ChatGPT vs Grok for math

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.

Math: GPT-6.1 Sol passed 5 of 5 and Grok 4.7 5 of 5. GPT-6.1 Sol answered 6.6× sooner at the median, 1.8 s against 11.7 s. GPT-6.1 Sol cost 8.4× less, $0.0043 against $0.0362 for the 5 replies. Grok 4.7's replies ran 67% longer, in tokens of reply, thinking not counted.

1. 1. A discount, then sales tax

   Everyday. GPT: 4 of 4 models passed, GPT-6 Luna the cheapest at $0.0001 · Grok: 1 of 1 model passed, Grok 4.7 at $0.0033. The prompt in full.

   GPT-6.1 Sol and Grok 4.7 both passed this one. GPT-6.1 Sol answered sooner (1.5 s to 4.8 s), and GPT-6.1 Sol's reply cost less ($0.0006 to $0.0033); GPT-6.1 Sol wrote 39 tokens of reply, Grok 4.7 65.

   • GPT-6.1 Sol

     Passed: Final answer 66: right.

     Discounted price: $80 × 0.75 = $60  
     After sales tax: $60 × 1.10 = $66
     
     Final answer: $66

     402 tokens in, 39 out · 1.5 s · $0.0006 · 1 message on Pro · answered by openai/gpt-6.1-sol via OpenAI · September 29, 2026

   • Grok 4.7

     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 · October 2, 2026

2. 2. Pens at 3 for $4

   Everyday. GPT: 3 of 4 models passed, GPT-6.1 Sol the cheapest at $0.0010 · Grok: 1 of 1 model passed, Grok 4.7 at $0.0111. The prompt in full.

   GPT-6.1 Sol and Grok 4.7 both passed this one. GPT-6.1 Sol answered sooner (2.4 s to 18.5 s), and GPT-6.1 Sol's reply cost less ($0.0010 to $0.0111); GPT-6.1 Sol wrote 89 tokens of reply, Grok 4.7 211.

   • GPT-6.1 Sol

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

     Three singles cost $4.50, so each 3-for-$4 bundle saves $0.50. Use as many bundles as possible: 3 bundles give 9 pens, then buy 1 single.
     
     Cost: \(3 \times \$4 + \$1.50 = \$13.50\).
     
     Final answer: Buy three 3-pen bundles and one single pen for $13.50.

     404 tokens in, 127 out (38 of them reasoning) · 2.4 s · $0.0010 · 1 message on Pro · answered by openai/gpt-6.1-sol via OpenAI · September 29, 2026

   • Grok 4.7

     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 · October 2, 2026

3. 3. Compound interest over three years

   Everyday. GPT: 4 of 4 models passed, GPT-6 Luna the cheapest at $0.0001 · Grok: 1 of 1 model passed, Grok 4.7 at $0.0051. The prompt in full.

   GPT-6.1 Sol and Grok 4.7 both passed this one. GPT-6.1 Sol answered sooner (1.7 s to 8.0 s), and GPT-6.1 Sol's reply cost less ($0.0007 to $0.0051); GPT-6.1 Sol wrote 64 tokens of reply, Grok 4.7 65.

   • GPT-6.1 Sol

     Passed: Final answer 315.25: right.

     After 3 years, the balance is:
     \[
     2000(1.05)^3 = \$2,315.25
     \]
     
     Interest earned:
     \[
     \$2,315.25 - \$2,000 = \$315.25
     \]
     
     Final answer: $315.25

     404 tokens in, 64 out · 1.7 s · $0.0007 · 1 message on Pro · answered by openai/gpt-6.1-sol via OpenAI · September 29, 2026

   • Grok 4.7

     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 · October 2, 2026

4. 4. Four-digit numbers whose digits sum to 9

   Hard. GPT: 4 of 4 models passed, GPT-6 Luna the cheapest at $0.0001 · Grok: 1 of 1 model passed, Grok 4.7 at $0.0093. The prompt in full.

   GPT-6.1 Sol and Grok 4.7 both passed this one. GPT-6.1 Sol answered sooner (2.7 s to 15.1 s), and GPT-6.1 Sol's reply cost less ($0.0011 to $0.0093); GPT-6.1 Sol wrote 108 tokens of reply, Grok 4.7 178.

   • GPT-6.1 Sol

     Passed: Final answer 165: right.

     Let the digits be \(a,b,c,d\), with \(a\ge1\). Set \(x=a-1\). Then
     \[
     x+b+c+d=8,
     \]
     where all four variables are nonnegative. Each resulting digit is automatically at most 9.
     
     By stars and bars, the number of solutions is
     \[
     \binom{8+4-1}{4-1}=\binom{11}{3}=165.
     \]
     
     Final answer: 165

     380 tokens in, 147 out (39 of them reasoning) · 2.7 s · $0.0011 · 1 message on Pro · answered by openai/gpt-6.1-sol via OpenAI · September 29, 2026

   • Grok 4.7

     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 · October 2, 2026

5. 5. The highest of three dice is a 5

   Hard. GPT: 4 of 4 models passed, GPT-6 Luna the cheapest at $0.0001 · Grok: 1 of 1 model passed, Grok 4.7 at $0.0074. The prompt in full.

   GPT-6.1 Sol and Grok 4.7 both passed this one. GPT-6.1 Sol answered sooner (1.8 s to 11.7 s), and GPT-6.1 Sol's reply cost less ($0.0008 to $0.0074); GPT-6.1 Sol wrote 87 tokens of reply, Grok 4.7 127.

   • GPT-6.1 Sol

     Passed: Final answer (61/216 ): right.

     The highest number is exactly 5 if all three dice show at most 5, but not all show at most 4.
     
     \[
     P(\max=5)=\left(\frac56\right)^3-\left(\frac46\right)^3
     =\frac{125-64}{216}=\frac{61}{216}.
     \]
     
     Final answer: \(\frac{61}{216}\)

     395 tokens in, 87 out · 1.8 s · $0.0008 · 1 message on Pro · answered by openai/gpt-6.1-sol via OpenAI · September 29, 2026

   • Grok 4.7

     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 · October 2, 2026

• GPT-6 Astra vs Grok 4.7: 5 of 5 each; GPT-6 Astra answered 4.5× sooner at the median and Grok 4.7 cost 1.2× less. GPT-6 Astra vs Grok 4.7, on every job.

• GPT-6.1 Sol vs Grok 4.7: 5 of 5 each; GPT-6.1 Sol answered 6.6× sooner at the median and cost 8.4× less.

• GPT-6 Sol vs Grok 4.7: 5 of 5 each; GPT-6 Sol answered 5.4× sooner at the median and cost 4.0× less. GPT-6 Sol vs Grok 4.7, on every job.

• GPT-6 Luna vs Grok 4.7: GPT-6 Luna 4 of 5, Grok 4.7 5; GPT-6 Luna answered 5.3× sooner at the median and cost 73.5× less. GPT-6 Luna vs Grok 4.7, on every job.

Every GPT and Grok reply above was checked the same way as every other model's, by the rules published with the prompts: how the math prompts are scored, and each one in full.

• The lineups

  GPT: 4 models, GPT-6 Astra, GPT-6.1 Sol, GPT-6 Sol, and GPT-6 Luna. Grok: one model, Grok 4.7.

• Price per message

  The least expensive GPT model is GPT-6 Luna (60 messages a day on Pro); Grok's one model is Grok 4.7 (250 messages a month on Pro).

• Context window

  GPT goes up to 1.05M tokens (GPT-6 Astra); Grok up to 500K tokens (Grok 4.7).

• Images and PDFs

  Every model here reads images. Every model here takes a PDF as a whole file.

• On the Free plan

  None of these models is on the Free plan. Paid plans have them, with messages every month: GPT-6 Astra from Pro up.

In llmwise, a message to GPT goes to its maker, OpenAI, or through OpenRouter when llmwise can't reach the maker directly. Grok models are served only through OpenRouter, by endpoints that don't store or train on prompts. The Privacy Policy has the details.