WhichAI / Models / GLM-5.3

GLM-5.3

· verified September 8, 2026

public api in Generator coding reasoning agents

Provider

Statuspublic

AA Intelligence Index59.5 (September 8, 2026 snapshot)

Released2026-08-14

Context windown/a

Modalitiesn/a

API price $/1M (in / out)n/a

Speedn/a

AccessReleased August 14, 2026 · staged access · open weights NOT released at launch (unlike every previous GLM) · API price not published

In one line

Z.ai's 743B flagship: AA 59.5, the highest a Chinese lab has scored, with 84.5% on CyberGym and 54.4% on ExploitBench. The break with tradition matters more than the score: weights are held back behind a staged safety review, so for now GLM-5.3 is not the open model its version number suggests. The Flash sibling is.

Coding91

Reasoning88

Writing72

Agents & tools88

Category scores (0-100) are WhichAI blended ratings: public category leaderboards plus editorial judgment. Guidance, not official measurements.

Alternatives worth a look

Kimi K3 (Moonshot AI) · AA 59.7API $3/$15 per 1M tokens ($0.30 cached) · free kimi.com chat · open weights on Hugging Face (July 27, Modified MIT)
GPT-5.6 Sol (OpenAI) · AA 58.9Released July 9, 2026 (rolling out) · API $5/$30 per 1M tokens · up to 750 tok/s on Cerebras
Gemini 3.8 Flash (Google) · AA 58.7Released September 2, 2026 · API $0.75/$3.75 per 1M tokens ($0.075 cached) · free-tier availability not confirmed

Open GLM-5.3's official app ↗ Open in the WhichAI app Not sure? Take the 30-second finder

Artificial Analysis Intelligence Index, 2026 rebased scale (top models ~ 55-66). Snapshot: September 4, 2026 (BenchLM mirror), retrieved September 8, 2026. Specs and prices come from the OpenRouter public model list on the same date. Models nobody has measured carry no index score at all and never enter a ranking: where an estimate exists it is shown separately and labelled unmeasured. Context, price, modality and release dates come from the public OpenRouter model list (retrieved September 8, 2026) and vendor pages. Missing values are not published or not yet verified - shown as -. Sources are linked inside the app (Model guide and About > Methodology).