Claude Mythos 5vsGLM-5.3

Claude Mythos 5
GLM-5.3
Specifications
Parameters
743B
Context window
1M
API pricing
Cheapest input
$1.40Z.AI
Cheapest output
$4.40Z.AI
Benchmarks
Humanity's Last Exam · with tools
64.5%62.5%
Benchmarks
SWE-Bench Verified
95.5%
DeepSWE 1.1
66.9%
Terminal-Bench 3.0
28.3%
Terminal-Bench 2.1
88%
BrowseComp
88%
CyberGym
84.5%
ExploitBench
54.4%
ExploitGym · 6-hour budget
130
ExploitGym · 2-hour budget
105
OSWorld-Verified
85%
Agent's Last Exam · pass@1
28.5%
AutomationBench
48.2%
GDPval-AA v2
1769
Overview
CompanyAnthropicZ.ai
Release dateJun 9 2026Aug 14 2026
AccessProprietaryProprietary

Other comparisons

Claude Mythos 5vsGPT-5.6 SolGLM-5.3vsGPT-5.6 SolClaude Mythos 5vsGemini 3.7 FlashGLM-5.3vsGemini 3.7 FlashClaude Mythos 5vsMuse GlimmerGLM-5.3vsMuse GlimmerClaude Mythos 5vsGrok 4.6GLM-5.3vsGrok 4.6Claude Mythos 5vsDeepSeek-V4-Pro-0813GLM-5.3vsDeepSeek-V4-Pro-0813Claude Mythos 5vsMistral Medium 3.5GLM-5.3vsMistral Medium 3.5

Frequently asked questions

Claude Mythos 5 leads GLM-5.3 on 1 of the 1 benchmark they both report (Humanity's Last Exam). Claude Mythos 5 shipped 66 days before GLM-5.3, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On Humanity's Last Exam · with tools, Claude Mythos 5 leads at 64.5% vs GLM-5.3 at 62.5%.

Claude Mythos 5 was released by Anthropic on Jun 9 2026.

GLM-5.3 was released by Z.ai on Aug 14 2026.

Claude Mythos 5 leads on Humanity's Last Exam · with tools — Claude Mythos 5 64.5% vs GLM-5.3 62.5%.