Anthropic · proprietary

Claude Mythos Preview

Claude Mythos Preview by Anthropic appears in 1 source with Reasoning at 72.51. Best read for Code quality, LLM, Multimodal.

CreatorAnthropic

Release date2026-04-07

Knowledge cutoffNot published

ContextUnknown

Input priceUnknown

Output priceUnknown

Modalitytext + vision

CountryUS

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank132ranking · source_rank

Reasoning72.51reasoning · index_reasoning

Math62.31math · index_math

Coding57.83coding · index_code

Research41.59research · index_search

Vision50.73multimodal · index_vision

Tool calling40.31tool_calling · index_tool_calling

Long context37.38long_context · index_long_context

Healthcare24.25domain · index_healthcare

GPQA94.6 %reasoning · gpqa_score

SWE-bench Verified93.9 %coding · swe_bench_verified_score

Humanity Last Exam64.7 %reasoning · hle_score

MMMLU92.7 %reasoning · mmmlu_score

BrowseComp86.9 %research · browsecomp_score

SWE-bench Pro77.8 %coding · swe_bench_pro_score

CharXiv-R93.2 %multimodal · charxiv_r_score

Evidence

Citations and source overlap

LLM StatsPublic full LLM leaderboard advanced explorer snapshot, including ranking, benchmark indexes, pricing, speed, context, license, and model metadata.Retrieved 2026-06-01

FAQ

How should I read this profile?

Treat this as a source-backed model dossier, not an EvalKit-run verification. The public values are replicated from linked sources and kept source-scoped.

Is Claude Mythos Preview verified by EvalKit?

No. EvalKit currently shows 0 verified rows until real run evidence exists.

Why can metrics disagree?

Different sources test different tasks, dates, prompts, and aggregation methods. EvalKit keeps those differences visible instead of merging them into a fake universal score.