Claude Fable 5 vs Muse Wonder Full
完整资料:Claude Fable 5(Anthropic)和 Muse Wonder Full(Meta),包括全部基准测试、价格和排名。
更新于 · 数据来自 12 个来源
截至 2026年11月16日,质量上 Claude Fable 5 领先 Muse Wonder Full(BenchLeader Index 65.4 比 61.7)。看重推理(80 比 66)、编程(76 比 70)和知识(66 比 62)选 Claude Fable 5;看重智能体与工具(64 比 61)选 Muse Wonder Full。
要点(截至 2026年11月16日)
- Claude Fable 5 的 BenchLeader Index 为 65.4,Muse Wonder Full 为 61.7(BenchLeader,2026年11月16日)。
- Claude Fable 5 每百万 token 混合价格为 $20.00(标价,2026年11月16日)。
按用途怎么选
推荐模型的数值列在前面。类别得分采用 BenchLeader 标尺(50 为模型平均水平,15 分为一个标准差)。领先半个标准差及以上为“高”置信度;相差不到 1 分则视为“均可”。
主要差异
- 质量上 Claude Fable 5 领先:65.4 比 61.7。
- Claude Fable 5 在编程、知识、推理方面更强。
- Muse Wonder Full (max) 在智能体与工具方面更强。
概览
| 规格 | Claude Fable 5 | Muse Wonder Full |
|---|---|---|
| 提供商 | Anthropic | Meta |
| 发布日期 | 2026年6月9日 | 2026年10月12日 |
| 上下文窗口(token) | 1,000,000 | 1,000,000 |
| 对比时的配置 | Claude Fable 5 | Muse Wonder Full (max) |
| 开放权重 | 否 | 否 |
| 每百万 token 价格(输入 / 输出 / 缓存输入) | $10.00 / $50.00 / $1.00 | – |
逐类别对比
类别得分采用 BenchLeader 标尺:50 为参评模型的平均水平,15 分为一个标准差。差距不到 1 分视为持平。
| 类别 | Claude Fable 5 | Muse Wonder Full (max) | 领先者 |
|---|---|---|---|
| 推理 | 80.1 | 65.8 | Claude Fable 5 |
| 编程 | 75.5 | 69.9 | Claude Fable 5 |
| 智能体与工具 | 60.5 | 63.6 | Muse Wonder Full |
| 知识 | 66.4 | 62.3 | Claude Fable 5 |
| 人类偏好 | 67.7 | – | 无法比较 |
| 长上下文 | – | 66.6 | 无法比较 |
同一图表对比
各领域采用与 Index 相同的标尺,平均模型为 50 分。单击某个领域可查看构成它的基准测试。 可从列表中最多选择 5 个模型。
未绘制(测得的模型少于两个):数学, 指令遵循, 长上下文, 多模态, 人类偏好。
各来源的分歧
在两者都有结果的 0 项基准测试中,Claude Fable 5 领先 0 项,Muse Wonder Full 领先 0 项。所有同时评测两者的综合评分都认为 Claude Fable 5 更强。
| 综合 Index | Claude Fable 5 | Muse Wonder Full (max) | 领先者 |
|---|---|---|---|
| BenchLeader Index | 65.4 | 61.7 | Claude Fable 5 |
各发布方使用各自的任务、评测框架和推理强度设置,因此总体结论可能不同;BenchLeader 将它们统一到同一标尺上。† 表示同一模型在另一推理强度设置下的测量值(发布方未测试本页对比的设置)。
价格、速度与延迟
标价按每 1 个输出 token 对应 3 个输入 token 混合计算。每项任务的价格采用方法论页面中的 token 数量。每项基准测试任务的成本、token 数和耗时均为实测值,取自 Artificial Analysis 整个 Intelligence Index 测试的平均值。
| 指标 | Claude Fable 5 | Muse Wonder Full (max) |
|---|---|---|
| 每百万 token 混合价格 | $20.00 | – |
| 每百万 token 输入 / 输出 | $10.00 / $50.00 | – / – |
| 每百万 token 缓存输入 | $1.00 | – |
| 每项任务价格:聊天回复 | $0.019 | – |
| 每项任务价格:总结一份 30 页的报告 | $0.150 | – |
| 每项任务价格:代码编辑 | $0.135 | – |
| 每项任务价格:智能体编程会话 | $0.800 | – |
| 每项任务价格:结构化信息提取 | $0.030 | – |
| 智能体编程会话(输入大多命中缓存) | $0.395 | – |
| 每项任务输出 token(AA Index) | – | 88k |
| 其中推理部分 | – | 55k |
| 输出速度 | 50 tok/s | – |
| 首次回答时间 | 3.2 秒 | – |
每个模型都按其排名最高的推理强度设置进行对比。Claude Fable 5 得分 65.4,首个回答 token 需 3 秒;Claude Fable 5 (max) 为 65.1(95 秒),Claude Fable 5 (high) 为 63.9(3 秒)。Muse Wonder Full (max) 得分 61.7。推理强度越高,回答前思考越久:得分更高,但等待更长、计费 token 也更多。 推理强度如何影响得分和成本
全部基准测试
共 158 项基准测试,按类别分组;点击名称可查看该排行榜及领先模型。† 表示同一模型在另一推理强度设置下的测量值,仅供参考,不计入胜场。
| 指标 | 发布方 | Claude Fable 5 | Muse Wonder Full (max) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 65.4 | 61.7 |
| 智能体与工具得分 | BenchLeader | 60.5 | 63.6 |
| 编程得分 | BenchLeader | 75.5 | 69.9 |
| 人类偏好得分 | BenchLeader | 67.7 | – |
| 知识得分 | BenchLeader | 66.4 | 62.3 |
| 推理得分 | BenchLeader | 80.1 | 65.8 |
| 长上下文得分 | BenchLeader | – | 66.6 |
| 混合价格(美元/百万 token) | BenchLeader | $20.00 | – |
| 输出速度 | BenchLeader | 50 tok/s | – |
| 首次回答时间 | BenchLeader | 3.2 秒 | – |
| 上下文窗口 | BenchLeader | 1,000,000 token | 1,000,000 token |
| 推理 | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 85.9%† | – |
| SimpleBench | SimpleBench | 81.9%† | – |
| Arena Hard Prompts | Arena (LMArena) | 1530† | – |
| LiveBench 1.0 Reasoning | LiveBench | 89.7%† | – |
| GPQA Diamond (AA) | Artificial Analysis | 92.6%† | – |
| Humanity's Last Exam (AA) | Artificial Analysis | 55.5%† | 53.6% |
| HLE-Diamond (AA) | Artificial Analysis | – | 48.5% |
| GPQA Diamond (Vals) | Vals AI | 93.2%† | – |
| EnigmaEval | Scale AI SEAL | 39.3%† | – |
| Kagi LLM Benchmark | Kagi LLM Benchmark | 88.8% | – |
| ARC-AGI-1 | ARC Prize | 98.5%† | – |
| ARC-AGI-2 | ARC Prize | 89.2%† | – |
| CritPt | Artificial Analysis | 28.6%† | 32.9% |
| CritPt v2 hard subset (AA) | Artificial Analysis | – | 56.5% |
| MysteryMechanism | Vals AI | – | 35.1% |
| Arena Expert | Arena (LMArena) | 1550† | – |
| Chess Puzzles | Epoch AI Benchmarking Hub | 47.0%† | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 52.0%† | – |
| LMCA | Epoch AI Benchmarking Hub | 60.3%† | – |
| DTBench | Epoch AI Benchmarking Hub | 98.4%† | – |
| ForecastBench | ForecastBench | 65.9%† | – |
| BTF-3 | Epoch AI Benchmarking Hub | 13.0%† | – |
| 编程 | |||
| SciCode | SciCode | 61.0%† | – |
| WeirdML | WeirdML | 91.9%† | – |
| FrontierCode | Cognition | 53.5% | – |
显示全部 158 项基准测试
| 指标 | 发布方 | Claude Fable 5 | Muse Wonder Full (max) |
|---|---|---|---|
| 编程 | |||
| GSO-Bench | GSO-Bench | 78.4% | – |
| Arena Coding | Arena (LMArena) | 1552† | – |
| Arena WebDev | Arena (LMArena) | 1625† | 1724 |
| LiveBench 1.0 Coding | LiveBench | 86.0%† | – |
| SciCode (AA) | Artificial Analysis | 61.0%† | 62.6% |
| LiveCodeBench | Vals AI | 89.8%† | – |
| IOI | Vals AI | – | 79.8% |
| SWE-bench (Vals) | Vals AI | 95.0%† | – |
| Code Migration | Vals AI | 55.1%† | 61.0% |
| Code Migration v1.1 | Vals AI | – | 62.8% |
| ProgramBench | Vals AI | 2.0%† | 0.5% |
| SWE-bench Multimodal | Vals AI | – | 47.3% |
| Vibe Code Bench 1-100 | Vals AI | – | 34.0% |
| Vibe Code Bench v1.1 | Vals AI | 90.3%† | 86.0% |
| SWE Atlas v1.0: Codebase QnA | Scale AI SEAL | 39.0%† | – |
| SWE Atlas v1.0: Refactoring | Scale AI SEAL | 54.8%† | – |
| SWE Atlas v1.0: Test Writing | Scale AI SEAL | 55.6%† | – |
| MirrorCode | Epoch AI Benchmarking Hub | 70.0%† | – |
| Surface Evolver Bench | Epoch AI Benchmarking Hub | 95.0%† | – |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | 69.7%† | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 2041.3† | – |
| FrontierSWE | Epoch AI Benchmarking Hub | 47.0%† | – |
| WeirdML v3 | WeirdML | 15.6%† | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 42.4%† | 57.1% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 84.6%† | – |
| Startrise Frontend | Startrise | 73.8%† | – |
| GameBench 2 Overall | DuelLab GameBench 2 | 65.8 | – |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 58.1† | – |
| Design Arena Website | Design Arena | 1288 | – |
| FrontierCode 1.1 (AA) | Artificial Analysis | – | 44.9% |
| FrontierCode 2.0 (AA) | Artificial Analysis | – | 37.8% |
| 智能体与工具 | |||
| Terminal-Bench | Terminal-Bench | 44.9%† | – |
| Remote Labor Index | Scale AI / CAIS | 16.1% | – |
| APEX-Agents | Mercor | 63.6% | – |
| Arena Agent | Arena (LMArena) | 7.3† | 9 |
| LiveBench Agentic Coding | LiveBench | 62.2%† | – |
| Terminal-Bench Hard | Artificial Analysis | 62.9%† | – |
| τ²-Bench Telecom (AA) | Artificial Analysis | 98.5%† | – |
| Terminal-Bench 2.1 (Vals) | Vals AI | 80.5%† | – |
| MCP Atlas | Scale AI SEAL | 83.3% | – |
| HiL-Bench | Scale AI SEAL | 56.3% | – |
| τ³-bench Banking | τ²-bench | 39.7%† | – |
| GDPval-AA v2.1, normalised score | Artificial Analysis | – | 67.8% |
| GDPval-AA v2.1 | Artificial Analysis | 1618† | 1857 |
| τ³-Banking (AA) | Artificial Analysis | 38.1%† | – |
| Analyst Agent (AA) | Artificial Analysis | 48.8%† | – |
| CyberBench | Vals AI | – | 73.6% |
| Finance Agent v2 | Vals AI | 56.3%† | 59.1% |
| Finance Agent v2.1 | Vals AI | – | 67.6% |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | – | 23.3% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 11.3%† | 21.7% |
| Legal Research Bench | Vals AI | 49.5%† | 53.4% |
| Robo-bench | Vals AI | – | 10.4% |
| SREBench | Vals AI | – | 11.8% |
| Tax Agent Bench | Vals AI | 38.3%† | 43.0% |
| Terminal-Bench 4.0 (Vals) | Vals AI | 41.4%† | 58.1% |
| Terminal-Bench Science | Vals AI | 15.7%† | 37.1% |
| Web Search Index | Vals AI | 46.9%† | – |
| Arena Search | Arena (LMArena) | 1229† | – |
| Arena Agent Task Completion | Arena (LMArena) | 5.1† | 11.1 |
| PostTrainBench | Epoch AI Benchmarking Hub | 37.3%† | – |
| GBAEval | Epoch AI Benchmarking Hub | 74.5% | – |
| Vending-Bench 2 | Andon Labs | 4529.9 | – |
| AutomationBench | Artificial Analysis | 54.1%† | 71.3% |
| GDP.pdf (AA) | Artificial Analysis | 24.0%† | 32.6% |
| Harvey LAB-AA v1.1 | Harvey | – | 13.1% |
| EnterpriseOps-Gym | Artificial Analysis | 51.1%† | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1536† | 1729 |
| GDPx | GDPx by SemiAnalysis | – | 9.0% |
| Design Arena Agentic | Design Arena | 1275 | – |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | – | 37.1% |
| 数学 | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 87.0%† | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 90.2%† | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 99.7%† | – |
| ProofBench | Vals AI | 95.0%† | – |
| LiveBench Mathematics | LiveBench | 96.0%† | – |
| Arena Maths | Arena (LMArena) | 1520† | – |
| FrontierMath Erdős | Epoch AI Benchmarking Hub | 0.0%† | – |
| 知识 | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 70.7%† | – |
| LiveBench 1.0 Data Analysis | LiveBench | 80.5%† | – |
| AA-Omniscience v1.1 | Artificial Analysis | – | 30.6 |
| MMLU-Pro | Vals AI | 91.5%† | – |
| LegalBench | Vals AI | 88.6%† | 87.4% |
| CorpFin | Vals AI | 71.8%† | – |
| TaxEval | Vals AI | 76.9%† | – |
| PRBench Finance | Scale AI SEAL | 53.9% | – |
| PRBench Legal | Scale AI SEAL | 52.6% | – |
| BioMysteryBench | Vals AI | – | 73.3% |
| Excel Modeling Benchmark | Vals AI | 73.7%† | 71.9% |
| Excel Modeling Benchmark v1.1 | Vals AI | – | 75.0% |
| MedCode | Vals AI | 56.1%† | 49.9% |
| MedScribe | Vals AI | 88.5%† | 89.3% |
| Public Benefits Bench v1.1 | Vals AI | 70.4%† | 73.8% |
| Access to Justice Benchmark | Vals AI | – | 74.7% |
| Financial Coaching Bench | Vals AI | – | 75.0% |
| Immigration Bench | Vals AI | – | 71.2% |
| EBR-bench | Epoch AI Benchmarking Hub | 39.5%† | – |
| GDP.pdf | Epoch AI Benchmarking Hub | 30.0% | – |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | – | 41.0% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | – | 82.4% |
| 指令遵循 | |||
| LiveBench Language | LiveBench | 90.7%† | – |
| LiveBench Instruction Following | LiveBench | 75.8%† | – |
| IFBench | Artificial Analysis | 63.5%† | – |
| Arena Instruction Following | Arena (LMArena) | 1509† | – |
| 人类偏好 | |||
| Arena Text | Arena (LMArena) | 1504† | – |
| EQ-Bench 4 | EQ-Bench | 1313 | – |
| EQ-Bench Creative Writing v3 | EQ-Bench | 1944 | – |
| Arena Creative Writing | Arena (LMArena) | 1501† | – |
| Arena Multi-turn | Arena (LMArena) | 1517† | – |
| Arena Longer Queries | Arena (LMArena) | 1522† | – |
| 多模态 | |||
| Arena Vision | Arena (LMArena) | 1326† | – |
| MMMU-Pro (Vals) | Vals AI | 89.3%† | – |
| MortgageTax | Vals AI | 68.9%† | – |
| Humanity's Sixth Sense | Scale AI SEAL | 34.5%† | – |
| GeoBench | GeoBench | 89.0%† | – |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 38.6% | – |
| Furniture Assembly | Epoch AI Benchmarking Hub | 35.8%† | – |
| 长上下文 | |||
| AA-LCR v1.1 | Artificial Analysis | 82.3%† | 83.7% |
| Arena Document | Arena (LMArena) | 1500† | – |
| MLCR | Artificial Analysis | 20.6%† | 22.2% |
| 综合 | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 164.1 | – |
| LiveBench 1.0 | LiveBench | 83.0%† | – |
| AA Intelligence Index v5.0.1 | Artificial Analysis | – | 50.1 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 49.6† | 55.8 |
| AA Progress Index v1 | Artificial Analysis | 329.3† | 343.2 |
| Vals Index | Vals AI | – | 66.8 |
| Vals Finance Index | Vals AI | – | 64.5% |
| Vals RSI Index | Vals AI | 24.3%† | 24.4% |
| Vals Science Index | Vals AI | – | 48.5% |
| Vals Multimodal Index | Vals AI | 74.2%† | – |
| Vals Router Index | Vals AI | – | 66.8%† |
| Vals Legal Index | Vals AI | – | 77.9% |
| 安全与诚实 | |||
| DistressBench | Scale AI SEAL | 69.4% | – |
数据截至 2026年11月16日。对比的是每个模型的最佳配置;每项分数的来源链接都在模型页面上。
DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
变化
- Claude Fable 5:BenchLeader Index 66.5 → 65.4。
- Claude Fable 5:1 项分数修订。
- Muse Wonder Full (max):BenchLeader Index 62.6 → 61.7。
- Claude Fable 5:1 项分数修订。
- Claude Fable 5:1 项分数修订。
- Muse Wonder Full (max):1 项分数修订。
- Muse Wonder Full (max):1 项分数修订。
- Muse Wonder Full (max):1 项新结果(Arena Agent)。
- Muse Wonder Full (max):6 项新结果(AA Intelligence Index v5.0.1, AA Progress Index v1, HLE-Diamond (AA)…);2 项分数修订。
- Claude Fable 5:BenchLeader Index 67.3 → 66.5。
相关对比
- Claude Fable 5 vs Claude Fable 5.2
- Claude Fable 5 vs Gemini 4 Carbon
- Claude Fable 5 vs Claude Opus 5.5
- Muse Wonder Full vs Claude Fable 5.2
- Muse Wonder Full vs Gemini 4 Carbon
- Muse Wonder Full vs Claude Opus 5.5
- Muse Wonder Full vs GPT-6 Astra
- Claude Fable 5 vs Muse Spark 1.3
排行榜: 综合最佳大模型 · 最适合编程的大模型 · 最适合智能体的大模型 · 便宜好用的大模型
Claude Fable 5 vs Muse Wonder Full:常见问题
- Claude Fable 5 比 Muse Wonder Full 更好吗?
- 质量上 Claude Fable 5 领先:65.4 比 61.7。BenchLeader Index 综合了所有第三方质量基准测试;截至 2026年11月16日,Claude Fable 5 总体领先,但请结合你的用途查看各类别得分。
- 编程用 Claude Fable 5 还是 Muse Wonder Full 更好?
- Claude Fable 5 在编程方面得分更高(类别得分 76 比 70,50 为平均水平)。
- 智能体和工具调用用 Claude Fable 5 还是 Muse Wonder Full 更好?
- Muse Wonder Full 在智能体任务方面得分更高(类别得分 64 比 61,50 为平均水平)。
- 处理长文档哪个更好?
- 两者都支持 1,000,000 token 的上下文。
- Muse Wonder Full 是什么时候发布的?
- Muse Wonder Full 于 2026年10月12日 发布。