Claude Opus 4.5 vs Muse Wonder Full
完整资料:Claude Opus 4.5(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 11 个来源
截至 2026年11月16日,Claude Opus 4.5 与 Muse Wonder Full 的质量不相上下(BenchLeader Index 59.7 比 61.7,在 ±4.0 的误差范围内)。在两者都有成绩的所有类别中,Muse Wonder Full 均领先。
要点(截至 2026年11月16日)
- Claude Opus 4.5 的 BenchLeader Index 为 59.7,Muse Wonder Full 为 61.7(BenchLeader,2026年11月16日)。
- Claude Opus 4.5 每百万 token 混合价格为 $10.00(标价,2026年11月16日)。
- 在两者都有结果的 6 项基准测试中,Muse Wonder Full 领先 6 项(BenchLeader,2026年11月16日)。
- 在 Arena WebDev 上,Claude Opus 4.5 的评分为 1493,Muse Wonder Full 为 1724(LMArena,截至 2026年11月16日 的公布数据)。
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
- Claude Opus 4.5 (high) 与 Muse Wonder Full (max) 的质量不相上下(59.7 比 61.7,在 ±4.0 的误差范围内)。
- Claude Opus 4.5 (high) 在推理方面更强。
- Muse Wonder Full (max) 在智能体与工具、编程、知识方面更强。
概览
| 规格 | Claude Opus 4.5 | Muse Wonder Full |
|---|---|---|
| 提供商 | Anthropic | Meta |
| 发布日期 | 2025年11月24日 | 2026年10月12日 |
| 上下文窗口(token) | 200,000 | 1,000,000 |
| 对比时的配置 | Claude Opus 4.5 (high) | Muse Wonder Full (max) |
| 开放权重 | 否 | 否 |
| 每百万 token 价格(输入 / 输出 / 缓存输入) | $5.00 / $25.00 / $0.500 | – |
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 Opus 4.5 (high) | Muse Wonder Full (max) | 领先者 |
|---|---|---|---|
| 推理 | 66.6 | 65.8 | 持平 |
| 编程 | 60.6 | 69.9 | Muse Wonder Full |
| 智能体与工具 | 52.7 | 63.6 | Muse Wonder Full |
| 数学 | 65.3 | – | 无法比较 |
| 知识 | 60.0 | 62.3 | Muse Wonder Full |
| 人类偏好 | 66.2 | – | 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 6 项基准测试中,Claude Opus 4.5 领先 0 项,Muse Wonder Full 领先 6 项。
| 综合 Index | Claude Opus 4.5 (high) | Muse Wonder Full (max) | 领先者 |
|---|---|---|---|
| BenchLeader Index | 59.7 | 61.7 | 不相上下 |
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 Opus 4.5 (high) | Muse Wonder Full (max) |
|---|---|---|
| 每百万 token 混合价格 | $10.00 | – |
| 每百万 token 输入 / 输出 | $5.00 / $25.00 | – / – |
| 每百万 token 缓存输入 | $0.500 | – |
| 每项任务价格:聊天回复 | $0.0095 | – |
| 每项任务价格:总结一份 30 页的报告 | $0.075 | – |
| 每项任务价格:代码编辑 | $0.068 | – |
| 每项任务价格:智能体编程会话 | $0.400 | – |
| 每项任务价格:结构化信息提取 | $0.015 | – |
| 智能体编程会话(输入大多命中缓存) | $0.198 | – |
| 每项任务输出 token(AA Index) | – | 88k |
| 其中推理部分 | – | 55k |
| 输出速度 | 40 tok/s | – |
| 首次回答时间 | 1.1 秒 | – |
每个模型都按其排名最高的推理强度设置进行对比。Claude Opus 4.5 (high) 得分 59.7,首个回答 token 需 1 秒;Claude Opus 4.5 (thinking) 为 59.3(14 秒),Claude Opus 4.5 为 57.1(1 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 163 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 Opus 4.5 (high) | Muse Wonder Full (max) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 59.7 | 61.7 |
| 智能体与工具得分 | BenchLeader | 52.7 | 63.6 |
| 编程得分 | BenchLeader | 60.6 | 69.9 |
| 人类偏好得分 | BenchLeader | 66.2 | – |
| 知识得分 | BenchLeader | 60.0 | 62.3 |
| 数学得分 | BenchLeader | 65.3 | – |
| 推理得分 | BenchLeader | 66.6 | 65.8 |
| 长上下文得分 | BenchLeader | – | 66.6 |
| 混合价格(美元/百万 token) | BenchLeader | $10.00 | – |
| 输出速度 | BenchLeader | 40 tok/s | – |
| 首次回答时间 | BenchLeader | 1.1 秒 | – |
| 上下文窗口 | BenchLeader | 200,000 token | 1,000,000 token |
| 推理 | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 86.0%† | – |
| Humanity's Last Exam | Scale AI / CAIS | 25.2%† | – |
| SimpleBench | SimpleBench | 62.0%† | – |
| Arena Hard Prompts | Arena (LMArena) | 1501 | – |
| LiveBench 1.0 Reasoning | LiveBench | 80.1% | – |
| GPQA Diamond (AA) | Artificial Analysis | 86.6%† | – |
| Humanity's Last Exam (AA) | Artificial Analysis | 30.1%† | 53.6% |
| HLE-Diamond (AA) | Artificial Analysis | – | 48.5% |
| GPQA Diamond (Vals) | Vals AI | 85.9% | – |
| Kagi LLM Benchmark | Kagi LLM Benchmark | 70.7%† | – |
| ARC-AGI-1 | ARC Prize | 80.0%† | – |
| ARC-AGI-2 | ARC Prize | 37.6%† | – |
| CritPt | Artificial Analysis | 4.6%† | 32.9% |
| CritPt v2 hard subset (AA) | Artificial Analysis | – | 56.5% |
| MysteryMechanism | Vals AI | – | 35.1% |
| SciPredict | Scale AI SEAL | 23.1%† | – |
| Arena Expert | Arena (LMArena) | 1503 | – |
| Chess Puzzles | Epoch AI Benchmarking Hub | 14.0%† | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 22.0%† | – |
| CL-bench | Epoch AI Benchmarking Hub | 21.1%† | – |
| LMCA | Epoch AI Benchmarking Hub | 44.5% | – |
| DTBench | Epoch AI Benchmarking Hub | 89.9% | – |
| ForecastBench | ForecastBench | 64.6%† | – |
| 编程 | |||
| SWE-bench Verified (Epoch) | Epoch AI Benchmarking Hub | 76.7%† | – |
| WeirdML | WeirdML | 63.7%† | – |
显示全部 163 项基准测试
| 指标 | 发布方 | Claude Opus 4.5 (high) | Muse Wonder Full (max) |
|---|---|---|---|
| 编程 | |||
| GSO-Bench | GSO-Bench | 26.5%† | – |
| Arena Coding | Arena (LMArena) | 1530 | – |
| Arena WebDev | Arena (LMArena) | 1493 | 1724 |
| LiveBench 1.0 Coding | LiveBench | 79.7% | – |
| SciCode (AA) | Artificial Analysis | – | 62.6% |
| LiveCodeBench | Vals AI | 83.7% | – |
| IOI | Vals AI | – | 79.8% |
| SWE-bench (Vals) | Vals AI | 76.4% | – |
| SWE-Bench Pro | Scale AI SEAL | 45.9%† | – |
| SWE-bench Verified (bash only) | SWE-bench | 76.8% | – |
| SWE-bench Multilingual (bash only) | SWE-bench | 70.7%† | – |
| SWE-bench Verified (any scaffold) | SWE-bench | 79.2%† | – |
| Code Migration | Vals AI | – | 61.0% |
| Code Migration v1.1 | Vals AI | – | 62.8% |
| ProgramBench | Vals AI | – | 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 | 20.6% | 86.0% |
| SWE-Bench Pro (private) | Scale AI SEAL | 23.4%† | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 1025.4† | – |
| AlgoTune | AlgoTune | 1.8† | – |
| WeirdML v3 | WeirdML | 6.5% | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | – | 57.1% |
| GameBench 2 Overall | DuelLab GameBench 2 | 47.1† | – |
| Design Arena Website | Design Arena | 1239† | – |
| FrontierCode 1.1 (AA) | Artificial Analysis | – | 44.9% |
| FrontierCode 2.0 (AA) | Artificial Analysis | – | 37.8% |
| LiveCodeBench (AA) | Artificial Analysis | 87.1%† | – |
| 智能体与工具 | |||
| Terminal-Bench | Terminal-Bench | 63.1%† | – |
| GDPval | OpenAI | 45.5%† | – |
| Cybench | Cybench | 82.0%† | – |
| Remote Labor Index | Scale AI / CAIS | 3.8%† | – |
| Arena Agent | Arena (LMArena) | – | 9 |
| LiveBench Agentic Coding | LiveBench | 39.7% | – |
| Terminal-Bench Hard | Artificial Analysis | 47.0%† | – |
| τ²-Bench Telecom (AA) | Artificial Analysis | 89.5%† | – |
| MCP Atlas | Scale AI SEAL | 69.8% | – |
| BFCL Overall | Berkeley Function Calling Leaderboard | 77.5%† | – |
| τ²-bench | τ²-bench | 85.3% | – |
| τ³-bench Banking | τ²-bench | 24.7% | – |
| GDPval-AA v2.1, normalised score | Artificial Analysis | – | 67.8% |
| GDPval-AA v2.1 | Artificial Analysis | – | 1857 |
| CyberBench | Vals AI | – | 73.6% |
| Finance Agent v2 | Vals AI | – | 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 | – | 21.7% |
| Legal Research Bench | Vals AI | – | 53.4% |
| Poker Agent | Vals AI | 1033.4%† | – |
| Robo-bench | Vals AI | – | 10.4% |
| SREBench | Vals AI | – | 11.8% |
| Tax Agent Bench | Vals AI | – | 43.0% |
| Terminal-Bench 2.0 (Vals) | Vals AI | 58.4% | – |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 58.1% |
| Terminal-Bench Science | Vals AI | – | 37.1% |
| Arena Search | Arena (LMArena) | 1186† | – |
| Arena Agent Task Completion | Arena (LMArena) | – | 11.1 |
| BALROG | BALROG | 43.0%† | – |
| DeepResearch Bench | DeepResearch Bench | 54.8% | – |
| METR Time Horizons | METR | 75.0%† | – |
| Vending-Bench 2 | Andon Labs | 4967.1† | – |
| AutomationBench | Artificial Analysis | – | 71.3% |
| GDP.pdf (AA) | Artificial Analysis | – | 32.6% |
| Harvey LAB-AA v1.1 | Harvey | – | 13.1% |
| AA-Briefcase v1.1 | Artificial Analysis | – | 1729 |
| GDPx | GDPx by SemiAnalysis | – | 9.0% |
| Design Arena Agentic | Design Arena | 1156† | – |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | – | 37.1% |
| DeepSearchQA | 24.0%† | – | |
| 数学 | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 34.4%† | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 4.9%† | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 86.1%† | – |
| ProofBench | Vals AI | 36.0%† | – |
| LiveBench Mathematics | LiveBench | 90.4% | – |
| AIME (Vals) | Vals AI | 76.9%† | – |
| MGSM | Vals AI | 94.8%† | – |
| Arena Maths | Arena (LMArena) | 1472 | – |
| AIME 2025 (AA) | Artificial Analysis | 91.3%† | – |
| 知识 | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 45.7%† | – |
| LiveBench 1.0 Data Analysis | LiveBench | 74.4% | – |
| AA-Omniscience v1.1 | Artificial Analysis | – | 30.6 |
| MMLU-Pro | Vals AI | 87.3% | – |
| LegalBench | Vals AI | 84.6% | 87.4% |
| CorpFin | Vals AI | 65.1% | – |
| TaxEval | Vals AI | 74.9% | – |
| MedQA | Vals AI | 93.2%† | – |
| PRBench Finance | Scale AI SEAL | 46.2%† | – |
| PRBench Legal | Scale AI SEAL | 44.2%† | – |
| MultiNRC | Scale AI SEAL | 41.2%† | – |
| BioMysteryBench | Vals AI | – | 73.3% |
| CaseLaw v2 | Vals AI | 62.6%† | – |
| Excel Modeling Benchmark | Vals AI | – | 71.9% |
| Excel Modeling Benchmark v1.1 | Vals AI | – | 75.0% |
| MedCode | Vals AI | 49.2% | 49.9% |
| MedScribe | Vals AI | 85.3% | 89.3% |
| Public Benefits Bench v1.1 | Vals AI | – | 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 | 14.3%† | – |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | – | 41.0% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | – | 82.4% |
| Global-MMLU-Lite (AA) | Artificial Analysis | 91.3%† | – |
| 指令遵循 | |||
| LiveBench Language | LiveBench | 81.3% | – |
| LiveBench Instruction Following | LiveBench | 62.5% | – |
| IFBench | Artificial Analysis | 58.0%† | – |
| MultiChallenge | Scale AI SEAL | 59.0%† | – |
| TutorBench | Scale AI SEAL | 49.8%† | – |
| Arena Instruction Following | Arena (LMArena) | 1483 | – |
| 人类偏好 | |||
| Arena Text | Arena (LMArena) | 1474 | – |
| EQ-Bench Creative Writing v3 | EQ-Bench | 1686† | – |
| Arena Creative Writing | Arena (LMArena) | 1469 | – |
| Arena Multi-turn | Arena (LMArena) | 1485 | – |
| Arena Longer Queries | Arena (LMArena) | 1495 | – |
| 多模态 | |||
| MMMU-Pro | Artificial Analysis | 74.0%† | – |
| VISTA | Scale AI SEAL | 45.3%† | – |
| MMMU-Pro (Vals) | Vals AI | 83.0% | – |
| MortgageTax | Vals AI | 68.7% | – |
| GeoBench | GeoBench | 75.0%† | – |
| VPCT | Epoch AI Benchmarking Hub | 40.0%† | – |
| Furniture Assembly | Epoch AI Benchmarking Hub | 28.3%† | – |
| 长上下文 | |||
| AA-LCR v1.1 | Artificial Analysis | 77.3%† | 83.7% |
| Arena Document | Arena (LMArena) | 1468† | – |
| MLCR | Artificial Analysis | – | 22.2% |
| 综合 | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 151.9† | – |
| LiveBench 1.0 | LiveBench | 72.6% | – |
| AA Intelligence Index v5.0.1 | Artificial Analysis | – | 50.1 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 29.1† | 55.8 |
| AA Progress Index v1 | Artificial Analysis | 284.4† | 343.2 |
| Vals Index | Vals AI | – | 66.8 |
| Vals Finance Index | Vals AI | – | 64.5% |
| Vals RSI Index | Vals AI | 14.8% | 24.4% |
| Vals Science Index | Vals AI | – | 48.5% |
| Vals Router Index | Vals AI | – | 66.8%† |
| Vals Legal Index | Vals AI | – | 77.9% |
| 安全与诚实 | |||
| FORTRESS | Scale AI SEAL | 13.6%† | – |
| MASK | Scale AI SEAL | 87.1%† | – |
| 元数据 | |||
| AA Openness Index | Artificial Analysis | 11.1† | – |
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 Opus 4.5 (high):13 项新结果(LiveCodeBench, MMLU-Pro, LegalBench…)。
- Muse Wonder Full (max):BenchLeader Index 62.6 → 61.7。
- 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。
- Muse Wonder Full (max):1 项新结果(Terminal-Bench-Science 0.1 (AA))。
- Claude Opus 4.5 (high):1 项新结果(Vals RSI Index)。
- Muse Wonder Full (max):9 项新结果(Code Migration v1.1, Excel Modeling Benchmark v1.1, Finance Agent v2.1…)。
- Muse Wonder Full (max):1 项新结果(FrontierCode 1.1 (AA))。
相关对比
- 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 Opus 4.5 vs Muse Spark 1.3
- Claude Opus 4.5 vs GPT-6.1 Sol
- Claude Opus 4.5 vs Gemini 4 Argon
- Claude Opus 4.5 vs Claude Sonnet 5.5
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 Opus 4.5 vs Muse Wonder Full:常见问题
- Claude Opus 4.5 比 Muse Wonder Full 更好吗?
- Claude Opus 4.5 (high) 与 Muse Wonder Full (max) 的质量不相上下(59.7 比 61.7,在 ±4.0 的误差范围内)。BenchLeader Index 综合了所有第三方质量基准测试;截至 2026年11月16日,两者差距在误差范围内,请结合你的用途查看各类别得分。
- 编程用 Claude Opus 4.5 还是 Muse Wonder Full 更好?
- Muse Wonder Full 在编程方面得分更高(类别得分 70 比 61,50 为平均水平)。在两者共同的最主要编程基准测试 Arena WebDev 上,Claude Opus 4.5 为 1493,Muse Wonder Full 为 1724。
- 智能体和工具调用用 Claude Opus 4.5 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 53,50 为平均水平)。
- 处理长文档哪个更好?
- Muse Wonder Full 支持更长的上下文:1,000,000 token,Claude Opus 4.5 为 200,000 token。
- 第三方基准测试对 Claude Opus 4.5 和 Muse Wonder Full 的看法一致吗?
- 在两者都有结果的 6 项基准测试中,Claude Opus 4.5 领先 0 项,Muse Wonder Full 领先 6 项。
更多问题(1)
- Muse Wonder Full 是什么时候发布的?
- Muse Wonder Full 于 2026年10月12日 发布。