Muse Spark 對決 Gemini 4 Argon：12 月 1 日價格翻倍

Almost every Muse Spark versus G​emini 4 Argon comparison you can find today compares $1.25 against $2.00 per million input tokens, and that comparison expires in six weeks. G​oogle's own pricing page prices G​emini 4 Argon at $2.00 in and $10.00 out with cached input at $0.10 on an introductory basis "through November 30, 2026"; from December 1, 2026 the same model is listed at $4.00 in, $20.00 out and $0.20 cached. M​eta's Muse Spark family has not moved off $1.25 in and $4.25 out across Muse Spark 1.1, 1.2 and 1.3. So the interesting question about this matchup is not which model is smarter in October — it is what the arithmetic looks like on the first of December, and whether whatever you build on G​emini 4 Argon this month survives that date.

兩種模型，兩種截然不同的發表模式

G​emini 4 Argon is G​oogle's newest frontier model and it went generally available on October 13, 2026 — the changelog entry is a single line, and the developer documentation is dated the same week. Artificial Analysis' listing carries a September 2026 release note, which we read as a pre-GA or preview origin rather than a second launch; we could not find a formal preview announcement to confirm that, so the GA date is the one we treat as solid. G​oogle's model page marks it "Stable".

Muse Spark 1.3 is the current checkpoint of M​eta Superintelligence Labs' Muse Spark line, released September 2, 2026, with its "max" reasoning level opened to developers on September 4. The unversioned "Muse Spark" name refers to the original April 2026 model in the same family; version numbers are doing real work here, and 1.3 is the one to compare.

獨立計分板

這兩份榜單都來自 Artificial Analysis，而且兩者都測量高算力配置，因此這是少數能在該指數本身進行推理模型對推理模型、同基準比較的對決之一。本節所有內容都是 Artificial Analysis 的測量結果，而非廠商宣稱。

• Intelligence Index — G​emini 4 Argon (High): 53, rank 8 of 217. Muse Spark 1.3 (max): 48, rank 24 of 217.

• Cost per index task — G​emini 4 Argon: $1.99. Muse Spark 1.3: $1.60.

• Output speed — G​emini 4 Argon: not measured; the listing shows no figure. Muse Spark 1.3: 121.9 tokens per second, ranked 43 of 186.

• Verbosity — G​emini 4 Argon: 110M output tokens during the index. Muse Spark 1.3: 170M. Argon is the more concise of the two.

• 依實測的標價 — Argon 入門價為 $2.00 / $10.00；Muse Spark 1.3 為 $1.25 / $4.25，快取讀取為 $0.15。

五分的智能差距確實存在，但不算大。成本差距才是會反轉的那一項，而且反轉得很徹底：在初期費率下，Argon 每完成一項任務的成本約高出 24%；到了 12 月費率，同樣針對輸入與輸出定價的比較，輸入端大約翻倍，輸出端也翻倍，因此每項任務的溢價不再只是邊際之差。這是這項比較中唯一最具決策相關性的事實，而它並未出現在任何上市報導中。

每個實際上會接受什麼

此處，兩份正式紀錄來源彼此不一致，值得把這項分歧呈現出來，而不是選邊站。

G​oogle's own model page for G​emini 4 Argon lists text, image, video, audio and PDF as inputs with text output and thinking effort at low, medium or high, defaulting to medium. Artificial Analysis' summary sentence for the same model says it "supports text and image input" and outputs text. We checked both because that gap is exactly the kind of thing that gets copied forward; the vendor's own page is the broader and more specific list, and it is the one to test against. Treat the vendor list as the claim and verify it on your own files.

Muse Spark 1.3 就帳面規格而言是較狹窄的模型：輸入文字、圖像和影片，輸出文字；在文件記載的模態列中沒有音訊或 PDF 路徑，而推理階梯則可一路延伸到 max。

• Inputs — G​emini 4 Argon: text, image, video, audio, PDF per G​oogle; text and image per the independent listing. Muse Spark 1.3: text, image, video.

• 輸出 — 僅限文字，兩者皆是。

• 上下文視窗 — 兩者均為 1,048,576 個 token，Google 將其描述為一個由輸入、思考和輸出共享的統一視窗。

• Max output — G​emini 4 Argon: 65,536 tokens on default synchronous calls, extensible toward the full window with long decode. M​eta does not publish a max-output figure for Muse Spark 1.3 that we could verify.

• Reasoning control — Argon: low / medium / high, no off switch. Muse Spark 1.3: minimal through max, and M​eta's tooling notes reasoning cannot be turned off either.

供應商索賠，留在供應商這一側的界線內

兩家公司都沒有公布可相比較的表格，所以這是一份主張清單，而不是計分板，而且其中沒有任何內容是由我們複製的。

G​oogle's published figures for G​emini 4 Argon run 77.9% on DeepSWE v1.1, 57.4% on Terminal-bench 4.0, 69.2% on the OSWorld 2.0 offline subset, 51.3% on AutomationBench, 68.9% on the Vals Index, 71.6% on Chartography and 91.7% on LVBench, among others. M​eta's published figures for Muse Spark 1.3 centre on DeepSWE v1.1 at 75.4, OSWorld 2.0 at 66.9, Terminal-Bench 2.1 at 76.4 with the Terminus 2 agent, MCP-Atlas at 89.2 and GDPval-AA v2 at 1,754. Note where the two overlap and where they do not: DeepSWE is shared and close, OSWorld is shared and about two points apart on different revisions, and Terminal-Bench is reported by M​eta on an older version with a named agent harness. Subtracting across those differences is not arithmetic, it is fortune-telling.

One independent signal worth carrying alongside the vendor rows: LMArena's text leaderboard currently places a G​emini 4 Argon configuration first overall at 1524 Elo, marked preliminary. Muse Spark 1.3 has no entry on that board. Preliminary or not, that is the strongest evidence in the record that Argon's five-point index lead understates its standing with human voters.

決定它比基準測試更快的工程細節

• Sampling parameters are ignored — G​oogle's documentation states that temperature, top_p and top_k have no effect on G​emini 4 Argon, and that explicit caching is not supported, leaving implicit caching only. If your stack tunes temperature, that knob silently stops working rather than erroring. Muse Spark 1.3 exposes a reasoning-effort parameter but no equivalent published restriction on sampling.

• 逾時 — G​oogle 建議此模型的用戶端逾時至少為十五分鐘。如果你使用的是 60 秒的閘道預設值，你會看到看似模型錯誤、但實際上並非如此的失敗。

• 對話狀態 — Argon 使用伺服器端互動識別碼來處理多輪狀態；Muse Spark 系列的文件則是圍繞標準訊息陣列模式。在兩者之間移植並非尋找取代即可完成。

• 快取讀取——Muse Spark 1.3 的快取輸入價格為 $0.15，相較於標準價 $1.25，等於 88% 折扣。Argon 的快取輸入為 $0.10，相較於初期價 $2.00，之後會漲至 $0.20，相較於 $4.00。在大量重複使用的漫長 agent 迴圈中，這是最關鍵的費用項目，也是十二月之後兩者仍能保持接近的少數地方之一。

OrcaRouter 適合的地方，以及不適合的地方

Being precise about our own coverage: OrcaRouter routes Muse Spark 1.2 and Muse Spark 1.1 at Meta's list price with 0% markup passed through, alongside 200+ other models on one API with automatic failover and a routing DSL for splitting traffic between them. Muse Spark 1.3 and G​emini 4 Argon are both absent from our catalogue today — Argon is reachable through G​oogle's own API and several third-party platforms, and we are not one of them. So the honest framing is not "run both here". It is that the Muse Spark side of this comparison is available to you on a key you may already hold, which makes a cost test against Argon on your own prompts a same-week exercise rather than a procurement one, and that M​eta's pricing has been static across three checkpoints while G​oogle's has a published expiry date.

十二月前該做什麼

If you are already building on G​emini 4 Argon, the useful thing to do this month is not a benchmark run — it is a cost model at $4.00 and $20.00, because that is the price that will apply to everything you ship and leave running. If the answer at that price still works, Argon is the better model on the current evidence: higher index, more concise, broader documented input list, and the only one of the two with a top-of-board human-preference placement. If it does not, the substitution to evaluate is Muse Spark 1.3 at a flat $1.25 / $4.25, which trades five index points for a price that has not moved in three releases and roughly three times the output speed. The one thing we would not do is treat October's advertised rates as the rates — in this matchup, the number in the title is the one with an end date.

數字無法告訴你的是，這一切在實際運作中是否出了問題：針對此類模型有記錄的 AI 事件與代理故障，都收錄在the OrcaRouter AI Incident Archive，其中每筆條目都附有自己的來源、嚴重程度、可信度等級與爭議標記。