Skip to content
llmwise
Sign inStart free

Mistral Large 4 · Coding

Mistral Large 4 for coding: our test runs

Mistral Large 4 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.

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 9, 2026, Mistral Large 4 passed 4 of 5 of our coding prompts (1 of the 2 hard ones): 18th of 19 models. Each reply counted as 1 message on Pro, where it has 250 a month, and cost $0.0073 to run on average.

Prompt by prompt

Each of the 5 coding prompts, and how Mistral Large 4's reply did.

Mistral Large 4 on each coding prompt
PromptResultCostTime
Turn a title into a URL slugEverydayPassed: All 7 tests passed.$0.00227.0 s
Parse a duration like “1h 30m”EverydayPassed: All 10 tests passed.$0.003536.8 s
Merge overlapping intervalsEverydayPassed: All 7 tests passed.$0.00188.1 s
Evaluate an arithmetic expression, no evalHardFailed: No answer within Pro's reply limit of 8,000 tokens: the model spent them all reasoning.$0.017195.6 s
Parse CSV with quoted fieldsHardPassed: All 8 tests passed.$0.011857.3 s

Every coding reply from Mistral Large 4

  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')                    // split accented letters into base + combining mark
    .replace(/[\u0300-\u036f]/g, '')    // strip the combining marks (é → e, ñ → n, ü → u)
    .toLowerCase()
    .replace(/[^a-z0-9]+/g, '-')        // every run of non-alphanumerics becomes one hyphen
    .replace(/^-+|-+$/g, '');           // trim hyphens from start and end
}
```

    491 tokens in, 871 out (694 of them reasoning) · 7.0 s · $0.0022 · 1 message on Pro · answered by mistralai/mistral-large-4-0 via Mistral ·

  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 = /^\s*(?:(\d+)h)?\s*(?:(\d+)m)?\s*(?:(\d+)s)?\s*$/.exec(text);
  if (!match) return null;
  const [, h, m, s] = match;
  if (h === undefined && m === undefined && s === undefined) return null;
  return Number(h || 0) * 3600 + Number(m || 0) * 60 + Number(s || 0);
}
```

    473 tokens in, 1,505 out (1,161 of them reasoning) · 36.8 s · $0.0035 · 1 message on Pro · answered by mistralai/mistral-large-4-0 via Mistral ·

  3. Merge overlapping intervals

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

    Passed: All 7 tests passed.

    ```javascript
function mergeIntervals(intervals) {
  if (intervals.length === 0) return [];

  const sorted = intervals.slice().sort((a, b) => a[0] - b[0]);
  const merged = [];

  let start = sorted[0][0];
  let end = sorted[0][1];

  for (let i = 1; i < sorted.length; i++) {
    const s = sorted[i][0];
    const e = sorted[i][1];

    if (s <= end) {
      if (e > end) end = e;
    } else {
      merged.push([start, end]);
      start = s;
      end = e;
    }
  }

  merged.push([start, end]);
  return merged;
}
```

    456 tokens in, 727 out (552 of them reasoning) · 8.1 s · $0.0018 · 1 message on Pro · answered by mistralai/mistral-large-4-0 via Mistral ·

  4. Evaluate an arithmetic expression, no eval

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

    Failed: No answer within Pro's reply limit of 8,000 tokens: the model spent them all reasoning.

    (no reply)

    562 tokens in, 8,000 out (6,714 of them reasoning) · 95.6 s · $0.0171 · 1 message on Pro · answered by mistralai/mistral-large-4-0 via Mistral ·

  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 === '') return [];

  const rows = [];
  let row = [];
  let field = '';
  let inQuotes = false;
  let hasField = false; // current field has begun (quote opened or char seen)
  let i = 0;

  const endField = () => {
    row.push(field);
    field = '';
    hasField = false;
  };
  const endRow = () => {
    endField();
    rows.push(row);
    row = [];
  };

  while (i < text.length) {
    const ch = text[i];

    if (inQuotes) {
      if (ch === '"') {
        if (text[i + 1] === '"') {
          field += '"';
          i += 2;
        } else {
          inQuotes = false;
          i++;
        }
      } else {
        field += ch;
        i++;
      }
      continue;
    }

    if (ch === '"' && !hasField) {
      inQuotes = true;
      hasField = true;
      i++;
    } else if (ch === ',') {
      endField();
      i++;
    } else if (ch === '\n' || ch === '\r') {
      if (ch === '\r' && text[i + 1] === '\n') i++;
      endRow();
      i++;
    } else {
      field += ch;
      hasField = true;
      i++;
    }
  }

  // Push the final row unless the text ended with a line break.
  if (hasField || row.length > 0) {
    endField();
    rows.push(row);
  }

  return rows;
}
```

    491 tokens in, 5,505 out (4,808 of them reasoning) · 57.3 s · $0.0118 · 1 message on Pro · answered by mistralai/mistral-large-4-0 via Mistral ·

How it compares on coding

Mistral Large 4 beside the job's picks among every model. 17 models share the hard-problems pick, and Mistral Large 4 isn't one of them.

Mistral Large 4 beside other models on coding
ModelPassedOn ProCost per reply
GLM 5.3Our pick: hard problems (shared), best value5 of 5250 a month on Pro$0.0015
GLM 5.3 FlashOur pick: hard problems (shared), everyday5 of 560 a day on Pro$0.0003
Mistral Large 44 of 5250 a month on Pro$0.0073
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: 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.

Mistral Large 4 next to each model on coding

Mistral Large 4 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 5.1: Mistral Large 4 answered 6.6× later (36.8 s to 5.5 s), cost 5.8× less, and passed 4 of 5 to its 5. Only Claude Fable 5.1 passed Evaluate an arithmetic expression, no eval.

  • Against Claude Opus 5.5: Mistral Large 4 answered 5.1× later (36.8 s to 7.2 s), cost 2.3× less, and passed 4 of 5 to its 5. Only Claude Opus 5.5 passed Evaluate an arithmetic expression, no eval.

  • Against Claude Sonnet 5.5: Mistral Large 4 answered 18.8× later (36.8 s to 2.0 s), cost 1.2× more, and passed 4 of 5 to its 5. Only Claude Sonnet 5.5 passed Evaluate an arithmetic expression, no eval.

  • Against Claude Sonnet 5: Mistral Large 4 answered 13.8× later (36.8 s to 2.7 s), cost 1.4× less, and passed 4 of 5 to its 5. Only Claude Sonnet 5 passed Evaluate an arithmetic expression, no eval.

  • Against Claude Haiku 5.5: Mistral Large 4 answered 9.3× later (36.8 s to 3.9 s), cost 16.1× more, and passed 4 of 5 to its 5. Only Claude Haiku 5.5 passed Evaluate an arithmetic expression, no eval.

  • Against Claude Haiku 4.5: Mistral Large 4 answered 15.7× later (36.8 s to 2.3 s), cost 2.6× more, and passed 4 of 5 to its 3. Only Mistral Large 4 passed Parse CSV with quoted fields.

  • Against GPT-6 Astra: Mistral Large 4 answered 4.5× later (36.8 s to 8.2 s), cost 3.1× less, and passed 4 of 5 to its 5. Only GPT-6 Astra passed Evaluate an arithmetic expression, no eval.

  • Against GPT-6.1 Sol: Mistral Large 4 answered 7.7× later (36.8 s to 4.8 s), cost 3.2× more, and passed 4 of 5 to its 5. Only GPT-6.1 Sol passed Evaluate an arithmetic expression, no eval.

  • Against GPT-6 Sol: Mistral Large 4 answered 7.7× later (36.8 s to 4.8 s), cost 1.4× more, and passed 4 of 5 to its 5. Only GPT-6 Sol passed Evaluate an arithmetic expression, no eval.

  • Against GPT-6 Luna: Mistral Large 4 answered 8.1× later (36.8 s to 4.6 s), cost 25.4× more, and passed 4 of 5 to its 5. Only GPT-6 Luna passed Evaluate an arithmetic expression, no eval.

  • Against Gemini 3.1 Pro (preview): Mistral Large 4 answered 3.6× later (36.8 s to 10.3 s), cost 2.7× less, and passed 4 of 5 to its 5. Only Gemini 3.1 Pro (preview) passed Evaluate an arithmetic expression, no eval.

  • Against Gemini 3.8 Flash: Mistral Large 4 answered 8.8× later (36.8 s to 4.2 s), cost 3.7× more, and passed 4 of 5 to its 5. Only Gemini 3.8 Flash passed Evaluate an arithmetic expression, no eval.

  • Against DeepSeek V4.1 Flash: Mistral Large 4 answered 14.8× later (36.8 s to 2.5 s), cost 4.0× more, and passed 4 of 5 to its 5. Only DeepSeek V4.1 Flash passed Evaluate an arithmetic expression, no eval.

  • Against DeepSeek V4 Pro: Mistral Large 4 answered 3.2× sooner (36.8 s to 119.6 s), cost 3.3× less, and passed 4 of 5 to its 5. Only DeepSeek V4 Pro passed Evaluate an arithmetic expression, no eval.

  • Against Grok 4.7: Mistral Large 4 answered 1.2× later (36.8 s to 31.6 s), cost 3.4× less, and passed 4 of 5 to its 5. Only Grok 4.7 passed Evaluate an arithmetic expression, no eval.

  • Against Kimi K3: Mistral Large 4 answered 8.9× later (36.8 s to 4.1 s), cost 1.2× more, and passed 4 of 5 to its 5. Only Kimi K3 passed Evaluate an arithmetic expression, no eval.

  • Against GLM 5.3: Mistral Large 4 answered 34.9× later (36.8 s to 1.1 s), cost 5.0× more, and passed 4 of 5 to its 5. Only GLM 5.3 passed Evaluate an arithmetic expression, no eval.

  • Against GLM 5.3 Flash: Mistral Large 4 answered 4.4× later (36.8 s to 8.4 s), cost 28.8× more, and passed 4 of 5 to its 5. Only GLM 5.3 Flash passed Evaluate an arithmetic expression, no eval.

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.

Mistral Large 4, and coding, elsewhere

Questions

Is Mistral Large 4 good for coding?

In our test runs it passed 4 of 5 coding prompts, 18th of the 19 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 Mistral Large 4 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