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

Kimi K3 vs GLM-5

Moonshot AI
Kimi K3
Z.ai
GLM-5
Overview
CompanyMoonshot AIZ.ai
Release dateJul 16 2026Feb 12 2026
AccessOpen WeightOpen Weight
Specifications
Parameters
2.8T
744B
Context window
1M
Benchmarks
Nonsense detection
BullshitBench v2
28%
Coding
SWE-Bench Verified
77.8%
Multilingual coding
SWE-Bench Multilingual
73.3%
Agentic coding
DeepSWE 1.0
67.5%
Agentic terminal coding
Terminal-Bench 2.1
88.3%
Agentic terminal coding
Terminal-Bench 2.0
56.2%
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
75.9%
Multidisciplinary reasoning
Humanity's Last Exam · no tools
43.5%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
56%Best
50.4%
Science
GPQA Diamond
93.5%Best
86%
Knowledge work
GDPval-AA v2
1668
Chart reasoning
CharXiv Reasoning
84.8%
Multimodal reasoning
MMMU-Pro
81.6%
Community preference (code)
Arena Elo (Code)
1430
Timeline
Release gapGLM-5 shipped 154 days before Kimi K3

Which is better: Kimi K3 or GLM-5?

Kimi K3 leads GLM-5 on 3 of the 3 benchmarks they both report (BrowseComp, Humanity's Last Exam, GPQA Diamond). GLM-5 shipped 154 days before Kimi K3, so benchmark comparisons should account for the intervening progress.

Kimi K3 has 2.8T parameters, while GLM-5 has 744B.

On BrowseComp, Kimi K3 leads at 91.2% vs GLM-5 at 75.9%. On Humanity's Last Exam · with tools, Kimi K3 leads at 56% vs GLM-5 at 50.4%. On GPQA Diamond, Kimi K3 leads at 93.5% vs GLM-5 at 86%.

Frequently asked questions

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

GLM-5 was released by Z.ai on Feb 12 2026.

Kimi K3 leads on Humanity's Last Exam · with tools — Kimi K3 56% vs GLM-5 50.4%.

Other comparisons