DataLearner logo
CL

Claude Mythos Preview

Chat modelMythosClaude Mythos

Claude Mythos Preview

Release date: 2026-04-07Updated: 2026-06-15 07:18:23.1394,701
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
No data
Chinese support
Supported
Reasoning ability

Claude Mythos Preview（内部代号 Capybara）是 Anthropic 的超旗舰模型，在 DataLearner 收录的评测中几乎全部排名第一：GPQA Diamond 94.60、SWE-bench Verified 93.90、HLE 56.80、SWE-bench Pro 77.80。模型参数未披露，暂无公开 API 定价，目前仅通过 Project Glasswing 向约 40 家机构开放，不面向普通用户。

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Claude Mythos Preview

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking Mode (Default)Standard Mode
Context length
No data
Max output length
8K tokens
Model type
Chat model
Modality (in / out)
Text, Image → Text
Release date
2026-04-07
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
No data
Claude Mythos Preview

Open source & experience

Code license
不开源
Weights license
不开源
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Live demo
No live demo
Claude Mythos Preview

Official resources

Claude Mythos Preview

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Learn about pricing modes
Standard
TypeConditionInputOutput
Text-$25.00/ 1M$125.00/ 1M
Claude Mythos Preview

Benchmark Results

Claude Mythos Preview currently shows benchmark results led by GPQA Diamond (1 / 180, score 94.60), HLE (1 / 163, score 64.70), SWE-bench Verified (3 / 109, score 93.90). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
Tool usage

General Knowledge

3 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Extended
94.60
1 / 180
HLE
Extended
56.80
8 / 163
HLE
ExtendedTools
64.70
1 / 163

Coding and Software Engineer

3 evaluations
Benchmark / mode
Score
Rank/total
SWE-bench Verified
ExtendedTools
93.90
3 / 109
SWE-bench Multilingual
ExtendedTools
87.30
1 / 21
SWE-Bench Pro - Public
ExtendedTools
77.80
2 / 45

AI Agent - Information Search

1 evaluations
Benchmark / mode
Score
Rank/total
BrowseComp
ExtendedTools
84.90
4 / 47

AI Agent - Tool Usage

2 evaluations
Benchmark / mode
Score
Rank/total
Terminal Bench 2.0
ExtendedTools
82
2 / 46
OSWorld-Verified
ExtendedTools
79.60
4 / 19
View benchmark analysisCompare with other models

Compare with other models

Claude Mythos Preview

Publisher

Claude Mythos Preview

Model Overview

Claude Mythos Preview（内部代号 Capybara）是 Anthropic 的超旗舰模型，在 DataLearner 收录的评测中几乎全部排名第一：GPQA Diamond 94.60、SWE-bench Verified 93.90、HLE 56.80、SWE-bench Pro 77.80。模型参数未披露，暂无公开 API 定价，目前仅通过 Project Glasswing 向约 40 家机构开放，不面向普通用户。

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code