Claude Fable 5.2

Anthropic·6 个数据来源·更新于 2026-11-10

上下文窗口1M厂商官网
最大输出128K厂商官网
输入 / 百万 Token$8厂商官网
输出 / 百万 Token$40厂商官网

评测表现

只在同一来源、同一口径下比较。切换来源可查看不同测试结果。

5 个评测来源

当前配置:各基准设置见下表

采集于 2026-11-10查看原始页面

综合分数和同榜图表来自 LLM Stats 榜单(采集于 2026-11-10);下方逐项成绩来自模型页。榜单出处

LLM Stats · LLM Stats Score
61.3原榜第 1 名

同榜模型表现

LLM Stats Score · 同一来源与榜单口径,分数越高越好

7 个配置
所选配置其他配置
查看完整对比数据
模型与配置LLM Stats Score每任务成本
Claude Fable 5.2 · 当前模型61.3未公布
Claude Mythos 5.259.6未公布
Claude Opus 5.558.9未公布
Gemini 4 Carbon57.5未公布
Claude Sonnet 5.557.2未公布
GPT-6 Astra56.8未公布
Kimi K3.1 Pro55.1未公布

不同来源的分数不能直接相加或横向比较;评测任务成本不是 API Token 单价。

逐项基准成绩

29 项已收录成绩 · 保留原始单位和测试条件

AA-Briefcase v1.1厂商自报 · 越高越好
1,785分

Announcement + System Card §8.14.4. AA-Briefcase v1.1 Elo at max effort (max_score 3000). Rubric pass rate 66.1% not stored.

成绩出处
ARC-AGI-3厂商自报 · 越高越好
79.26%

System Card §8.15. Verified by the ARC Prize Foundation; Standard harness at high effort (max effort 65.66%). Provider Adapter harness scored 97.72% at high effort.

成绩出处
AutomationBench厂商自报 · 越高越好
51.4%

Fable 5.2 with production safeguards enabled. Announcement + System Card §8.14.5. Zapier private held-out set (AutomationBench 1.0.6, 657 tasks) at max effort with the API's default fallbacks.

成绩出处
Chartography厂商自报 · 越高越好
91.6%

System Card §8.13.1. With tools (container and image cropping tool) at max effort; 5-run average.

成绩出处
Chartography (no tools)厂商自报 · 越高越好
73.4%

Announcement + System Card §8.13.1. Without tools at max effort; 5-run average; Gemini 3.5 Flash grader as on the Surge AI leaderboard.

成绩出处
CursorBench 4.0厂商自报 · 越高越好
60%

System Card §8.8. CursorBench 4.0 at max effort, measured independently by Cursor in its production harness (xhigh 56.3%, high 56.9%). Cursor attributes part of the score to prompt and harness improvements, so it may not be directly comparable with earlier Claude 5.5 system cards.

成绩出处
DeepSWE 1.1厂商自报 · 越高越好
74.3%

System Card §8.3. DeepSWE v1.1 (113 tasks); 5-trial average.

成绩出处
FrontierCode 2.0厂商自报 · 越高越好
49.1%

Fable 5.2 with production safeguards enabled. Announcement + System Card Table 8.1.A / §8.4. Best across effort levels (xhigh); mean@5 run by Cognition. Max effort 45.7%, high 45.3%. Not comparable with FrontierCode 1.1.

成绩出处
FrontierSWE V2厂商自报 · 越高越好
69.9%

Fable 5.2 with production safeguards enabled. Announcement + System Card §8.7. Proximal harness; max effort; mean across five trials per task.

成绩出处
GDPval-AA 2.1厂商自报 · 越高越好
1,831分

System Card Table 8.1.A / §8.14.3. GDPval-AA v2.1 Elo at max effort (max_score 3000); xhigh scored 1751.

成绩出处
Global-MMLU厂商自报 · 越高越好
96%

System Card §8.17.1. Average accuracy across 42 languages; max effort; single trial; no tools; blocked or unanswered questions (0.5%) excluded.

成绩出处
HealthBench厂商自报 · 越高越好
59.6%

System Card §8.16.1. Length-adjusted score at max effort, run independently at Anthropic's request with GPT-4.1 grading and fallbacks on. Not comparable with earlier Claude system cards graded by Claude Opus 4.8.

成绩出处
HealthBench Professional厂商自报 · 越高越好
67.7%

System Card §8.16.2. Length-adjusted score at max effort; GPT-5.4 grader at low effort; fallbacks on. Not comparable with earlier Claude system cards.

成绩出处
HealthBench Professional (raw)厂商自报 · 越高越好
71.1%

System Card §8.16.2. Raw score before length adjustment at max effort.

成绩出处
HealthBench (raw)厂商自报 · 越高越好
58.8%

System Card §8.16.1. Raw score before length adjustment at max effort; same third-party run and grader as the length-adjusted score.

成绩出处
Humanity's Last Exam厂商自报 · 越高越好
73.2%

System Card Table 8.1.A / §8.11.1. Full 2,500-question HLE, reasoning only (no tools); 980k-token task budget, no compaction.

成绩出处
Humanity's Last Exam (with tools)厂商自报 · 越高越好
74.2%

Fable 5.2 with production safeguards enabled. Announcement + System Card Table 8.1.A / §8.11.1. Web search, web fetch, programmatic tool calling and code execution; HLE sources blocklisted; 980k-token task budget.

成绩出处
MILU厂商自报 · 越高越好
94.1%

System Card §8.17.2. Average accuracy across 11 languages; max effort; averaged over five trials; no tools.

成绩出处
OfficeQA厂商自报 · 越高越好
83.4%

System Card §8.14.1. OfficeQA full set; max effort; mean of five runs; agentic harness with extracted-text documents.

成绩出处
OfficeQA Pro厂商自报 · 越高越好
72.9%

System Card §8.14.1. OfficeQA Pro (133-question subset); max effort; mean of five runs.

成绩出处
OSWorld 2.1 (partial)厂商自报 · 越高越好
89.3%

Fable 5.2 with production safeguards enabled. Announcement + System Card §8.13.3. Official offline set (82 of 108 tasks); partial score, Pass@1 averaged over five attempts at max effort.

成绩出处
OSWorld 2.1 (strict)厂商自报 · 越高越好
54.6%

System Card §8.13.3. Official offline set (82 of 108 tasks); strict pass rate, Pass@1 averaged over five attempts at max effort.

成绩出处
PhysicianBench厂商自报 · 越高越好
64.4%

System Card §8.16.3. 100 EHR tasks, five attempts each, max effort; graded with Claude Opus 5.

成绩出处
Program Bench厂商自报 · 越高越好
85.6%

System Card §8.10.1. 166 golden tasks; mini-swe-agent harness; no 6-hour limit. 91.6% when the harness also shows remaining context tokens.

成绩出处
SWE-bench Multilingual厂商自报 · 越高越好
96.6%

System Card Table 8.1.A / §8.2. Adaptive thinking at max effort; 5-trial average. 300 problems across nine programming languages.

成绩出处
SWE-Bench Multimodal厂商自报 · 越高越好
74.1%

System Card Table 8.1.A / §8.2. Adaptive thinking at max effort; 5-trial average.

成绩出处
SWE-Bench Pro厂商自报 · 越高越好
93%

System Card Table 8.1.A / §8.2. Adaptive thinking at max effort; 5-trial average.

成绩出处
Terminal-Bench 4.0厂商自报 · 越高越好
67.6%

Fable 5.2 with production safeguards enabled. System Card §8.5. Claude Code --bare at max effort, no internet access (cached resources and offline search); 10 trials per task, SE ±1.8 pts. Safeguard fallbacks on 2.5% of requests. Mythos 5.2 without safeguards scored 70.5%.

成绩出处
Terminal-Bench-Science 0.1厂商自报 · 越高越好
74.6%

Fable 5.2 with production safeguards enabled. Announcement + System Card §8.6. Claude Code --bare at max effort, no internet access; 10 trials per task, SE ±4.3 pts. Mythos 5.2 without safeguards scored 75.3%.

成绩出处

技术规格

只展示有可靠来源的资料;优先采用厂商官网与官方模型仓库。

发布日期
2026-11-09厂商官网
知识截止
2026-06厂商官网
上下文窗口
1M Token厂商官网
最大输入
1M TokenLLM Stats
最大输出
128K Token厂商官网
输入模态
文本、图像厂商官网
输出模态
文本厂商官网
开放权重
否Artificial Analysis
推理模式
支持厂商官网
许可证
ProprietaryLLM Stats

价格与用量

美元 / 百万 Token。不同服务商或测试配置的报价分别列出。

模型 API 价格,单位为美元每百万 Token
来源 / 服务商输入输出缓存读取
厂商官网 · Claude Fable 5.2$8$40$0.2
Anthropic$8$40$0.2

估算一次用量

按表格第一条报价计算,普通文本、无缓存。

预计费用$12
不含工具、图片、推理额外计费或阶梯价格;以服务商实际账单为准。

每个数字,都有出处

同名模型通过开发机构和明确版本关联。预览版、日期版本和不同规模模型分别建档。

厂商官网

厂商官方文档 · 基础规格与标准 API 报价

1 条记录最近采集 2026-11-10

Artificial Analysis

公开评测数据;保留来源原始口径

10 条记录最近采集 2026-11-10

LLM Stats

公开模型页与公开榜单;自报成绩单独标识

2 条记录最近采集 2026-11-10

BenchLM

公开评测数据;保留来源原始口径

1 条记录最近采集 2026-11-10

LiveBench

公开评测数据;保留来源原始口径

1 条记录最近采集 2026-11-10

OpenRouter

公开模型目录与 API 报价

1 条记录最近采集 2026-11-10
查看全部配置与采集记录
来源 / 配置采集时间原始数据
Artificial AnalysisClaude Fable 5.2 (max)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisClaude Fable 5.2 (xhigh)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisClaude Fable 5.2 (high)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisClaude Fable 5.2 (medium)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisClaude Fable 5.2 (low)SHA-256 c969b09538b1254d…2026-11-10T14:08:35Z查看来源
Artificial AnalysisClaude Fable 5.2 (Max, Default Fallback)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
Artificial AnalysisClaude Fable 5.2 (High, Default Fallback)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
Artificial AnalysisClaude Fable 5.2 (Low, Default Fallback)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
Artificial AnalysisClaude Fable 5.2 (Medium, Default Fallback)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
Artificial AnalysisClaude Fable 5.2 (Xhigh, Default Fallback)SHA-256 d88cf30c17a50945…2026-11-10T13:51:48Z查看来源
LLM StatsClaude Fable 5.22026-11-10T14:08:28Z查看来源
LLM StatsClaude Fable 5.2SHA-256 512d6713bffd6877…2026-11-10T13:51:52Z查看来源
BenchLMClaude Fable 5.22026-11-10查看来源
LiveBenchClaude Fable 5.2 (xhigh)2026-11-10T14:08:34Z查看来源
OpenRouterClaude Fable 5.2SHA-256 63cbc45064d84060…2026-11-10T13:51:49Z查看来源
厂商官网Claude Fable 5.2SHA-256 0ce469f8bf697337…2026-11-10T13:59:35Z查看来源
继续浏览模型排行榜