Gemini 4 Hydrogen vs Muse Spark 1.3
Gemini 4 Hydrogen scores higher on the Models at Work leaderboard (78 vs 69 out of 100). On independent tests alone, Gemini 4 Hydrogen is ahead (96 vs 82). Muse Spark 1.3 is cheaper for a typical mix of reading and writing: $0.78 per million tokens against $3 on Gemini 4 Hydrogen, which is 3.8 times as much (at least one figure is an Artificial Analysis estimate, not a list price).
| Gemini 4 Hydrogen · Google | Muse Spark 1.3 · Meta | |
|---|---|---|
| Leaderboard rank | #2 | #12 |
| Score (0–100) | 78 | 69 |
| Kind of work | Everyday default | Everyday default |
| Price per 1M tokens | $1.50 to read · $7.50 to write | $0.78 for a typical mix (estimate) |
| Reads at once | 1M tokens (about 750,000 words) | Not verified |
| Where you can get it | Gemini Enterprise Agent Platform (Google Cloud), Google AI Studio, Gemini for business, Gemini Enterprise, Gemini app | Gemini Enterprise Agent Platform (Google Cloud), preview |
| Can a company host it itself | No | Not verified |
| Artificial Analysis Intelligence Index | 54 | Not measured |
| Vals Finance Index | 66.14% (rank 2) | Not measured |
| Vals Tax Agent Bench | 52.30% (rank 1) | Not measured |
| Vals Legal Research Bench | 53.85% (rank 6) | Not measured |
| Arena text score | Not measured | 1494 |
| DistressBench (Scale) | Not measured | 84.88 |
| Humanity's Last Exam, Diamond (Scale) | Not measured | 25.40 |
| Humanity's Sixth Sense (Scale) | Not measured | 37.40 |
| Vals Tax Agent Bench (Muse Spark 1.3 Max) | Not measured | 42.44% (rank 11) |
| Vals Legal Research Bench (Muse Spark 1.3 Max) | Not measured | 55.29% (rank 2) |
| Professional Reasoning Benchmark - Finance (Scale) | Not measured | 59.54 |
| Professional Reasoning Benchmark - Legal (Scale) | Not measured | 61.56 |
| Best for | Everyday drafting and summarising, Spreadsheet models and forecasts in Google Sheets, First-pass tax and finance research, checked by a person, Multi-step tasks across Gmail and Drive | Customer-facing chat, Sensitive support conversations, Teams already buying from Meta |
Cost of 1,000 jobs
| 1,000 of these | Gemini 4 Hydrogen | Muse Spark 1.3 |
|---|---|---|
| Support repliesthe customer message, the account notes and two help articles read; a 300-word reply written | $7.50 | No list price |
| Documents processeda two-page invoice or form read; the fields pulled out | $5.25 | No list price |
| Calls summariseda 40-minute call transcript read; a summary and next steps written | $20 | No list price |
| Contracts revieweda 40-page contract read against a checklist; a memo of issues written | $56 | No list price |
| Drafts writtena brief and one example read; a 600-word email or proposal section written | $8.25 | No list price |
Worked out from each vendor’s list price and a fixed size for each job. A product built on a model charges its own price on top. See what every model costs for the same jobs.
Choose Gemini 4 Hydrogen for
- Everyday drafting and summarising
- Spreadsheet models and forecasts in Google Sheets
- First-pass tax and finance research, checked by a person
- Multi-step tasks across Gmail and Drive
The everyday default here: second on Vals AI's test of finance work (66.1% against 67.1% for Gemini 4 Carbon) and first on its tax test, at 25% under Carbon's list price today and 62.5% under it from 1 December.
Caveats: Released 12 November 2026: its score rests on four independent tests and no reports yet from people who have run it for more than a few days. Google sells it as the successor to Gemini 3.8 Flash, but it costs twice what 3.8 Flash does until 1 January 2027, when Google's pricing page says 3.8 Flash rises to the same $1.50 in / $7.50 out per million tokens. On Vals AI's tax test it ranks first with 52.3% of questions right, so close to half its answers there were wrong: a person still checks the output. In Gemini Enterprise it is switched off until an administrator turns it on, per Google Cloud's release notes. Google does not say which Gemini app plans get it or whether it becomes the default in Gemini for business. Up from 9th to 2nd: Vals AI's finance, tax and legal research tests now count for every model, and Artificial Analysis now reads it at 54, up from 51. It is within three points of the models either side, which is a tie.
Choose Muse Spark 1.3 for
- Customer-facing chat
- Sensitive support conversations
- Teams already buying from Meta
Meta's earlier everyday model tops Scale's finance and legal reasoning tests (59.5 and 61.6) and is second on Vals AI's legal research test (55.3%), but it has no vendor list price on record and one confirmed place to buy, in preview.
Caveats: No vendor list price was found; the board uses Artificial Analysis's blended figure of $0.78 per million tokens from 10 October. Artificial Analysis dropped it when it rebuilt its index, so it has no current score there. On Google's cloud it is labelled preview, which usually means no service guarantee. Up from 21st to 12th because tests of professional work from Vals AI and Scale now count. The Vals AI readings are for its Max setting. Treat the rank as soft: one route to buy, in preview, and a price taken from a tester, not from Meta.
What people running them say
Gemini 4 Hydrogen: On the Hacker News (a developer forum) launch thread, 534 upvotes, most comments are about Google's model names. On substance: modeless reads Google's charts as 'a better choice than Sonnet in areas outside of coding'; onlyrealcuzzo calls early results 'disappointing', reporting it does more than asked; ComputerGuru notes it costs more than anyone pays for 3.8 Flash today. Developers on day one, none verified, and too little to score.
Questions people ask
Which is better, Gemini 4 Hydrogen or Muse Spark 1.3?
Gemini 4 Hydrogen scores higher on the Models at Work leaderboard (78 vs 69 out of 100). On independent tests alone, Gemini 4 Hydrogen is ahead (96 vs 82). Muse Spark 1.3 is cheaper for a typical mix of reading and writing: $0.78 per million tokens against $3 on Gemini 4 Hydrogen, which is 3.8 times as much (at least one figure is an Artificial Analysis estimate, not a list price).
When should I choose Gemini 4 Hydrogen over Muse Spark 1.3?
Choose Gemini 4 Hydrogen for everyday drafting and summarising, spreadsheet models and forecasts in google sheets, first-pass tax and finance research, checked by a person, multi-step tasks across gmail and drive. The everyday default here: second on Vals AI's test of finance work (66.1% against 67.1% for Gemini 4 Carbon) and first on its tax test, at 25% under Carbon's list price today and 62.5% under it from 1 December.
When should I choose Muse Spark 1.3 over Gemini 4 Hydrogen?
Choose Muse Spark 1.3 for customer-facing chat, sensitive support conversations, teams already buying from meta. Meta's earlier everyday model tops Scale's finance and legal reasoning tests (59.5 and 61.6) and is second on Vals AI's legal research test (55.3%), but it has no vendor list price on record and one confirmed place to buy, in preview.
Which is cheaper, Gemini 4 Hydrogen or Muse Spark 1.3?
Gemini 4 Hydrogen costs $1.50 per million tokens it reads (input) and $7.50 per million tokens it writes (output) on Google's list price (Google: Introducing Gemini 4 Hydrogen, read Nov 18, 2026). A token is about three-quarters of a word. Meta does not publish a simple list price for Muse Spark 1.3; Artificial Analysis estimates $0.78 per million tokens for a typical mix of three parts reading to one part writing.
Scores come from the Models at Work leaderboard: Score is 0 to 100 and computed, not typed. 40% is independent testing (Artificial Analysis, Arena, Scale, Epoch, Vals and others; each test is scaled against the best score on this board, and tests of real work, such as finished freelance projects or professional tasks, count double the exams). 30% is price: the vendor's list price for a typical mix of reading and writing, on a fixed scale from $0.05 to $60 per million tokens, so a model that costs a fifth as much gains real ground. 15% is what people report after running it, from Signals and linked threads. 15% is fit: how much text it can take in at once and where a business can get it (the products and clouds that carry it), with a small credit for open weights. A missing component drops out and the rest are reweighted. A model with no independent test yet is provisional and ranks below every measured one. Within three points is a tie. Vendor-published figures are labelled and never counted. Prices are vendor list prices where published; a typical mix assumes three parts reading to one part writing.