Skip to content

Kimi K3.1 Pro · Math

Kimi K3.1 Pro for math: our test runs

Kimi K3.1 Pro 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, Kimi K3.1 Pro 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 $0.0029 to run on average.

Prompt by prompt

Each of the 5 math prompts, and how Kimi K3.1 Pro's reply did.

Kimi K3.1 Pro on each math prompt
PromptResultCostTime
A discount, then sales taxEverydayPassed: Final answer 66: right.$0.00242.5 s
Pens at 3 for $4EverydayPassed: Final answer Three sets of 3 pens plus 1 single pen, costing 13.50.: right.$0.00333.4 s
Compound interest over three yearsEverydayPassed: Final answer 315.25: right.$0.00282.7 s
Four-digit numbers whose digits sum to 9HardPassed: Final answer 165: right.$0.00333.7 s
The highest of three dice is a 5HardPassed: Final answer (61/216 ): right.$0.00265.3 s

Every math reply from Kimi K3.1 Pro

  1. A discount, then sales tax

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

    Passed: Final answer 66: right.

    Discounted price: $80 × 75% = $60  
    After 10% sales tax: $60 × 1.10 = $66
    
    Final answer: $66

    665 tokens in, 103 out (53 of them reasoning) · 2.5 s · $0.0024 · 1 message on Pro · answered by moonshotai/kimi-k3.1-pro via Together ·

  2. Pens at 3 for $4

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

    Passed: Final answer Three sets of 3 pens plus 1 single pen, costing 13.50.: right.

    Buy **3 sets of 3 pens** for 9 pens: \(3 \times \$4 = \$12\).  
    Then buy **1 single pen**: \(\$1.50\).  
    
    Total: \(\$12 + \$1.50 = \$13.50\).
    
    Final answer: Three sets of 3 pens plus 1 single pen, costing $13.50.

    667 tokens in, 194 out (102 of them reasoning) · 3.4 s · $0.0033 · 1 message on Pro · answered by moonshotai/kimi-k3.1-pro via Together ·

  3. Compound interest over three years

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

    Passed: Final answer 315.25: right.

    Balance after 3 years:  
    \[
    \$2{,}000(1.05)^3 = \$2{,}315.25
    \]
    
    Interest earned:  
    \[
    \$2{,}315.25 - \$2{,}000 = \$315.25
    \]
    
    Final answer: $315.25

    667 tokens in, 148 out (66 of them reasoning) · 2.7 s · $0.0028 · 1 message on Pro · answered by moonshotai/kimi-k3.1-pro via Together ·

  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 digits be \(a,b,c,d\), where \(a\ge 1\) and \(a+b+c+d=9\).
    
    Set \(a'=a-1\). Then \(a',b,c,d\ge 0\) and
    \[
    a'+b+c+d=8.
    \]
    By stars and bars, the number of solutions is
    \[
    \binom{8+4-1}{4-1}=\binom{11}{3}=165.
    \]
    
    Final answer: 165

    643 tokens in, 198 out (83 of them reasoning) · 3.7 s · $0.0033 · 1 message on Pro · answered by moonshotai/kimi-k3.1-pro via Together ·

  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.

    There are \(5^3=125\) outcomes where all dice show at most 5. Subtract the \(4^3=64\) outcomes where all dice show at most 4, leaving \(125-64=61\) outcomes where the highest number is exactly 5.
    
    Final answer: \(\frac{61}{216}\)

    658 tokens in, 126 out (46 of them reasoning) · 5.3 s · $0.0026 · 1 message on Pro · answered by moonshotai/kimi-k3.1-pro via Together ·

How it compares on math

Kimi K3.1 Pro beside the job's picks among every model. 27 models share the hard-problems pick, Kimi K3.1 Pro among them.

Kimi K3.1 Pro beside other models on math
ModelPassedOn ProCost per reply
GPT-6.1 TerraOur pick: hard problems (shared), best value5 of 5250 a month on Pro$0.0005
GPT-6 LunaOur pick: hard problems (shared), everyday5 of 560 a day on Pro$0.0001
Kimi K3.1 ProOur pick: hard problems (shared)5 of 5125 a month on Pro$0.0029
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.

Kimi K3.1 Pro next to each model on math

Kimi K3.1 Pro 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: Kimi K3.1 Pro answered 1.2× later (3.4 s to 2.8 s), cost 2.2× less, and passed 5 of 5 to its 5.

  • Against Claude Fable 5.1: Kimi K3.1 Pro answered 1.9× later (3.4 s to 1.7 s), cost 3.1× less, and passed 5 of 5 to its 5.

  • Against Claude Opus 5.5: Kimi K3.1 Pro answered 1.3× later (3.4 s to 2.7 s), cost 1.5× less, and passed 5 of 5 to its 5.

  • Against Claude Sonnet 5.5: Kimi K3.1 Pro answered 1.9× later (3.4 s to 1.8 s), cost 1.6× more, and passed 5 of 5 to its 5.

  • Against Claude Sonnet 5: Kimi K3.1 Pro answered 1.3× later (3.4 s to 2.5 s), cost 1.4× less, and passed 5 of 5 to its 5.

  • Against Claude Haiku 5.5: Kimi K3.1 Pro answered 2.1× later (3.4 s to 1.6 s), cost 19.1× more, and passed 5 of 5 to its 5.

  • Against Claude Haiku 4.5: Kimi K3.1 Pro answered 1.6× later (3.4 s to 2.1 s), cost 1.6× more, and passed 5 of 5 to its 5.

  • Against GPT-6.2 Astra: Kimi K3.1 Pro answered 1.3× later (3.4 s to 2.6 s), cost 2.6× less, and passed 5 of 5 to its 5.

  • Against GPT-6 Astra: Kimi K3.1 Pro answered 1.2× sooner (3.4 s to 3.9 s), cost 1.8× less, and passed 5 of 5 to its 5.

  • Against GPT-6.2 Sol: Kimi K3.1 Pro answered 1.7× later (3.4 s to 2.0 s), cost 1.5× more, and passed 5 of 5 to its 5.

  • Against GPT-6.1 Sol: Kimi K3.1 Pro answered 3.2× sooner (3.4 s to 10.9 s), cost 2.8× more, and passed 5 of 5 to its 5.

  • Against GPT-6 Sol: Kimi K3.1 Pro answered 1.3× later (3.4 s to 2.5 s), cost 2.6× more, and passed 5 of 5 to its 5.

  • Against GPT-6.1 Terra: Kimi K3.1 Pro answered 1.5× later (3.4 s to 2.2 s), cost 5.6× more, and passed 5 of 5 to its 5.

  • Against GPT-6 Luna: Kimi K3.1 Pro answered within 10% of its time (3.4 s to 3.3 s), cost 54.4× more, and passed 5 of 5 to its 5.

  • Against Gemini 4 Carbon: Kimi K3.1 Pro answered 1.8× sooner (3.4 s to 6.1 s), cost 1.1× more, and passed 5 of 5 to its 5.

  • Against Gemini 4 Argon: Kimi K3.1 Pro answered 2.1× sooner (3.4 s to 7.1 s), cost 1.9× more, and passed 5 of 5 to its 5.

  • Against Gemini 4 Hydrogen: Kimi K3.1 Pro answered 1.1× later (3.4 s to 2.9 s), cost 1.2× more, and passed 5 of 5 to its 5.

  • Against Gemini 3.1 Pro (preview): Kimi K3.1 Pro answered 1.9× sooner (3.4 s to 6.5 s), cost 1.7× less, and passed 5 of 5 to its 5.

  • Against Gemini 3.8 Flash: Kimi K3.1 Pro answered 1.2× sooner (3.4 s to 4.0 s), cost 3.2× more, and passed 5 of 5 to its 5.

  • Against DeepSeek V4.1 Flash: Kimi K3.1 Pro answered 4.8× later (3.4 s to 0.7 s), cost 9.8× more, and passed 5 of 5 to its 5.

  • Against DeepSeek V4 Pro: Kimi K3.1 Pro answered 1.3× sooner (3.4 s to 4.4 s), cost 1.9× more, and passed 5 of 5 to its 5.

  • Against Grok 4.7: Kimi K3.1 Pro answered 2.6× sooner (3.4 s to 8.8 s), cost 2.8× less, and passed 5 of 5 to its 5.

  • Against Kimi K3: Kimi K3.1 Pro answered 1.5× sooner (3.4 s to 5.2 s), cost 1.3× less, and passed 5 of 5 to its 5.

  • Against GLM 5.3: Kimi K3.1 Pro answered 2.7× later (3.4 s to 1.2 s), cost 3.8× more, and passed 5 of 5 to its 5.

  • Against GLM 5.3 Flash: Kimi K3.1 Pro answered 3.3× later (3.4 s to 1.0 s), cost 17.3× more, and passed 5 of 5 to its 5.

  • Against Mistral Large 4: Kimi K3.1 Pro answered 1.9× sooner (3.4 s to 6.4 s), cost 2.6× 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.

Kimi K3.1 Pro, and math, elsewhere

Questions

Is Kimi K3.1 Pro 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 Kimi K3.1 Pro 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.