Muse Wonder 对决 Intern S2：1,048,576 个 Token 对 256K，且没有共同的标尺

Intern-S2-397B and Muse Wonder have never been measured against each other by anyone. That is not a gap in the research — it is a structural fact about how each model came to exist. I​nternLM published Intern-S2-397B on September 13, 2026 as an Apache-2.0 open-weights checkpoint for scientific intelligence and long-horizon agents, benchmarked entirely by its own makers, with no third-party score at all. Meta Superintelligence Labs began selling Muse Wonder on October 12, 2026 through the Meta Model API and Muse Code, and it has exactly one independent evaluator's row. So everything below requires labelling which side of the fence each number sits on, and the two models disagree about something more basic than benchmark scores: what a context window is for. Muse Wonder's 1,048,576 tokens are a flat, priced, single-response budget. Intern-S2-397B's are split — 256K for text reasoning and 64K for multimodal input — on a checkpoint you download rather than call.

这个对比中有价值的地方不在于哪个模型胜出，而在于：其中一个是可在你自己的边界内运行的、用于科学文档工作的工具，而另一个则是按固定费率租用、拥有超大便用窗口的通用型选手。这是两种不同的购买。

每个模型实际上是什么

Intern-S2-397B is Shanghai AI Laboratory's I​nternLM flagship, released September 13, 2026 under Apache-2.0. The name carries 397B; the model card says 403 billion total parameters, and that difference is the kind of inconsistency a checkpoint built in public accumulates. Architecturally it is a standard mixture-of-experts transformer — 60 layers, 512 experts with 10 active per token — and its headline claim is a pre-training paradigm that reads raw pages of scientific literature, figures, layout, symbolic notation and prose together, rather than parsing the text out first. Around that it scales reinforcement learning across more than twenty scientific domains and adds long-horizon agent training in sandboxed environments. It takes text, image and time-series input, produces forecasts from the time-series path, serves on LMDeploy, vLLM and SGLang, supports tool calling, and thinks by default unless you pass enable_thinking=False per request. In BF16 the checkpoint is roughly 807 GB, so self-hosting means a serious multi-GPU node.

Muse Wonder 是 Meta Superintelligence Labs 于 2026 年 10 月 12 日发布的前沿成果，以双检查点系列的形式公布。只有 muse-wonder-1.0 提供按 token 计费的端点，位于 Meta Model API 上以及 Muse Code 内；得分更高的配置 Muse Wonder Full 仅通过 Muse Code 订阅销售，没有公开的价目表。可调用的检查点接受文本、图像、语音和视频输入，返回文本，具有 1,048,576 token 的上下文窗口，单次响应上限为 943,718 token，定价为每百万输入 token 4.00 美元、缓存 0.20 美元、输出 20.00 美元，并且强制运行推理，其努力程度阶梯从 minimal 到 max，默认 medium。没有权重，没有许可证，也没有在端点变更后仍可继续运行的版本。

这是它们之间第一个真正的区别，而且它不是基准测试中的一行。一个是文件。另一个是契约。

上下文窗口，这两个模型对它的含义理解不同。

这正是规格表对比最容易产生误导的地方，因为这两款模型通常都被描述为长上下文。

• 文本上下文 —— Muse Wonder 单窗口支持 1,048,576 tokens；Intern-S2-397B 以 256K 进行文本推理

• 多模态上下文 —— Muse Wonder 的完整窗口涵盖其图像、语音和视频输入；Intern-S2-397B 则拥有独立的 64K 多模态上下文

• 单次响应最大输出——Muse Wonder 943,718 tokens；Intern-S2-397B 未公布可比数值

• 输入类型 — Muse Wonder 的文本、图像、语音、视频；Intern-S2-397B 的文本、图像、时间序列

• 时间序列预测 — Muse Wonder 不支持；Intern-S2-397B 支持，目前仅通过 LMDeploy 接入

• 费率 — Muse Wonder 每百万 token 输入 $4.00，缓存 $0.20，输出 $20.00；Intern-S2-397B 未公布每 token 费率，因为其分发模式是下载

预测这一行在另一侧没有对应项，而且它不是营销卖点——它是该模型以现有形态存在的原因。一个摄入时间序列信号并生成预测的模型，所做的事情是文本模型无论窗口多大都无法被要求完成的。如果这正是你的工作负载，那么比较早已结束。

对其他人来说，真正相关的问题是到底什么才合适。以统一费率提供的 1,048,576 token 窗口，和你在自己拥有的硬件上运行的 256K 文本窗口，是两种不同的产品，而这种差异恰恰会体现在那些让长上下文变得有意思的工作负载中——提示词里放进一个代码库、一批论文语料，或者一个会保留历史记录的长时间智能体会话。

这些证据基础，它们并不接触

两个模型公布的数值无法放在同一坐标轴上，而其中的原因值得直言不讳地说明。

Intern-S2-397B's benchmark card is I​nternLM's own, run through OpenCompass, VLMEvalKit and AgentCompass by the team that built the model, with no independent reproduction. Its columns are Qwen3.5-397B-A17B, D​eepSeek V4 Pro, Kimi K2.7-Code, GLM-5.2, GPT-5.5, Gemini 3.1 Pro and Claude Opus 4.8 — no model from M​eta, and no Muse Wonder, so the vendor's own table does not contain a single Muse comparison. and any "Intern-S2 versus Muse Wonder" figure circulating anywhere is an extrapolation across two unrelated tables.

What that card does publish, all of it I​nternLM-reported: 89.77 on MMLU Pro, 93.56 on HMMT-2026, 81.68 on MMMU Pro, 68.54 on SWE-bench-Pro, 64.04 on TerminalBench 2.1, and on the scientific sets 55.71 on Biology-Instructions, 63.28 on SciReasoner 1.5 and 53.95 on Mol-Instructions. Read that as a portrait: strong on knowledge, maths and multimodal reasoning, leading on software engineering, and twenty points behind Claude Opus 4.8 on terminal work — the exact axis a production agent spends its day on.

Muse Wonder's evidence is the inverse shape. M​eta's launch table covers both checkpoints at maximum reasoning and is built largely from sustained-agent benchmarks — DeepSWE 1.1, SWE-Marathon, Terminal-Bench 4.0-AA, OSWorld V2.1 — all of it vendor-reported, in M​eta's harness, unreproduced. Independent commentary has repeated the strongest rows without the caveat, which is how a vendor harness becomes a fact in public. The one genuinely independent row is Artificial Analysis' Intelligence Index at 52 at maximum effort, ninth of more than 200 models, with about $4.52 of measured cost per completed index task and roughly 130 million output tokens consumed against a board median near 85 million.

所以：一个模型的优势，是由其开发方在没有任何第三方重跑过的科学基准上宣称的。另一个模型的优势，则是由其开发方在智能体基准上同样宣称的——同样没有任何第三方重跑过。没有任何人将二者进行过比较。对此，一个诚实的页面唯一能做的，就是把它明说出来。

比较在何处由价格决定，何处又不由价格决定

Intern-S2-397B has no rate card. That is the whole pricing section, and it is a real finding rather than a missing value: you either self-host roughly 807 GB of BF16 weights on hardware you own, or you register for a token on I​nternLM's own API and live within whatever quota is granted. There is no per-token number to put beside Muse Wonder's $4.00 and $20.00, and no invoice to compare with a pay-per-token bill.

这件事对决策的影响比“免费还是付费”更微妙。下载来的检查点把可变成本变成了资本成本，也把供应商关系变成了你拥有的制品。当你的数据不能离开自己的边界、你的工作负载稳定到足以证明投入 GPU 的合理性，或者可复现性比某个基准分数更重要时，这非常有价值。但如果你的流量呈尖峰式波动、你的团队没有服务栈，或者你需要模型自己变好而你什么都不用做，那它的价值就很小。

Neither model is served by us, and it is worth saying so plainly rather than implying otherwise: Intern-S2-397B is a brand-new Apache-2.0 checkpoint with no routing coverage, and Muse Wonder is on M​eta's API and inside Muse Code with no third-party serving we can verify. What a router does help with is the half of this that is callable. OrcaRouter carries more than 200 models behind one key at provider list price with 0% markup — no middleman delta, so a vendor price cut is live the same day — including M​eta's own Muse Spark 1.2 and Muse Spark 1.1, so the M​eta models you can reach today sit next to everything else on the same credential. If your production traffic lands on a routed model and your scientific batch work runs on Intern-S2-397B somewhere you control, that seam is a routing decision rather than a second integration.

谁应该选哪个

当工作内容是阅读科学材料时——图表密集的论文、分子图、扫描表格、基于时间序列信号的预测，或者一个必须持续推进研究任务的智能体——就选 Intern-S2-397B。Apache-2.0 许可证意味着你可以在专有数据上对它进行微调，并把结果保留在自己的边界之内，而这正是任何价目表都无法体现的比较部分。要为硬件做好预算，并预计几个月内不会有独立评分榜——该代码库才发布几周，尚无第三方评测。

Take Muse Wonder when the work is general, long and agentic, and when you would rather rent than own: a 1,048,576-token window at a flat rate with no step, a 943,718-token response ceiling that nothing in Intern-S2's published material answers, mandatory reasoning for hard multi-step tasks, and a pay-per-token bill you can put in a spreadsheet today. The caveat is the same one that applies to every row M​eta published: two days of independent measurement is two days, and one evaluator is one evaluator.

需要两者兼备的团队，应把二者之间的边界当作路由问题，而不是迁移问题。把常规流量跑在你能调用的模型上，把科研工作留在你能掌握的检查点上，并且在相信供应商关于 Intern-S2-397B 终端性能的数字之前，先在这个模型上重新跑一遍你自己的评估——因为供应商自己的表格里，它是最不给自己长脸的一行。