GPT-5.5 vs Muse Wonder
完整资料:GPT-5.5(OpenAI)和 Muse Wonder(Meta),包括全部基准测试、价格和排名。
更新于 · 数据来自 13 个来源
截至 2026年11月16日,GPT-5.5 与 Muse Wonder 的质量不相上下(BenchLeader Index 64.1 比 64.4,在 ±4.9 的误差范围内)。Muse Wonder 更便宜,对方的价格是它的 1.4 倍(每百万 token 混合价格 $8.00 比 $11.25)。在两者都有成绩的所有类别中,Muse Wonder 均领先。
要点(截至 2026年11月16日)
- GPT-5.5 的 BenchLeader Index 为 64.1,Muse Wonder 为 64.4(BenchLeader,2026年11月16日)。
- GPT-5.5 每百万 token 混合价格为 $11.25(标价,2026年11月16日)。
- Muse Wonder 每百万 token 混合价格为 $8.00(标价,2026年11月16日)。
- 在两者都有结果的 3 项基准测试中,Muse Wonder 领先 2 项(BenchLeader,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”。
| 用途 | 推荐 | 理由 | 置信度 |
|---|---|---|---|
| 智能体与工具调用 | Muse Wonder | 类别得分 76 比 62 | 高 |
| 数学 | 均可 | 类别得分 69 比 70;ProofBench 50.0% 比 84.0% | 均可 |
| 知识 | Muse Wonder | 类别得分 77 比 64 | 高 |
| 对话质量(人类偏好) | – | 只有 Muse Wonder 有 Arena 评分(类别得分 70) | 无法比较 |
| 成本最低 | Muse Wonder | 每百万 token 混合价格 $8.00 比 $11.25;智能体编程会话 $0.320 比 $0.420 | – |
| 首次回答最快 | Muse Wonder | 首个回答 token 3.3 秒(Muse Wonder)比 38.3 秒(GPT-5.5 (xhigh)) | – |
| 低预算大批量 | 两者都不选 | 通常更小的模型更合适:便宜好用的大模型、最快的大模型 | – |
主要差异
- GPT-5.5 (xhigh) 与 Muse Wonder 的质量不相上下(64.1 比 64.4,在 ±4.9 的误差范围内)。
- Muse Wonder 在智能体与工具、知识、数学方面更强。
- Muse Wonder 更便宜,对方的价格是它的 1.4 倍(每百万 token 混合价格 $8.00 比 $11.25)。
概览
| 规格 | GPT-5.5 | Muse Wonder |
|---|---|---|
| 提供商 | OpenAI | Meta |
| 发布日期 | 2026年4月23日 | 2026年10月12日 |
| 上下文窗口(token) | 1,050,000 | 1,048,576 |
| 对比时的配置 | GPT-5.5 (xhigh) | Muse Wonder |
| 开放权重 | 否 | 否 |
| 每百万 token 价格(输入 / 输出 / 缓存输入) | $5.00 / $30.00 / $0.500 | $4.00 / $20.00 / $0.200 |
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 | GPT-5.5 (xhigh) | Muse Wonder | 领先者 |
|---|---|---|---|
| 推理 | 68.1 | – | 无法比较 |
| 编程 | 60.7 | – | 无法比较 |
| 智能体与工具 | 61.8 | 75.6 | Muse Wonder |
| 数学 | 69.3 | 70.1 | 持平 |
| 知识 | 63.6 | 77.1 | Muse Wonder |
| 指令遵循 | 74.0 | – | 无法比较 |
| 人类偏好 | – | 69.6 | 无法比较 |
| 多模态 | 62.3 | – | 无法比较 |
| 长上下文 | 66.9 | – | 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):推理, 编程, 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 3 项基准测试中,GPT-5.5 领先 1 项,Muse Wonder 领先 2 项。所有同时评测两者的综合评分都认为 Muse Wonder 更强。
| 综合 Index | GPT-5.5 (xhigh) | Muse Wonder | 领先者 |
|---|---|---|---|
| BenchLeader Index | 64.1 | 64.4 | 不相上下 |
| Arena Text | 1481† | 1511 | Muse Wonder |
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 | GPT-5.5 (xhigh) | Muse Wonder |
|---|---|---|
| 每百万 token 混合价格 | $11.25 | $8.00 |
| 每百万 token 输入 / 输出 | $5.00 / $30.00 | $4.00 / $20.00 |
| 每百万 token 缓存输入 | $0.500 | $0.200 |
| 每项任务价格:聊天回复 | $0.011 | $0.0076 |
| 每项任务价格:总结一份 30 页的报告 | $0.078 | $0.060 |
| 每项任务价格:代码编辑 | $0.075 | $0.054 |
| 每项任务价格:智能体编程会话 | $0.420 | $0.320 |
| 每项任务价格:结构化信息提取 | $0.016 | $0.012 |
| 智能体编程会话(输入大多命中缓存) | $0.217 | $0.149 |
| 输出速度 | 81 tok/s | 70 tok/s |
| 首次回答时间 | 38.3 秒 | 3.3 秒 |
| 完整回答耗时(最近一次测量 2026年11月13日) | 104.3 秒 | – |
每个模型都按其排名最高的推理强度设置进行对比。GPT-5.5 (xhigh) 得分 64.1,首个回答 token 需 38 秒;GPT-5.5 (high) 为 63.5(16 秒),GPT-5.5 为 61.0(3 秒)。Muse Wonder 得分 64.4,首个回答 token 需 3 秒;Muse Wonder (max) 为 60.8(20 秒),Muse Wonder (high) 为 56.2(13 秒)。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 190 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 | GPT-5.5 (xhigh) | Muse Wonder |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 64.1 | 64.4 |
| 智能体与工具得分 | BenchLeader | 61.8 | 75.6 |
| 编程得分 | BenchLeader | 60.7 | – |
| 指令遵循得分 | BenchLeader | 74.0 | – |
| 知识得分 | BenchLeader | 63.6 | 77.1 |
| 长上下文得分 | BenchLeader | 66.9 | – |
| 数学得分 | BenchLeader | 69.3 | 70.1 |
| 多模态得分 | BenchLeader | 62.3 | – |
| 推理得分 | BenchLeader | 68.1 | – |
| 人类偏好得分 | BenchLeader | – | 69.6 |
| 混合价格(美元/百万 token) | BenchLeader | $11.25 | $8.00 |
| 输出速度 | BenchLeader | 81 tok/s | 70 tok/s |
| 首次回答时间 | BenchLeader | 38.3 秒 | 3.3 秒 |
| 上下文窗口 | BenchLeader | 1,050,000 token | 1,048,576 token |
| 推理 | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 90.7%† | – |
| SimpleBench | SimpleBench | 69.0%† | – |
| Arena Hard Prompts | Arena (LMArena) | 1499† | 1531† |
| LiveBench 2.0 Reasoning | LiveBench | – | 90.6%† |
| LiveBench 1.0 Reasoning | LiveBench | 89.7% | 90.6%† |
| GPQA Diamond (AA) | Artificial Analysis | 93.5% | – |
| Humanity's Last Exam (AA) | Artificial Analysis | 45.8% | 50.1%† |
| HLE-Diamond (AA) | Artificial Analysis | – | 39.0%† |
| GPQA Diamond (Vals) | Vals AI | 93.2% | – |
| Kagi LLM Benchmark | Kagi LLM Benchmark | 88.8%† | – |
| ARC-AGI-1 | ARC Prize | 95.0% | – |
| ARC-AGI-2 | ARC Prize | 85.0% | – |
| ARC-AGI-3 | ARC Prize | 0.4%† | – |
| CritPt | Artificial Analysis | 27.1% | 28.3%† |
| CritPt v2 hard subset (AA) | Artificial Analysis | – | 50.5%† |
| MysteryMechanism | Vals AI | – | 27.5%† |
| HLE-Diamond (Scale) | Scale AI SEAL | – | 37.3% |
| Arena Expert | Arena (LMArena) | 1510† | 1525† |
| Chess Puzzles | Epoch AI Benchmarking Hub | 63.0% | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 56.0% | 51.0%† |
| CL-bench Life | Epoch AI Benchmarking Hub | 22.2%† | – |
| LMCA | Epoch AI Benchmarking Hub | 54.3% | 56.8% |
| DTBench | Epoch AI Benchmarking Hub | 96.0% | 95.2% |
| ForecastBench | ForecastBench | 64.2%† | – |
| BTF-3 | Epoch AI Benchmarking Hub | 14.3%† | – |
显示全部 190 项基准测试
| 指标 | 发布方 | GPT-5.5 (xhigh) | Muse Wonder |
|---|---|---|---|
| 编程 | |||
| SciCode | SciCode | 55.8% | 60.3%† |
| WeirdML | WeirdML | 84.9% | – |
| FrontierCode | Cognition | 43.0%† | – |
| GSO-Bench | GSO-Bench | 40.2% | – |
| Arena Coding | Arena (LMArena) | 1510† | 1542† |
| Arena WebDev | Arena (LMArena) | 1512 | 1647† |
| LiveBench 2.0 Coding | LiveBench | – | 74.9%† |
| LiveBench 1.0 Coding | LiveBench | 82.2% | 80.7%† |
| LiveCodeBench | Vals AI | 85.3% | – |
| IOI | Vals AI | – | 66.9%† |
| SWE-bench (Vals) | Vals AI | 82.6% | – |
| Code Migration | Vals AI | 45.2% | 62.5%† |
| Code Migration v1.1 | Vals AI | – | 72.4%† |
| ProgramBench | Vals AI | 0.5% | – |
| SWE-bench Multimodal | Vals AI | – | 45.6%† |
| Vibe Code Bench 1-100 | Vals AI | – | 26.6%† |
| Vibe Code Bench v1.1 | Vals AI | 69.8% | 83.1%† |
| SWE Atlas v1.0: Codebase QnA | Scale AI SEAL | 45.4% | – |
| SWE Atlas v1.0: Refactoring | Scale AI SEAL | 44.8% | – |
| SWE Atlas v1.0: Test Writing | Scale AI SEAL | 42.6% | – |
| SWE Atlas v1.1 | Scale AI SEAL | – | 64.8% |
| SWE Atlas v1.1: Codebase QnA | Scale AI SEAL | – | 73.4% |
| SWE Atlas v1.1: Test Writing | Scale AI SEAL | – | 61.1% |
| SWE Atlas v1.1: Refactoring | Scale AI SEAL | – | 60.0% |
| SWE-Bench Pro V2 | Scale AI SEAL | – | 96.7%† |
| SWE-Bench Pro V2 HARD | Scale AI SEAL | – | 90.2%† |
| MirrorCode | Epoch AI Benchmarking Hub | 23.3% | 45.6%† |
| Surface Evolver Bench | Epoch AI Benchmarking Hub | 88.1%† | – |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | 67.0% | – |
| CursorBench | Cursor | – | 50.4%† |
| ALE-Bench | Epoch AI Benchmarking Hub | 1943.0 | – |
| WeirdML v3 | WeirdML | – | 15.2%† |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 14.7% | 52.0%† |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 84.3% | – |
| GameBench 2 Overall | DuelLab GameBench 2 | 49.2† | 64.8 |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 59.9 | 54.9† |
| Design Arena Website | Design Arena | 1248† | 1378† |
| FrontierCode 1.1 (AA) | Artificial Analysis | – | 46.5%† |
| FrontierCode 2.0 (AA) | Artificial Analysis | – | 27.9%† |
| 智能体与工具 | |||
| Terminal-Bench | Terminal-Bench | 84.7%† | 47.0%† |
| OSWorld-Verified 2.0 | OSWorld | 13.0% | – |
| Remote Labor Index | Scale AI / CAIS | 6.3%† | – |
| APEX-Agents | Mercor | 55.1%† | 66.1%† |
| Arena Agent | Arena (LMArena) | – | 1.8† |
| LiveBench Long Agentic | LiveBench | – | 46.2%† |
| LiveBench Browser | LiveBench | – | 60.0%† |
| LiveBench Agentic Coding | LiveBench | 54.0% | 62.7%† |
| Terminal-Bench Hard | Artificial Analysis | 60.6% | – |
| τ²-Bench Telecom (AA) | Artificial Analysis | 93.9% | – |
| Terminal-Bench 2.1 (Vals) | Vals AI | 57.3%† | – |
| MCP Atlas | Scale AI SEAL | 75.3% | – |
| HiL-Bench | Scale AI SEAL | 39.7%† | 79.7% |
| τ³-bench Banking | τ²-bench | 44.6% | – |
| GDPval-AA v2.1, normalised score | Artificial Analysis | – | 63.5%† |
| GDPval-AA v2.1 | Artificial Analysis | 1357 | 1770† |
| τ³-Banking (AA) | Artificial Analysis | 39.0% | – |
| ITBench SRE (AA) | Artificial Analysis | 45.8% | – |
| Analyst Agent (AA) | Artificial Analysis | 50.0% | – |
| APEX-Agents (AA) | Artificial Analysis | 37.7% | – |
| CUA-bench | Vals AI | – | 7.2%† |
| CyberBench | Vals AI | – | 80.4%† |
| Finance Agent v2 | Vals AI | 51.8% | 56.6%† |
| Finance Agent v2.1 | Vals AI | – | 65.5%† |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | – | 23.8%† |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 3.8% | 17.1%† |
| Legal Research Bench | Vals AI | 40.4% | 50.5%† |
| SkillsBench | Vals AI | 62.2% | – |
| SREBench | Vals AI | 3.8% | – |
| Tax Agent Bench | Vals AI | 21.8% | 36.3%† |
| Terminal-Bench 2.0 (Vals) | Vals AI | 73.2%† | – |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 49.5%† |
| Terminal-Bench Science | Vals AI | – | 22.9%† |
| Time Horizon Index: KSP | Vals AI | 8.3% | – |
| Arena Search | Arena (LMArena) | 1226† | – |
| Arena Agent Task Completion | Arena (LMArena) | – | 5.4† |
| DeepResearch Bench | DeepResearch Bench | 54.0%† | – |
| PostTrainBench | Epoch AI Benchmarking Hub | 23.9% | 24.2%† |
| ExploitBench | Epoch AI Benchmarking Hub | 47.4%† | – |
| GBAEval | Epoch AI Benchmarking Hub | 53.2%† | – |
| Vending-Bench 2 | Andon Labs | 7523.8† | 9432.2 |
| AutomationBench | Artificial Analysis | 47.3% | 68.1%† |
| GDP.pdf (AA) | Artificial Analysis | 21.2% | 30.6%† |
| Harvey LAB-AA v1.1 | Harvey | – | 10.0%† |
| EnterpriseOps-Gym | Artificial Analysis | 46.6% | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1135 | 1659† |
| GDPx | GDPx by SemiAnalysis | – | 6.8%† |
| Design Arena Agentic | Design Arena | 1113† | 1177† |
| RoboDojo (LLM as robot policy) | RoboDojo | 1.1† | – |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | – | 25.7%† |
| MKA (AA) | Artificial Analysis | – | 47.5%† |
| 数学 | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 85.3% | 82.1%† |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 72.5% | 70.7%† |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 84.4%† | 99.4%† |
| ProofBench | Vals AI | 50.0% | 84.0% |
| LiveBench Mathematics | LiveBench | 95.9% | 96.5%† |
| AIME 2026 | MathArena | 100.0% | – |
| HMMT February 2026 | MathArena | 98.5% | – |
| USAMO 2026 | MathArena | 98.2% | – |
| MathArena Apex | MathArena | 80.2% | – |
| Arena Maths | Arena (LMArena) | 1500† | 1490† |
| FrontierMath Erdős | Epoch AI Benchmarking Hub | 0.0% | – |
| 知识 | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 63.0% | – |
| LiveBench 2.0 Data Analysis | LiveBench | – | 81.6%† |
| LiveBench Research | LiveBench | – | 93.0%† |
| LiveBench 1.0 Data Analysis | LiveBench | 81.6% | 81.6%† |
| AA-Omniscience v1.1 | Artificial Analysis | – | 25.1† |
| MMLU-Pro | Vals AI | 88.1% | – |
| LegalBench | Vals AI | 86.5% | – |
| CorpFin | Vals AI | 68.4% | – |
| TaxEval | Vals AI | 75.0% | – |
| PRBench Finance | Scale AI SEAL | – | 58.7% |
| PRBench Legal | Scale AI SEAL | – | 58.4% |
| BioMysteryBench | Vals AI | – | 67.0%† |
| CaseLaw v2 | Vals AI | 66.2% | – |
| Excel Modeling Benchmark | Vals AI | 64.5% | 67.1%† |
| Excel Modeling Benchmark v1.1 | Vals AI | – | 72.5%† |
| MedCode | Vals AI | 49.1% | – |
| MedScribe | Vals AI | 86.9% | – |
| Public Benefits Bench v1.1 | Vals AI | 60.9% | 70.2%† |
| Access to Justice Benchmark | Vals AI | – | 73.0%† |
| Financial Coaching Bench | Vals AI | – | 73.8%† |
| Immigration Bench | Vals AI | – | 69.6%† |
| DrugDiscoveryBench | Scale AI SEAL | 51.6% | – |
| EBR-bench | Epoch AI Benchmarking Hub | 34.3% | 31.4%† |
| GDP.pdf | Epoch AI Benchmarking Hub | 26.0% | 30.8%† |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | – | 38.0%† |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | – | 79.1%† |
| 指令遵循 | |||
| LiveBench Language | LiveBench | 87.4% | 82.9%† |
| LiveBench Instruction Following | LiveBench | 70.7% | 73.0%† |
| IFBench | Artificial Analysis | 75.8% | – |
| Arena Instruction Following | Arena (LMArena) | 1475† | 1498† |
| 人类偏好 | |||
| Arena Text | Arena (LMArena) | 1476† | 1511† |
| EQ-Bench 4 | EQ-Bench | 1295† | 1325 |
| EQ-Bench Creative Writing v3 | EQ-Bench | 1845† | 2007 |
| Arena Creative Writing | Arena (LMArena) | 1448† | 1491† |
| Arena Multi-turn | Arena (LMArena) | 1484† | 1525† |
| Arena Longer Queries | Arena (LMArena) | 1486† | 1507† |
| 多模态 | |||
| Arena Vision | Arena (LMArena) | 1296† | – |
| LiveBench Design | LiveBench | – | 70.9%† |
| MMMU-Pro | Artificial Analysis | 79.9% | 83.8%† |
| MMMU-Pro (Vals) | Vals AI | 88.3% | – |
| MortgageTax | Vals AI | 68.8% | – |
| Humanity's Sixth Sense | Scale AI SEAL | – | 43.7%† |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 36.2%† | 31.7% |
| Furniture Assembly | Epoch AI Benchmarking Hub | 44.2% | 54.2%† |
| VIALS-AA | Handshake AI | – | 55.3%† |
| Code2Video-AA | Artificial Analysis | 1000 | 997† |
| 长上下文 | |||
| AA-LCR v1.1 | Artificial Analysis | 84.3% | 80.7%† |
| Arena Document | Arena (LMArena) | 1479† | – |
| MLCR | Artificial Analysis | 28.9% | 22.2%† |
| 综合 | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 160.1† | 161.7 |
| LiveBench 2.0 | LiveBench | – | 70.7%† |
| LiveBench 1.0 | LiveBench | 80.2% | 81.2%† |
| AA Intelligence Index v5.0.1 | Artificial Analysis | – | 43.6† |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 38.4 | 52.4† |
| AA Progress Index v1 | Artificial Analysis | 320 | 335.8† |
| Vals Index | Vals AI | – | 64.9† |
| Vals Finance Index | Vals AI | – | 61.2%† |
| Vals RSI Index | Vals AI | 16.5% | – |
| Vals Science Index | Vals AI | – | 39.1%† |
| Vals Multimodal Index | Vals AI | 68.1% | – |
| Vals Router Index | Vals AI | – | 64.9% |
| Vals Legal Index | Vals AI | – | 75.3%† |
| 安全与诚实 | |||
| FORTRESS | Scale AI SEAL | 16.3% | – |
| DistressBench | Scale AI SEAL | – | 85.9% |
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
- Muse Wonder:BenchLeader Index 63.0 → 64.4。
- GPT-5.5 (xhigh):1 项新结果(GDPval-AA v2.1)。
- GPT-5.5 (xhigh):BenchLeader Index 64.6 → 64.1。
- Muse Wonder:BenchLeader Index 63.5 → 63.0。
- GPT-5.5 (xhigh):1 项分数修订。
- GPT-5.5 (xhigh):1 项新结果(MirrorCode)。
- Muse Wonder:1 项新结果(Blueprint-Bench 2)。
- Muse Wonder:BenchLeader Index 64.3 → 63.5。
- Muse Wonder:5 项分数修订。
- GPT-5.5 (xhigh):1 项分数修订。
相关对比
- GPT-5.5 vs Claude Fable 5.2
- GPT-5.5 vs Gemini 4 Carbon
- GPT-5.5 vs Claude Opus 5.5
- Muse Wonder vs Claude Fable 5.2
- Muse Wonder vs Gemini 4 Carbon
- Muse Wonder vs Claude Opus 5.5
- Muse Wonder vs GPT-6 Astra
- GPT-5.4 vs Muse Wonder
排行榜: 综合最佳大模型 · 最适合智能体的大模型 · 便宜好用的大模型
GPT-5.5 vs Muse Wonder:常见问题
- GPT-5.5 比 Muse Wonder 更好吗?
- GPT-5.5 (xhigh) 与 Muse Wonder 的质量不相上下(64.1 比 64.4,在 ±4.9 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。
- GPT-5.5 和 Muse Wonder 哪个更便宜?价格会变吗?
- 目前 Muse Wonder 更便宜:每百万 token $8.00 比 $11.25(按每 1 个输出 token 对应 3 个输入 token 混合计算)。两者均未公布价格调整。
- GPT-5.5 和 Muse Wonder 哪个更快?
- GPT-5.5 输出更快(输出 81 比 70 token/秒,Artificial Analysis 7 日中位数)。
- 智能体和工具调用用 GPT-5.5 还是 Muse Wonder 更好?
- Muse Wonder 在智能体任务方面得分更高(类别得分 76 比 62,50 为平均水平)。
- 处理长文档哪个更好?
- 两者都约为 1.1M token(GPT-5.5 为 1,050,000,Muse Wonder 为 1,048,576)。
更多问题(3)
- 哪个延迟更低?
- Muse Wonder 先开始回答:据 Artificial Analysis 测量,首个回答 token 的等待时间为 3.3 秒比 38.3 秒。这主要取决于推理强度:设置越高,回答前思考得越久。
- 第三方基准测试对 GPT-5.5 和 Muse Wonder 的看法一致吗?
- 在两者都有结果的 3 项基准测试中,GPT-5.5 领先 1 项,Muse Wonder 领先 2 项。所有同时评测两者的综合评分都认为 Muse Wonder 更强。
- Muse Wonder 是什么时候发布的?
- Muse Wonder 于 2026年10月12日 发布。