Claude Fable 5.1
开始使用
API 接入
Aixy API文档
目录部署标识：anthropic/claude-fable-5-1。具体区域、权限与价格以服务商为准。
Merge Gateway API文档
目录部署标识：anthropic/claude-fable-5-1。具体区域、权限与价格以服务商为准。
Tempr Gateway API文档
目录部署标识：anthropic/claude-fable-5-1。具体区域、权限与价格以服务商为准。
NEAR AI Cloud API文档
目录部署标识：anthropic/claude-fable-5-1。具体区域、权限与价格以服务商为准。
Eden AI API文档
目录部署标识：anthropic/claude-fable-5-1。具体区域、权限与价格以服务商为准。
LLM Gateway API文档
目录部署标识：anthropic/claude-fable-5-1。具体区域、权限与价格以服务商为准。
CrossModel API文档
目录部署标识：anthropic/claude-fable-5-1。具体区域、权限与价格以服务商为准。
Perplexity Agent API文档
目录部署标识：anthropic/claude-fable-5-1。具体区域、权限与价格以服务商为准。
Anthropic API文档
目录部署标识：claude-fable-5-1。具体区域、权限与价格以服务商为准。
公开成绩与计算依据
综合参考分根据已公开的评测资料整理。查看发布日期依据
综合参考分 78.3 · 19项基准
推理求解 84.3
FrontierMath · 87.8 %
Claude Fable 5.1 · Published page gpt6-astra-official; row FrontierMath Tier 4 (v2); preserve page footnotes and task-specific settings · 2026-09-29公开
GPQA Diamond · 0.937373737373737 比例
Artificial Analysis · 独立评测 · Diamond
Claude Fable 5.1 (Max, Default Fallback) · Current AA standalone protocol. Status verified in aa-method-current.md section gpqa-diamond
Terminal-Bench-Science · 40.00%
Vals AI · 独立评测 · 0.1.0
Claude Fable 5.1 / Mini-SWE-agent · Current displayed evaluator row. Mini-SWE-agent. Scores are not pooled across harnesses; source methodology and repeat counts retained.
HLE · 51.3 %
Scale AI · 独立评测 · Diamond
claude-fable-5-1 · scale-hle-reviewed-method-20261029
Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions.
CritPt · 0.525 比例
Artificial Analysis · 独立评测 · 2 Hard
Claude Fable 5.1 (Max, Default Fallback) · Artificial Analysis current published protocol; critpt-v2-hard
工具与任务执行 86.5
tau3-Banking · 0.472164948453608 比例
Artificial Analysis · 独立评测 · 1.0.1
Claude Fable 5.1 (Max, Default Fallback) · Current AA standalone protocol. Status verified in aa-method-current.md section tau3-banking
GDPval-AA · 1763.29 分
Artificial Analysis · 独立评测 · 2.1
Claude Fable 5.1 (Max, Default Fallback) · Artificial Analysis current published protocol; gdpval-aa-normalized
Terminal-Bench · 0.52020202020202 比例
Artificial Analysis · 独立评测 · 4.0
Claude Fable 5.1 (Max, Default Fallback) · Artificial Analysis current published protocol; terminalbench-4-0
AutomationBench · 0.5937591715646424 比例
Artificial Analysis · 独立评测 · current published task suite
Claude Fable 5.1 (Max, Default Fallback) · Artificial Analysis current published protocol; automationbench-aa
AA-Briefcase · 1669.49 分
Artificial Analysis · 独立评测 · 1.1
Claude Fable 5.1 (Max, Default Fallback) · Artificial Analysis current published protocol; aa-briefcase
OSWorld · 80.7% partial
www.anthropic.com · 官方发布比较 · 2.1
Fable 5.1 · Published page official-0dd3bed5c7dd; row Computer use OSWorld 2.1; preserve page footnotes and task-specific settings · 2026-09-22公开
AA-AnalystAgent · 0.575 比例
Artificial Analysis · 独立评测 · current AA pass^5
Claude Fable 5.1 (Max, Default Fallback) · Artificial Analysis current published protocol; aa-analyst-agent
编程 54.3
FrontierCode · 0.316248737373737 比例
Artificial Analysis · 独立评测 · 2.0
Claude Fable 5.1 (Max, Default Fallback) · Artificial Analysis current published protocol; frontiercode-2-0
DeepSWE · 67.4 %
openai.com · 官方发布比较 · 1.1
Claude Fable 5.1 · Published page gpt6-astra-official; row DeepSWE v1.1; preserve page footnotes and task-specific settings · 2026-09-29公开
语言与信息处理 79.3
GDP.pdf · 0.262 比例
Artificial Analysis · 独立评测 · current published task suite
Claude Fable 5.1 (Max, Default Fallback) · Artificial Analysis current published protocol; gdp-pdf
SimpleQA Verified · 0.708 比例
Epoch AI · 独立评测 · run 1.2.0
claude-fable-5-1_max · epoch-simpleqa-reviewed-method-20261029-task-version-1.2.0 · 2026-09-01公开
AA-Omniscience · 0.684 比例
Artificial Analysis · 独立评测 · 1.1
Claude Fable 5.1 (Max, Default Fallback) · Artificial Analysis current published protocol; omniscience-accuracy
AA-Omniscience · 0.29957805907172996 比例
Artificial Analysis · 独立评测 · 1.1
Claude Fable 5.1 (Max, Default Fallback) · Artificial Analysis current published protocol; omniscience-non-hallucination
多模态理解 88.9
Humanity Sixth Sense · 40.8 %
Scale AI · 独立评测 · current published task suite
Claude-Fable-5.1 · scale-hss-reviewed-method-20261029
Chartography · 88.4% with tools
www.anthropic.com · 官方发布比较 · current published task suite
Fable 5.1 · Published page official-0dd3bed5c7dd; row Visual chart recognition Chartography; preserve page footnotes and task-specific settings · 2026-09-22公开
外部综合指数
AA Index 5.0 · 49 · 2026-10-28公开
资料来源
- 版本日期来源 · 版本资料 · 2026-10-29查阅
- openai.com · official_release_comparison · 2026-10-29查阅
- Vals AI · independent_evaluation · 2026-10-29查阅
- Scale AI · independent_evaluation · 2026-10-29查阅
- www.anthropic.com · official_release_comparison · 2026-10-29查阅
- Epoch AI · independent_evaluation · 2026-10-29查阅
- Scale AI · independent_evaluation · 2026-10-29查阅