has 5.2 only, not 5.3.
Week-volume SKU: 4.34T (+18% WoW) and the only Z.ai DeepSWE listing. Open weights at zai-org/GLM-5.2.
GLM 5.1: 2026-08-19 OpenRouter row.
GLM 5V Turbo: 2026-08-19 OpenRouter row.
GLM 5 Turbo: 2026-08-19 OpenRouter row.
GLM 5: 2026-08-19 OpenRouter row.
GLM 4.7 Flash: 2026-08-19 OpenRouter row.
GLM 4.7: 2026-08-19 OpenRouter row.
GLM 4.6V: 2026-08-19 OpenRouter row.
GLM 4.6: 2026-08-19 OpenRouter row.
GLM 4.5V: 2026-08-19 OpenRouter row.
GLM 4.5: 2026-08-19 OpenRouter row.
Current GLM. Hosted. No 5.2 score pasted on.
Week-volume GLM. DeepSWE 44% ±2. MIT weights.
GLM 5.1: 2026-08-19 OpenRouter row.
GLM 5V Turbo: 2026-08-19 OpenRouter row.
GLM 5 Turbo: 2026-08-19 OpenRouter row.
GLM 5: 2026-08-19 OpenRouter row.
GLM 4.7 Flash: 2026-08-19 OpenRouter row.
GLM 4.7: 2026-08-19 OpenRouter row.
GLM 4.6V: 2026-08-19 OpenRouter row.
GLM 4.6: 2026-08-19 OpenRouter row.
GLM 4.5V: 2026-08-19 OpenRouter row.
GLM 4.5: 2026-08-19 OpenRouter row.
This hub lists every published card. Start with GLM 5.3.
Ranked view: Best coding models: the independent leaderboard puts every Z.ai card with an independent coding row next to every other lab on one board, with the confidence intervals left visible.
The app is free with your own keys. Plus adds Continuum-hosted inference and the ids we actually list on each card.