Gemini 4 Hydrogen · Math
Gemini 4 Hydrogen for math: our test runs
Gemini 4 Hydrogen ran our 5 math prompts in llmwise, through the same pipeline your messages take. Here's every reply as it came, whether it passed, what it cost and what it counts as on Pro, next to the other models.
Based on 5 of our test runs on , through OpenRouter with the app's own prompt and settings.
Short answer
In our test runs on November 17, 2026, Gemini 4 Hydrogen passed 5 of 5 of our math prompts (both hard ones): tied 1st of 27 models. Each reply counted as 1 message on Pro, where it has 125 a month, and cost $0.0023 to run on average.
Prompt by prompt
Each of the 5 math prompts, and how Gemini 4 Hydrogen's reply did.
| Prompt | Result | Cost | Time |
|---|---|---|---|
| A discount, then sales taxEveryday | Passed: Final answer 66: right. | $0.0012 | 2.4 s |
| Pens at 3 for $4Everyday | Passed: Final answer 3 packs of 3 pens and 1 single pen, costing 13.50: right. | $0.0030 | 4.2 s |
| Compound interest over three yearsEveryday | Passed: Final answer 315.25: right. | $0.0022 | 2.9 s |
| Four-digit numbers whose digits sum to 9Hard | Passed: Final answer 165: right. | $0.0032 | 5.3 s |
| The highest of three dice is a 5Hard | Passed: Final answer 61/216: right. | $0.0019 | 2.9 s |
Every math reply from Gemini 4 Hydrogen
A discount, then sales tax
An everyday prompt: “A discount, then sales tax”, in full.
Passed: Final answer 66: right.
Original price: $80 25% discount: $80 × 0.25 = $20 Discounted price: $80 − $20 = $60 10% sales tax: $60 × 0.10 = $6 Final price: $60 + $6 = $66 Final answer: $66
649 tokens in, 197 out (112 of them reasoning) · 2.4 s · $0.0012 · 1 message on Pro · answered by google/gemini-4-hydrogen via Google AI Studio ·
Pens at 3 for $4
An everyday prompt: “Pens at 3 for $4”, in full.
Passed: Final answer 3 packs of 3 pens and 1 single pen, costing 13.50: right.
A 3-pen pack costs $4.00 ($1.33 per pen), which is cheaper than buying single pens at $1.50 each. To minimize the cost for 10 pens, buy as many 3-pen packs as possible without going over 10: * **3 packs of 3 pens** = 9 pens for $3 \times \$4.00 = \$12.00$ * **1 single pen** = 1 pen for $\$1.50$ * **Total** = 10 pens for $\$12.00 + \$1.50 = \$13.50$ (Any fewer 3-pen packs replaces a $4.00 pack with 3 single pens costing $4.50, increasing the total.) Final answer: 3 packs of 3 pens and 1 single pen, costing $13.50
650 tokens in, 665 out (461 of them reasoning) · 4.2 s · $0.0030 · 1 message on Pro · answered by google/gemini-4-hydrogen via Google AI Studio ·
Compound interest over three years
An everyday prompt: “Compound interest over three years”, in full.
Passed: Final answer 315.25: right.
Total amount after 3 years: $$A = 2000 \times (1 + 0.05)^3 = 2000 \times 1.157625 = \$2,315.25$$ Interest earned: $$\$2,315.25 - \$2,000 = \$315.25$$ Final answer: $315.25
648 tokens in, 449 out (347 of them reasoning) · 2.9 s · $0.0022 · 1 message on Pro · answered by google/gemini-4-hydrogen via Google AI Studio ·
Four-digit numbers whose digits sum to 9
A hard prompt: “Four-digit numbers whose digits sum to 9”, in full.
Passed: Final answer 165: right.
Let the four-digit integer be $d_1 d_2 d_3 d_4$, where $d_1 \ge 1$ and $d_2, d_3, d_4 \ge 0$. We need to find the number of integer solutions to: $$d_1 + d_2 + d_3 + d_4 = 9$$ Substitute $d_1' = d_1 - 1$ so that all variables are non-negative integers ($d_1' \ge 0$): $$d_1' + d_2 + d_3 + d_4 = 8$$ Note that since the sum is $8$, no digit can exceed $9$ (meaning $d_1 \le 9$ and $d_2, d_3, d_4 \le 9$ are automatically satisfied). Using the stars and bars method, the number of non-negative integer solutions is: $$\binom{8 + 4 - 1}{4 - 1} = \binom{11}{3} = \frac{11 \times 10 \times 9}{3 \times 2 \times 1} = 165$$ Final answer: 165623 tokens in, 725 out (447 of them reasoning) · 5.3 s · $0.0032 · 1 message on Pro · answered by google/gemini-4-hydrogen via Google AI Studio ·
The highest of three dice is a 5
A hard prompt: “The highest of three dice is a 5”, in full.
Passed: Final answer 61/216: right.
Total possible outcomes when rolling three fair six-sided dice: $6^3 = 216$. - Outcomes where every die is $5$ or less: $5^3 = 125$. - Outcomes where every die is $4$ or less: $4^3 = 64$. Subtracting the two gives the outcomes where the highest number is exactly $5$: $$125 - 64 = 61$$ Since $61$ is prime and does not divide $216$, the fraction $\frac{61}{216}$ is already in lowest terms. Final answer: 61/216640 tokens in, 372 out (224 of them reasoning) · 2.9 s · $0.0019 · 1 message on Pro · answered by google/gemini-4-hydrogen via Google AI Studio ·
How it compares on math
Gemini 4 Hydrogen beside the job's picks among every model. 27 models share the hard-problems pick, Gemini 4 Hydrogen among them.
| Model | Passed | On Pro | Cost per reply |
|---|---|---|---|
| GPT-6.1 TerraOur pick: hard problems (shared), best value | 5 of 5 | 250 a month on Pro | $0.0005 |
| GPT-6 LunaOur pick: hard problems (shared), everyday | 5 of 5 | 60 a day on Pro | $0.0001 |
| Gemini 4 HydrogenOur pick: hard problems (shared) | 5 of 5 | 125 a month on Pro | $0.0023 |
Every limit is published. Paid plans also have a monthly fair-use limit on AI cost: Plus $3.75, Pro $7.50, Max $20, Ultra $42, Studio $85. Using every message on your plan at typical sizes stays under it; very large messages and heavy research use it faster. Every limit, explained.
Gemini 4 Hydrogen next to each model on math
Gemini 4 Hydrogen against each model on the same 5 math prompts. One run each, through OpenRouter: a wait depends on the provider and the load that day, so a lead under 10% counts as close.
Against Claude Fable 5.2: Gemini 4 Hydrogen answered within 10% of its time (2.9 s to 2.8 s), cost 2.7× less, and passed 5 of 5 to its 5.
Against Claude Fable 5.1: Gemini 4 Hydrogen answered 1.7× later (2.9 s to 1.7 s), cost 3.9× less, and passed 5 of 5 to its 5.
Against Claude Opus 5.5: Gemini 4 Hydrogen answered 1.1× later (2.9 s to 2.7 s), cost 1.9× less, and passed 5 of 5 to its 5.
Against Claude Sonnet 5.5: Gemini 4 Hydrogen answered 1.7× later (2.9 s to 1.8 s), cost 1.3× more, and passed 5 of 5 to its 5.
Against Claude Sonnet 5: Gemini 4 Hydrogen answered 1.2× later (2.9 s to 2.5 s), cost 1.8× less, and passed 5 of 5 to its 5.
Against Claude Haiku 5.5: Gemini 4 Hydrogen answered 1.8× later (2.9 s to 1.6 s), cost 15.3× more, and passed 5 of 5 to its 5.
Against Claude Haiku 4.5: Gemini 4 Hydrogen answered 1.4× later (2.9 s to 2.1 s), cost 1.3× more, and passed 5 of 5 to its 5.
Against GPT-6.2 Astra: Gemini 4 Hydrogen answered 1.1× later (2.9 s to 2.6 s), cost 3.3× less, and passed 5 of 5 to its 5.
Against GPT-6 Astra: Gemini 4 Hydrogen answered 1.3× sooner (2.9 s to 3.9 s), cost 2.2× less, and passed 5 of 5 to its 5.
Against GPT-6.2 Sol: Gemini 4 Hydrogen answered 1.5× later (2.9 s to 2.0 s), cost 1.2× more, and passed 5 of 5 to its 5.
Against GPT-6.1 Sol: Gemini 4 Hydrogen answered 3.7× sooner (2.9 s to 10.9 s), cost 2.2× more, and passed 5 of 5 to its 5.
Against GPT-6 Sol: Gemini 4 Hydrogen answered 1.2× later (2.9 s to 2.5 s), cost 2.1× more, and passed 5 of 5 to its 5.
Against GPT-6.1 Terra: Gemini 4 Hydrogen answered 1.3× later (2.9 s to 2.2 s), cost 4.5× more, and passed 5 of 5 to its 5.
Against GPT-6 Luna: Gemini 4 Hydrogen answered 1.1× sooner (2.9 s to 3.3 s), cost 43.6× more, and passed 5 of 5 to its 5.
Against Gemini 4 Carbon: Gemini 4 Hydrogen answered 2.1× sooner (2.9 s to 6.1 s), cost 1.1× less, and passed 5 of 5 to its 5.
Against Gemini 4 Argon: Gemini 4 Hydrogen answered 2.4× sooner (2.9 s to 7.1 s), cost 1.6× more, and passed 5 of 5 to its 5.
Against Gemini 3.1 Pro (preview): Gemini 4 Hydrogen answered 2.2× sooner (2.9 s to 6.5 s), cost 2.1× less, and passed 5 of 5 to its 5.
Against Gemini 3.8 Flash: Gemini 4 Hydrogen answered 1.4× sooner (2.9 s to 4.0 s), cost 2.6× more, and passed 5 of 5 to its 5.
Against DeepSeek V4.1 Flash: Gemini 4 Hydrogen answered 4.2× later (2.9 s to 0.7 s), cost 7.9× more, and passed 5 of 5 to its 5.
Against DeepSeek V4 Pro: Gemini 4 Hydrogen answered 1.5× sooner (2.9 s to 4.4 s), cost 1.6× more, and passed 5 of 5 to its 5.
Against Grok 4.7: Gemini 4 Hydrogen answered 3.0× sooner (2.9 s to 8.8 s), cost 3.5× less, and passed 5 of 5 to its 5.
Against Kimi K3.1 Pro: Gemini 4 Hydrogen answered 1.1× sooner (2.9 s to 3.4 s), cost 1.2× less, and passed 5 of 5 to its 5.
Against Kimi K3: Gemini 4 Hydrogen answered 1.7× sooner (2.9 s to 5.2 s), cost 1.7× less, and passed 5 of 5 to its 5.
Against GLM 5.3: Gemini 4 Hydrogen answered 2.4× later (2.9 s to 1.2 s), cost 3.1× more, and passed 5 of 5 to its 5.
Against GLM 5.3 Flash: Gemini 4 Hydrogen answered 2.9× later (2.9 s to 1.0 s), cost 13.9× more, and passed 5 of 5 to its 5.
Against Mistral Large 4: Gemini 4 Hydrogen answered 2.2× sooner (2.9 s to 6.4 s), cost 2.1× more, and passed 5 of 5 to its 5.
How these runs were done
Final answer. Automatic. The reply's last “Final answer:” line must hold the right value.
Gemini 4 Hydrogen, and math, elsewhere
- Gemini 4 Hydrogen: price, limits and messages on every plan
- The best AI for math: our picks among every model
- Gemini for math
- Gemini 4 Hydrogen for coding: our test runs
- Gemini 4 Hydrogen for writing: our test runs
- Gemini 4 Hydrogen for data analysis: our test runs
- Analyze a CSV with code: the prompt, and its price
- AI prompts for students, tested on four models
- AI prompts for teachers, tested with every reply
- Our test runs: 50 prompts on every model
Questions
Is Gemini 4 Hydrogen good for math?
In our test runs it passed 5 of 5 math prompts, tied 1st of the 27 models in llmwise. Every reply is on this page, so you can judge them yourself.
How many of my messages does a math reply from Gemini 4 Hydrogen use?
1 message each on Pro, where it has 125 a month on Pro. The price of a message is fixed and shown before you send it, however long the reply.
How were these runs done?
The same way for every model: each prompt sent through llmwise's own pipeline, each reply checked the same way. The methods page has every prompt and how each is scored.
Claude, GPT, Gemini, DeepSeek, Grok, Kimi, GLM, and Mistral, in one chat.
See what a message costs before you send it. Every plan is month to month: cancel in two clicks. Sign in with an email link, no password.