AI Leaderboard · Proprietary

Claude Mythos Preview benchmarks, pricing, and ranking.

Open live leaderboardOpen in app
Rank #9AskClash overall score: 59.8
$25.0 / $125Input and output token price, when published. Context: 1M.
API/OAuthBilling and access path cached for this model row.

Claude Mythos Preview benchmark snapshot

AskClash combines public benchmark cells into a weighted percentile score and penalizes missing coverage so narrow rows do not dominate better-measured models.

Overall59.8
Benchmark cells6
Context1M
CreatorAnthropic

Public benchmark scores

Only benchmark columns with cached public values are shown here. Missing cells remain blank in the live table.

HLE

64.7 score

GPQA

94.5 score

SWE-bench

93.9 score

OSWorld

79.6 score

CharXiv

93.2 score

MMMU-Pro

92.7 score

Related model comparisons

Use these links to compare nearby frontier and open-weight models from the same AI leaderboard data.

GPT-5.5GPT-5.5 xHighClaude Opus 4.7 (Adaptive)GPT-5.4Gemini 3.5 FlashClaude Opus 4.7Qwen3.7 MaxClaude Opus 4.6

Related AI and tech coverage

Cached AskClash article matches that can provide release, provider, or market context around this model.

Behind the Scenes Hardening Firefox with Claude Mythos Preview

Behind the Scenes Hardening Firefox with Claude Mythos Preview Simon Willison’s Weblog Subscribe Sponsored by: MongoDB — Join MongoDB.local London 2026 on 7 May to learn how teams move AI from prototype to production. 7th May 2026 - Link Blog Behind the Scenes Hardening Firefox with Claude Mythos Preview ( via ) Fascinating, in-depth details on how Mozilla used their access to the Claude Mythos preview to locate and then fix hundreds of vulnerabilities in Firefox: Suddenly, the bugs are very goo

Anthropic's Project Glasswing - restricting Claude Mythos to security researchers - sounds necessary to me

Anthropic’s Project Glasswing—restricting Claude Mythos to security researchers—sounds necessary to me Simon Willison’s Weblog Subscribe Sponsored by: WorkOS — Production-ready APIs for auth and access control, so you can ship faster. Anthropic’s Project Glasswing—restricting Claude Mythos to security researchers—sounds necessary to me 7th April 2026 Anthropic didn’t release their latest model, Claude Mythos ( system card PDF ), today. They have instead made it available to a very restricted set

Anthropic to let partners share Mythos cybersecurity findings with others

Mythos, announced on April 7, is being deployed as part of Anthropic's "Project Glasswing," a controlled initiative under which select organizations, including major tech ⁠firms such as Amazon , Microsoft , Nvidia and Apple , are permitted to use ​the unreleased Claude Mythos Preview model for defensive cybersecurity purposes. The Pentagon is deploying Mythos to find and patch software vulnerabilities across the U.S. government even as it races to complete a transition away from the AI company,

Last cached leaderboard date: May 22, 2026. This model page is generated from the AskClash AI Leaderboard cache and linked from the live leaderboard.