Skip to content
llmwise
Sign inStart free

Gemini 4 Argon · Math

Gemini 4 Argon for math: our test runs

Gemini 4 Argon 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.

Start freeSee pricing

Based on 5 of our test runs on , through OpenRouter with the app's own prompt and settings. Updated .

Short answer

In our test runs on October 15, 2026, Gemini 4 Argon passed 5 of 5 of our math prompts (both hard ones): tied 1st of 20 models. Each reply counted as 1 message on Pro, where it has 62 a month, and cost $0.0015 to run on average.

Prompt by prompt

Each of the 5 math prompts, and how Gemini 4 Argon's reply did.

Gemini 4 Argon on each math prompt
PromptResultCostTime
A discount, then sales taxEverydayPassed: Final answer 66: right.$0.00124.1 s
Pens at 3 for $4EverydayPassed: Final answer Buy three 3-packs and one single pen for 13.50: right.$0.00154.4 s
Compound interest over three yearsEverydayPassed: Final answer 315.25: right.$0.00144.2 s
Four-digit numbers whose digits sum to 9HardPassed: Final answer 165: right.$0.00204.5 s
The highest of three dice is a 5HardPassed: Final answer 61/216: right.$0.00164.9 s

Every math reply from Gemini 4 Argon

  1. A discount, then sales tax

    An everyday prompt: “A discount, then sales tax”, in full.

    Passed: Final answer 66: right.

    1. **Calculate the discount:** 25% of $80 is $80 × 0.25 = $20.
2. **Find the discounted price:** $80 - $20 = $60.
3. **Calculate the sales tax:** 10% of $60 is $60 × 0.10 = $6.
4. **Add the tax to the discounted price:** $60 + $6 = $66.

Final answer: $66

    649 tokens in, 116 out · 4.1 s · $0.0012 · 1 message on Pro · answered by google/gemini-4-argon via Google AI Studio ·

  2. Pens at 3 for $4

    An everyday prompt: “Pens at 3 for $4”, in full.

    Passed: Final answer Buy three 3-packs and one single pen for 13.50: right.

    To get 10 pens as cheaply as possible, maximize the 3-pack deal ($1.33 per pen) and buy the remainder as singles ($1.50 per pen):

- 3 packs of 3 pens (9 pens) = 3 × $4.00 = $12.00
- 1 single pen = $1.50
- Total for 10 pens = $12.00 + $1.50 = $13.50

(Buying 4 packs of 3 would give 12 pens for $16.00, which is more expensive and not *exactly* 10 pens.)

Final answer: Buy three 3-packs and one single pen for $13.50

    650 tokens in, 171 out · 4.4 s · $0.0015 · 1 message on Pro · answered by google/gemini-4-argon via Google AI Studio ·

  3. Compound interest over three years

    An everyday prompt: “Compound interest over three years”, in full.

    Passed: Final answer 315.25: right.

    Using the compound interest formula $A = P(1 + r)^t$:

* Principal ($P$) = $2,000
* Rate ($r$) = 0.05
* Time ($t$) = 3 years

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, 153 out · 4.2 s · $0.0014 · 1 message on Pro · answered by google/gemini-4-argon via Google AI Studio ·

  4. 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 represented by its digits $d_1, d_2, d_3, d_4$. We want to find the number of solutions to the equation:
$$d_1 + d_2 + d_3 + d_4 = 9$$
where $d_1 \ge 1$ and $d_2, d_3, d_4 \ge 0$. (Since the maximum sum is 9, no digit can exceed 9, so we do not need to worry about the upper bound of $\le 9$ for each digit.)

Let $d_1' = d_1 - 1$, so that $d_1' \ge 0$. Substituting this into the equation gives:
$$d_1' + d_2 + d_3 + d_4 = 8$$

Using the stars and bars method for $n = 8$ and $k = 4$, 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: 165

    623 tokens in, 284 out · 4.5 s · $0.0020 · 1 message on Pro · answered by google/gemini-4-argon via Google AI Studio ·

  5. 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.

    The total number of possible outcomes when rolling three six-sided dice is $6^3 = 216$.

For the highest number showing to be at most 5, all three dice must show a number from 1 to 5, giving $5^3 = 125$ outcomes.
For the highest number showing to be at most 4, all three dice must show a number from 1 to 4, giving $4^3 = 64$ outcomes.

The number of outcomes where the highest number is *exactly* 5 is the difference between these two:
$$125 - 64 = 61$$

Since 61 is a prime number, the fraction $\frac{61}{216}$ is already in its lowest terms.

Final answer: 61/216

    640 tokens in, 183 out · 4.9 s · $0.0016 · 1 message on Pro · answered by google/gemini-4-argon via Google AI Studio ·

How it compares on math

Gemini 4 Argon beside the job's picks among every model. 19 models share the hard-problems pick, Gemini 4 Argon among them.

Gemini 4 Argon beside other models on math
ModelPassedOn ProCost per reply
GLM 5.3Our pick: hard problems (shared), best value5 of 5250 a month on Pro$0.0004
Claude Haiku 5.5Our pick: hard problems (shared), everyday5 of 560 a day on Pro$0.0001
Gemini 4 ArgonOur pick: hard problems (shared)5 of 562 a month on Pro$0.0015
On Pro: Pro's count on each model. Cost: what OpenRouter charged us per reply, on average.

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 Argon next to each model on math

Gemini 4 Argon 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 5.1: Gemini 4 Argon answered within 10% of its time (4.4 s to 4.6 s), cost 7.5× less, and passed 5 of 5 to its 5.

  • Against Claude Opus 5.5: Gemini 4 Argon answered 1.1× later (4.4 s to 3.9 s), cost 3.8× less, and passed 5 of 5 to its 5.

  • Against Claude Sonnet 5.5: Gemini 4 Argon answered 2.6× later (4.4 s to 1.7 s), cost 1.6× less, and passed 5 of 5 to its 5.

  • Against Claude Sonnet 5: Gemini 4 Argon answered 1.1× later (4.4 s to 3.9 s), cost 2.1× less, and passed 5 of 5 to its 5.

  • Against Claude Haiku 5.5: Gemini 4 Argon answered 2.5× later (4.4 s to 1.7 s), cost 10.5× more, and passed 5 of 5 to its 5.

  • Against Claude Haiku 4.5: Gemini 4 Argon answered 2.0× later (4.4 s to 2.2 s), cost within 10% of it, and passed 5 of 5 to its 5.

  • Against GPT-6 Astra: Gemini 4 Argon answered 1.7× later (4.4 s to 2.6 s), cost 5.5× less, and passed 5 of 5 to its 5.

  • Against GPT-6.1 Sol: Gemini 4 Argon answered 2.5× later (4.4 s to 1.8 s), cost 1.8× more, and passed 5 of 5 to its 5.

  • Against GPT-6 Sol: Gemini 4 Argon answered 2.0× later (4.4 s to 2.2 s), cost 1.2× less, and passed 5 of 5 to its 5.

  • Against GPT-6 Luna: Gemini 4 Argon answered 2.0× later (4.4 s to 2.2 s), cost 15.7× more, and passed 5 of 5 to its 4. Only Gemini 4 Argon passed Pens at 3 for $4.

  • Against Gemini 3.1 Pro (preview): Gemini 4 Argon answered 1.9× sooner (4.4 s to 8.3 s), cost 6.5× less, and passed 5 of 5 to its 5.

  • Against Gemini 3.8 Flash: Gemini 4 Argon answered within 10% of its time (4.4 s to 4.7 s), cost within 10% of it, and passed 5 of 5 to its 5.

  • Against DeepSeek V4.1 Flash: Gemini 4 Argon answered 4.7× later (4.4 s to 0.9 s), cost 6.2× more, and passed 5 of 5 to its 5.

  • Against DeepSeek V4 Pro: Gemini 4 Argon answered 1.6× later (4.4 s to 2.7 s), cost 1.8× more, and passed 5 of 5 to its 5.

  • Against Grok 4.7: Gemini 4 Argon answered 2.7× sooner (4.4 s to 11.7 s), cost 4.7× less, and passed 5 of 5 to its 5.

  • Against Kimi K3: Gemini 4 Argon answered 1.2× sooner (4.4 s to 5.4 s), cost 2.4× less, and passed 5 of 5 to its 5.

  • Against GLM 5.3: Gemini 4 Argon answered 4.6× later (4.4 s to 0.9 s), cost 4.4× more, and passed 5 of 5 to its 5.

  • Against GLM 5.3 Flash: Gemini 4 Argon answered 1.6× later (4.4 s to 2.7 s), cost 10.3× more, and passed 5 of 5 to its 5.

  • Against Mistral Large 4: Gemini 4 Argon answered 1.2× sooner (4.4 s to 5.1 s), cost 1.2× less, 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.

How the runs were done, and every math prompt.

Gemini 4 Argon, and math, elsewhere

Questions

Is Gemini 4 Argon good for math?

In our test runs it passed 5 of 5 math prompts, tied 1st of the 20 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 Argon use?

1 message each on Pro, where it has 62 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. Free is 5 messages to try; sign in with an email link, no password or card.

Start freeSee pricing