Skip to content

Kimi K3.1 Pro · Coding

Kimi K3.1 Pro for coding: our test runs

Kimi K3.1 Pro ran our 5 coding 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 coding 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 $0.0074 to run on average.

Prompt by prompt

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

Kimi K3.1 Pro on each coding prompt
PromptResultCostTime
Turn a title into a URL slugEverydayPassed: All 7 tests passed.$0.00343.6 s
Parse a duration like “1h 30m”EverydayPassed: All 10 tests passed.$0.00457.8 s
Merge overlapping intervalsEverydayPassed: All 7 tests passed.$0.00474.6 s
Evaluate an arithmetic expression, no evalHardPassed: All 15 tests passed.$0.013922.3 s
Parse CSV with quoted fieldsHardPassed: All 8 tests passed.$0.010621.9 s

Every coding reply from Kimi K3.1 Pro

  1. Turn a title into a URL slug

    An everyday prompt: “Turn a title into a URL slug”, in full.

    Passed: All 7 tests passed.

    ```javascript
    function slugify(title) {
      return title
        .normalize("NFD")
        .replace(/[\u0300-\u036f]/g, "")
        .toLowerCase()
        .replace(/[^a-z0-9]+/g, "-")
        .replace(/^-+|-+$/g, "");
    }
    ```

    750 tokens in, 190 out (106 of them reasoning) · 3.6 s · $0.0034 · 1 message on Pro · answered by moonshotai/kimi-k3.1-pro via Together ·

  2. Parse a duration like “1h 30m”

    An everyday prompt: “Parse a duration like “1h 30m””, in full.

    Passed: All 10 tests passed.

    ```javascript
    function parseDuration(text) {
      if (typeof text !== "string") return null;
    
      const match = text.match(/^\s*(?:(\d+)h)?\s*(?:(\d+)m)?\s*(?:(\d+)s)?\s*$/);
      if (!match || !match.slice(1).some(Boolean)) return null;
    
      const [, hours, minutes, seconds] = match;
      return Number(hours || 0) * 3600
        + Number(minutes || 0) * 60
        + Number(seconds || 0);
    }
    ```

    733 tokens in, 305 out (163 of them reasoning) · 7.8 s · $0.0045 · 1 message on Pro · answered by moonshotai/kimi-k3.1-pro via Together ·

  3. Merge overlapping intervals

    An everyday prompt: “Merge overlapping intervals”, in full.

    Passed: All 7 tests passed.

    ```javascript
    function mergeIntervals(intervals) {
      const sorted = intervals
        .map(([start, end]) => [start, end])
        .sort((a, b) => a[0] - b[0] || a[1] - b[1]);
    
      const merged = [];
    
      for (const [start, end] of sorted) {
        const last = merged[merged.length - 1];
    
        if (!last || start > last[1]) {
          merged.push([start, end]);
        } else if (end > last[1]) {
          last[1] = end;
        }
      }
    
      return merged;
    }
    ```

    714 tokens in, 328 out (177 of them reasoning) · 4.6 s · $0.0047 · 1 message on Pro · answered by moonshotai/kimi-k3.1-pro via Together ·

  4. Evaluate an arithmetic expression, no eval

    A hard prompt: “Evaluate an arithmetic expression, no eval”, in full.

    Passed: All 15 tests passed.

    ```javascript
    function evaluate(expression) {
      if (typeof expression !== "string") {
        throw new Error("Expression must be a string");
      }
    
      let index = 0;
    
      function skipSpaces() {
        while (index < expression.length && /\s/.test(expression[index])) {
          index++;
        }
      }
    
      function fail() {
        throw new Error("Invalid expression");
      }
    
      function parseExpression() {
        let value = parseTerm();
    
        while (true) {
          skipSpaces();
          const operator = expression[index];
          if (operator !== "+" && operator !== "-") return value;
    
          index++;
          const right = parseTerm();
          value = operator === "+" ? value + right : value - right;
        }
      }
    
      function parseTerm() {
        let value = parseUnary();
    
        while (true) {
          skipSpaces();
          const operator = expression[index];
          if (operator !== "*" && operator !== "/") return value;
    
          index++;
          const right = parseUnary();
          value = operator === "*" ? value * right : value / right;
        }
      }
    
      function parseUnary() {
        skipSpaces();
        if (expression[index] === "-") {
          index++;
          return -parseUnary();
        }
        return parsePower();
      }
    
      function parsePower() {
        const base = parsePrimary();
    
        skipSpaces();
        if (expression[index] === "^") {
          index++;
          return base ** parseUnary();
        }
    
        return base;
      }
    
      function parsePrimary() {
        skipSpaces();
    
        if (expression[index] === "(") {
          index++;
          const value = parseExpression();
          skipSpaces();
          if (expression[index] !== ")") fail();
          index++;
          return value;
        }
    
        const start = index;
        let digitCount = 0;
    
        while (index < expression.length && /[0-9]/.test(expression[index])) {
          index++;
          digitCount++;
        }
    
        if (expression[index] === ".") {
          index++;
          while (index < expression.length && /[0-9]/.test(expression[index])) {
            index++;
            digitCount++;
          }
        }
    
        if (digitCount === 0) fail();
        return Number(expression.slice(start, index));
      }
    
      const result = parseExpression();
      skipSpaces();
      if (index !== expression.length) fail();
      return result;
    }
    ```

    814 tokens in, 1,226 out (712 of them reasoning) · 22.3 s · $0.0139 · 1 message on Pro · answered by moonshotai/kimi-k3.1-pro via Together ·

  5. Parse CSV with quoted fields

    A hard prompt: “Parse CSV with quoted fields”, in full.

    Passed: All 8 tests passed.

    ```javascript
    function parseCsv(text) {
      if (text.length === 0) return [];
    
      const rows = [];
      let row = [];
      let field = "";
      let inQuotes = false;
      let atFieldStart = true;
      let endedWithLineBreak = false;
    
      for (let i = 0; i < text.length; i++) {
        const char = text[i];
        endedWithLineBreak = false;
    
        if (inQuotes) {
          if (char === '"') {
            if (text[i + 1] === '"') {
              field += '"';
              i++;
            } else {
              inQuotes = false;
            }
          } else {
            field += char;
          }
          continue;
        }
    
        if (char === '"' && atFieldStart) {
          inQuotes = true;
          atFieldStart = false;
        } else if (char === ",") {
          row.push(field);
          field = "";
          atFieldStart = true;
        } else if (char === "\n" || (char === "\r" && text[i + 1] === "\n")) {
          if (char === "\r") i++;
          row.push(field);
          rows.push(row);
          row = [];
          field = "";
          atFieldStart = true;
          endedWithLineBreak = true;
        } else {
          field += char;
          atFieldStart = false;
        }
      }
    
      if (!endedWithLineBreak) {
        row.push(field);
        rows.push(row);
      }
    
      return rows;
    }
    ```

    746 tokens in, 913 out (575 of them reasoning) · 21.9 s · $0.0106 · 1 message on Pro · answered by moonshotai/kimi-k3.1-pro via Together ·

How it compares on coding

Kimi K3.1 Pro beside the job's picks among every model. 25 models share the hard-problems pick, Kimi K3.1 Pro among them.

Kimi K3.1 Pro beside other models on coding
ModelPassedOn ProCost per reply
Gemini 3.8 FlashOur pick: hard problems (shared), best value5 of 5250 a month on Pro$0.0011
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$0.0074
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 coding

Kimi K3.1 Pro against each model on the same 5 coding 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 1.9× later (7.8 s to 4.1 s), cost 3.3× less, and passed 5 of 5 to its 5.

  • Against Claude Fable 5.1: Kimi K3.1 Pro answered 1.8× later (7.8 s to 4.5 s), cost 4.5× less, and passed 5 of 5 to its 5.

  • Against Claude Opus 5.5: Kimi K3.1 Pro answered 1.4× later (7.8 s to 5.7 s), cost 2.4× less, and passed 5 of 5 to its 5.

  • Against Claude Sonnet 5.5: Kimi K3.1 Pro answered 3.2× later (7.8 s to 2.5 s), cost 1.5× more, and passed 5 of 5 to its 5.

  • Against Claude Sonnet 5: Kimi K3.1 Pro answered 3.0× later (7.8 s to 2.6 s), cost 1.4× less, and passed 5 of 5 to its 5.

  • Against Claude Haiku 5.5: Kimi K3.1 Pro answered 6.1× later (7.8 s to 1.3 s), cost 18.7× more, and passed 5 of 5 to its 5.

  • Against Claude Haiku 4.5: Kimi K3.1 Pro answered 3.6× later (7.8 s to 2.2 s), cost 2.5× more, and passed 5 of 5 to its 3. Only Kimi K3.1 Pro passed Evaluate an arithmetic expression, no eval; Parse CSV with quoted fields.

  • Against GPT-6.2 Astra: Kimi K3.1 Pro answered 2.2× later (7.8 s to 3.5 s), cost 1.8× less, and passed 5 of 5 to its 5.

  • Against GPT-6 Astra: Kimi K3.1 Pro answered 1.4× later (7.8 s to 5.8 s), cost 1.5× less, and passed 5 of 5 to its 5.

  • Against GPT-6.2 Sol: Kimi K3.1 Pro answered 2.1× later (7.8 s to 3.8 s), cost 2.0× more, and passed 5 of 5 to its 5.

  • Against GPT-6.1 Sol: Kimi K3.1 Pro answered within 10% of its time (7.8 s to 7.9 s), cost 1.8× more, and passed 5 of 5 to its 5.

  • Against GPT-6 Sol: Kimi K3.1 Pro answered 1.6× later (7.8 s to 4.8 s), cost 2.6× more, and passed 5 of 5 to its 5.

  • Against GPT-6.1 Terra: Kimi K3.1 Pro answered 1.2× later (7.8 s to 6.8 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 (7.8 s to 7.3 s), cost 52.6× more, and passed 5 of 5 to its 5.

  • Against Gemini 4 Carbon: Kimi K3.1 Pro answered 4.6× sooner (7.8 s to 36.4 s), cost 1.9× less, and passed 5 of 5 to its 5.

  • Against Gemini 4 Argon: Kimi K3.1 Pro answered within 10% of its time (7.8 s to 7.6 s), cost 2.9× more, and passed 5 of 5 to its 5.

  • Against Gemini 4 Hydrogen: Kimi K3.1 Pro answered 1.1× later (7.8 s to 6.9 s), cost 1.2× more, and passed 5 of 5 to its 5.

  • Against Gemini 3.1 Pro (preview): Kimi K3.1 Pro answered 2.0× sooner (7.8 s to 15.7 s), cost 1.8× less, and passed 5 of 5 to its 5.

  • Against Gemini 3.8 Flash: Kimi K3.1 Pro answered 2.4× later (7.8 s to 3.3 s), cost 6.7× more, and passed 5 of 5 to its 5.

  • Against DeepSeek V4.1 Flash: Kimi K3.1 Pro answered 2.2× later (7.8 s to 3.5 s), cost 5.1× more, and passed 5 of 5 to its 5.

  • Against DeepSeek V4 Pro: Kimi K3.1 Pro answered 1.4× sooner (7.8 s to 11.3 s), cost 1.6× less, and passed 5 of 5 to its 5.

  • Against Grok 4.7: Kimi K3.1 Pro answered 4.0× sooner (7.8 s to 31.2 s), cost 3.6× less, and passed 5 of 5 to its 5.

  • Against Kimi K3: Kimi K3.1 Pro answered 1.3× later (7.8 s to 6.2 s), cost within 10% of it, and passed 5 of 5 to its 5.

  • Against GLM 5.3: Kimi K3.1 Pro answered 5.3× later (7.8 s to 1.5 s), cost 3.3× more, and passed 5 of 5 to its 3. Only Kimi K3.1 Pro passed Parse a duration like “1h 30m”; Parse CSV with quoted fields.

  • Against GLM 5.3 Flash: Kimi K3.1 Pro answered 7.3× later (7.8 s to 1.1 s), cost 28.5× more, and passed 5 of 5 to its 5.

  • Against Mistral Large 4: Kimi K3.1 Pro answered 6.0× sooner (7.8 s to 46.9 s), cost within 10% of it, and passed 5 of 5 to its 5.

How these runs were done

Tests. Automatic. The function runs against the prompt's tests in a separate Node.js process with a time limit and no file, network or child-process access; it passes when every test passes.

How the runs were done, and every coding prompt.

Kimi K3.1 Pro, and coding, elsewhere

Questions

Is Kimi K3.1 Pro good for coding?

In our test runs it passed 5 of 5 coding 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 coding 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.