Skip to content
llmwise
Sign inStart free

Grok 4.7 · Math

Grok 4.7 for math: our test runs

Grok 4.7 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 2, 2026, Grok 4.7 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 250 a month, and cost $0.0072 to run on average.

Prompt by prompt

Each of the 5 math prompts, and how Grok 4.7's reply did.

Grok 4.7 on each math prompt
PromptResultCostTime
A discount, then sales taxEverydayPassed: Final answer 66: right.$0.00334.8 s
Pens at 3 for $4EverydayPassed: Final answer 3 packs + 1 single ( 13.50): right.$0.011118.5 s
Compound interest over three yearsEverydayPassed: Final answer 315.25: right.$0.00518.0 s
Four-digit numbers whose digits sum to 9HardPassed: Final answer 165: right.$0.009315.1 s
The highest of three dice is a 5HardPassed: Final answer 61/216: right.$0.007411.7 s

Every math reply from Grok 4.7

  1. A discount, then sales tax

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

    Passed: Final answer 66: right.

    Discount: \(80 \times 0.25 = 20\), so sale price is \(80 - 20 = 60\).  
Tax: \(60 \times 0.10 = 6\), so final price is \(60 + 6 = 66\).

Final answer: $66

    1,635 tokens in, 290 out (225 of them reasoning) · 4.8 s · $0.0033 · 1 message on Pro · answered by x-ai/grok-4.7 via xAI ·

  2. Pens at 3 for $4

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

    Passed: Final answer 3 packs + 1 single ( 13.50): right.

    To buy exactly 10 pens, let \(x\) be the number of 3-packs (at \$4 each) and \(y\) the number of singles (at \$1.50 each), so \(3x + y = 10\) with \(x, y\) non-negative integers. The cost is \(4x + 1.5y\).

Feasible options:
- \(x=0\), \(y=10\): \$15.00
- \(x=1\), \(y=7\): \$14.50
- \(x=2\), \(y=4\): \$14.00
- \(x=3\), \(y=1\): \$13.50

Packs are cheaper per pen than singles, so maximizing packs (without exceeding 10) is optimal. Buying 4 packs yields 12 pens for \$16, which both exceeds 10 and costs more.

Final answer: 3 packs + 1 single ($13.50)

    1,637 tokens in, 1,596 out (1,385 of them reasoning) · 18.5 s · $0.0111 · 1 message on Pro · answered by x-ai/grok-4.7 via xAI ·

  3. Compound interest over three years

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

    Passed: Final answer 315.25: right.

    The balance after 3 years is \(2000 \times (1.05)^3 = 2000 \times 1.157625 = 2315.25\).

Interest earned is \(2315.25 - 2000 = 315.25\).

Final answer: 315.25

    1,637 tokens in, 649 out (584 of them reasoning) · 8.0 s · $0.0051 · 1 message on Pro · answered by x-ai/grok-4.7 via xAI ·

  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.

    The four-digit positive integers whose digits sum to 9 are the solutions of \(A + B + C + D = 9\) in which \(A \in \{1,\dots,9\}\) and \(B,C,D \in \{0,\dots,9\}\).

Because the target sum is only 9, the upper bounds of 9 are automatically satisfied. The change of variables \(A' = A - 1\) (so \(A' \ge 0\)) therefore converts the problem into the unrestricted equation
\[
A' + B + C + D = 8
\]
in non-negative integers. The number of solutions is
\[
\binom{8 + 4 - 1}{4 - 1} = \binom{11}{3} = 165.
\]

Final answer: 165

    1,614 tokens in, 1,305 out (1,127 of them reasoning) · 15.1 s · $0.0093 · 1 message on Pro · answered by x-ai/grok-4.7 via xAI ·

  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 outcomes is \(6^3 = 216\).

The outcomes in which every die shows at most 5 number \(5^3 = 125\). Among these, the outcomes in which every die shows at most 4 number \(4^3 = 64\). Subtracting yields the outcomes in which the maximum is exactly 5:
\[
125 - 64 = 61.
\]
Thus the desired probability is \(61/216\). (The fraction is already in lowest terms, since 61 is prime and does not divide 216.)

Final answer: 61/216

    1,629 tokens in, 972 out (845 of them reasoning) · 11.7 s · $0.0074 · 1 message on Pro · answered by x-ai/grok-4.7 via xAI ·

How it compares on math

Grok 4.7 beside the job's picks among every model. 19 models share the hard-problems pick, Grok 4.7 among them.

Grok 4.7 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
Grok 4.7Our pick: hard problems (shared)5 of 5250 a month on Pro$0.0072
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.

Grok 4.7 next to each model on math

Grok 4.7 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: Grok 4.7 answered 2.5× later (11.7 s to 4.6 s), cost 1.6× less, and passed 5 of 5 to its 5.

  • Against Claude Opus 5.5: Grok 4.7 answered 3.0× later (11.7 s to 3.9 s), cost 1.2× more, and passed 5 of 5 to its 5.

  • Against Claude Sonnet 5.5: Grok 4.7 answered 7.1× later (11.7 s to 1.7 s), cost 2.9× more, and passed 5 of 5 to its 5.

  • Against Claude Sonnet 5: Grok 4.7 answered 3.0× later (11.7 s to 3.9 s), cost 2.2× more, and passed 5 of 5 to its 5.

  • Against Claude Haiku 5.5: Grok 4.7 answered 6.7× later (11.7 s to 1.7 s), cost 49.2× more, and passed 5 of 5 to its 5.

  • Against Claude Haiku 4.5: Grok 4.7 answered 5.2× later (11.7 s to 2.2 s), cost 4.7× more, and passed 5 of 5 to its 5.

  • Against GPT-6 Astra: Grok 4.7 answered 4.5× later (11.7 s to 2.6 s), cost 1.2× less, and passed 5 of 5 to its 5.

  • Against GPT-6.1 Sol: Grok 4.7 answered 6.6× later (11.7 s to 1.8 s), cost 8.4× more, and passed 5 of 5 to its 5.

  • Against GPT-6 Sol: Grok 4.7 answered 5.4× later (11.7 s to 2.2 s), cost 4.0× more, and passed 5 of 5 to its 5.

  • Against GPT-6 Luna: Grok 4.7 answered 5.3× later (11.7 s to 2.2 s), cost 73.5× more, and passed 5 of 5 to its 4. Only Grok 4.7 passed Pens at 3 for $4.

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

  • Against Gemini 3.1 Pro (preview): Grok 4.7 answered 1.4× later (11.7 s to 8.3 s), cost 1.4× less, and passed 5 of 5 to its 5.

  • Against Gemini 3.8 Flash: Grok 4.7 answered 2.5× later (11.7 s to 4.7 s), cost 5.1× more, and passed 5 of 5 to its 5.

  • Against DeepSeek V4.1 Flash: Grok 4.7 answered 12.6× later (11.7 s to 0.9 s), cost 28.9× more, and passed 5 of 5 to its 5.

  • Against DeepSeek V4 Pro: Grok 4.7 answered 4.3× later (11.7 s to 2.7 s), cost 8.2× more, and passed 5 of 5 to its 5.

  • Against Kimi K3: Grok 4.7 answered 2.2× later (11.7 s to 5.4 s), cost 1.9× more, and passed 5 of 5 to its 5.

  • Against GLM 5.3: Grok 4.7 answered 12.4× later (11.7 s to 0.9 s), cost 20.5× more, and passed 5 of 5 to its 5.

  • Against GLM 5.3 Flash: Grok 4.7 answered 4.3× later (11.7 s to 2.7 s), cost 48.1× more, and passed 5 of 5 to its 5.

  • Against Mistral Large 4: Grok 4.7 answered 2.3× later (11.7 s to 5.1 s), cost 4.0× 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.

How the runs were done, and every math prompt.

Grok 4.7, and math, elsewhere

Questions

Is Grok 4.7 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 Grok 4.7 use?

1 message each on Pro, where it has 250 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