Back to models

GLM-4.7

ECI#87
143
Z.ai (Zhipu AI)
Dec. 22, 2025
Open weights

GLM-4.7 is an open-weights model from Z.ai (Zhipu AI), released December 22, 2025. It has an ECI score of 143 and ranks 87th of 249 tracked models. At the time of its release, it ranked 23rd of 178 tracked models.

GLM-4.7 vs select alternatives

DomainBenchmark
GLM-4.7
Z.ai (Zhipu AI)
Dec. 22, 2025
Open weights
GLM-4.6
Z.ai (Zhipu AI)
Sep. 30, 2025
Open weights
Kimi K2 Thinking
Moonshot
Nov. 6, 2025
Open weights
DeepSeek-V3.2
DeepSeek
Dec. 1, 2025
Open weights
ECI scoreBest score 166
143141146146
Ranking#87#104#73#68
Agent
APEX-AgentsBest score 47%
9%
4%
4%
7%
Games
Chess PuzzlesBest score 72%
6%
n/a
20%
14%
Mathematics
OTIS Mock AIME 2024-2025Best score 100%
83%
n/a
83%
88%
Science
CritPtBest score 32%
2%
1%
n/a
n/a
SciCodeBest score 62%
45%
38%
n/a
n/a
GPQA DiamondBest score 96%
83%
n/a
84%
83%
Software engineering
Text Arena (Coding)Best score 1797
1434134013371325
ALE-BenchBest score 2177
399341598—
Terminal-Bench 2.0Best score 85%
33%
25%
36%
40%

Model metadata

General
OrganizationZ.ai (Zhipu AI)
Release dateDec. 22, 2025
Model accessibilityOpen weights
CountryChina
Knowledge cutoffUnknown
Provider notesz.ai
Pricing
Input price$0.45 / 1M tokens
Output price$2 / 1M tokens
Training
Parameters3.6e11
Training compute4.4e24 FLOP
Training hardwareUnknown
Training timeUnknown
Training dataset sizeUnknown