The Model Index
Models/Anthropic

Claude Mythos Preview

AnthropicClosed weightsFlagship

Claude Mythos Preview is a closed AI model from Anthropic, released 7 Apr 2026, with no index score yet.

–Index scoreNo third-party results yet
–Price per million tokensno public API price found
–Context windowtokens it reads at once
7 Apr 2026ReleasedReplaced by Claude Mythos 5

Where it sitson the frontier

801001201401601802002023202420252026GPT-4 at launch = 100

Not plotted: no third-party score yet.

Test resultsby area · tick = best by any model

Reasoning & knowledgeno evidence yet
GPQA Diamond (Epoch AI)
no result
Humanity's Last Exam
no result
Mathsno evidence yet
FrontierMath (tiers 1-3)
no result
Codingno evidence yet
SWE-bench Verified
no result
Terminal-Bench 4.0
no result
Agentsno evidence yet
APEX-Agents
no result
Professional workno evidence yet
Finance Agent (v2)
no result
Novel problemsno evidence yet
ARC-AGI-2
no result
Long tasksevidence
METR time horizon
51 sec

Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.

What others sayrank on each leaderboard

Not on any of the rankings we follow yet.

Best attop three among current models

Where to use itprices checked 18 Nov 2026

Host prices from OpenRouter; going direct can differ.

Facts and sources

Released7 Apr 2026
Announcementanthropic.com ↗
Release entryClaude Mythos Preview (restricted; Project Glasswing)
Scored asClaude Mythos Preview
Output speed–
Hugging Faceclosed weights

Anthropic releasesaround this one

This page as a chartDownload PNG