AI Model Release Tracker - Timeline of Major AI Models from 2022-2026

Kimi K3 vs GLM-4.7

Moonshot AI
Kimi K3
Z.ai
GLM-4.7
Overview
CompanyMoonshot AIZ.ai
Release dateJul 16 2026Dec 22 2025
AccessOpen WeightOpen Weight
Specifications
Parameters
2.8T
Context window
1M
128k
Benchmarks
Coding
SWE-Bench Verified
73.8%
Agentic coding
DeepSWE 1.0
67.5%
Agentic terminal coding
Terminal-Bench 2.1
88.3%
Agentic terminal coding
Terminal-Bench 2.0
41%
Multi-step tool use
MCP Atlas
84.2%
Professional tool use
JobBench
52.9%
Personal tool use
Toolathlon-Verified
73.2%
Web browsing
BrowseComp
91.2%Best
52%
Multidisciplinary reasoning
Humanity's Last Exam · no tools
43.5%Best
24.8%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
56%Best
42.8%
Science
GPQA Diamond
93.5%Best
85.7%
Knowledge work
GDPval-AA v2
1668
Chart reasoning
CharXiv Reasoning
84.8%
Multimodal reasoning
MMMU-Pro
81.6%
Community preference (code)
Arena Elo (Code)
1440
Timeline
Release gapGLM-4.7 shipped 206 days before Kimi K3

Which is better: Kimi K3 or GLM-4.7?

Kimi K3 leads GLM-4.7 on 4 of the 4 benchmarks they both report (BrowseComp, Humanity's Last Exam, GPQA Diamond). GLM-4.7 shipped 206 days before Kimi K3, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Kimi K3) vs 128k (GLM-4.7).

On BrowseComp, Kimi K3 leads at 91.2% vs GLM-4.7 at 52%. On Humanity's Last Exam · no tools, Kimi K3 leads at 43.5% vs GLM-4.7 at 24.8%. On Humanity's Last Exam · with tools, Kimi K3 leads at 56% vs GLM-4.7 at 42.8%. On GPQA Diamond, Kimi K3 leads at 93.5% vs GLM-4.7 at 85.7%.

Frequently asked questions

Kimi K3 was released by Moonshot AI on Jul 16 2026.

GLM-4.7 was released by Z.ai on Dec 22 2025.

Kimi K3 leads on Humanity's Last Exam · no tools — Kimi K3 43.5% vs GLM-4.7 24.8%.

Kimi K3 has a 1M context window; GLM-4.7 has 128k.

Other comparisons