Claude Mythos 5vsDeepSeek-V4.1-Flash

Claude Mythos 5
DeepSeek-V4.1-Flash
Specifications
Context window
1M
Benchmarks
Humanity's Last Exam · with tools
64.5%63.9%
Benchmarks
SWE-Bench Verified
95.5%
DeepSWE 1.1
74.2%
NL2Repo-Bench
65.4%
Terminal-Bench 4.0
31.2%
Terminal-Bench 3.0
30%
Terminal-Bench 2.1
90.6%
Terminal-Bench 2.0
88%
BrowseComp
88%
CyberGym
88.1%
Humanity's Last Exam · no tools
36.8%
GPQA Diamond
90.9%
OSWorld-Verified
85%
Agent's Last Exam · pass@1
31.8%
AutomationBench
54.8%
Chartography · with tools
78.9%
Overview
CompanyAnthropicDeepSeek
Release dateJun 9 2026Sep 10 2026
AccessProprietaryProprietary

Other comparisons

Claude Mythos 5vsGPT-6 AstraDeepSeek-V4.1-FlashvsGPT-6 AstraClaude Mythos 5vsGemini 3.8 FlashDeepSeek-V4.1-FlashvsGemini 3.8 FlashClaude Mythos 5vsMuse Spark 1.3DeepSeek-V4.1-FlashvsMuse Spark 1.3Claude Mythos 5vsGrok 4.6DeepSeek-V4.1-FlashvsGrok 4.6Claude Mythos 5vsMistral Medium 3.5DeepSeek-V4.1-FlashvsMistral Medium 3.5Claude Mythos 5vsKimi K3DeepSeek-V4.1-FlashvsKimi K3

Frequently asked questions

Claude Mythos 5 leads DeepSeek-V4.1-Flash on 1 of the 1 benchmark they both report (Humanity's Last Exam). Claude Mythos 5 shipped 93 days before DeepSeek-V4.1-Flash, 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 DeepSeek-V4.1-Flash at 63.9%.