GLM 4.5open

Z.ai

58.9#84 of 427 overall

Family history

The 8 versions of this family, from first to newest, by release date. Click a point to open that version.

See the data as a table

Model	Released	Score	Rank	AA Intel.	Elo Arena
GLM-4	—	—	—	—	1226
GLM 4.5	07/25/2025	58.9	#84	—	1430
GLM 4.6	09/30/2025	54.4	#107	—	1440
GLM 4.7	12/22/2025	59.7	#82	—	1435
GLM 5	02/11/2026	64.7	#63	—	1446
GLM 5.1	04/07/2026	68.9	#42	—	1463
GLM 5.2	06/16/2026	74.3	#29	—	1470
GLM 5.3	08/18/2026	75.3	#26	31.7	1474

Scores by sourcepercentile = % of ranked models it beats

Metric	Value	Percentile	Source
Arena text (Elo) weight 2	1430	63%	LMArena
Humanity's Last Exam weight 1	13.0	60%	Artificial Analysis
GPQA Diamond	78.2	65%	Artificial Analysis
Long-context reasoning	52.7	46%	Artificial Analysis

Category	Score	Rank	Metrics
Reasoning	58.4	#160	Humanity's Last Exam, GPQA Diamond
Research	47.8	#191	Long-context reasoning
Chat	56.4	#73	Arena text (Elo)

RankingIA score on each collection day (hover to see the rank).

Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.