Mistral Large 4 · Data analysis
Mistral Large 4 for data analysis: our test runs
Mistral Large 4 ran our 5 data analysis 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. Updated .
Short answer
In our test runs on October 9, 2026, Mistral Large 4 passed 5 of 5 of our data analysis prompts (both hard ones): tied 1st of 19 models. Each reply counted as 1 message on Pro, where it has 250 a month, and cost $0.0037 to run on average.
Prompt by prompt
Each of the 5 data analysis prompts, and how Mistral Large 4's reply did.
| Prompt | Result | Cost | Time |
|---|---|---|---|
| The region with the most revenueEveryday | Passed: Final answer North, 1,085.00: right. | $0.0019 | 6.8 s |
| Average order value in AugustEveryday | Passed: Final answer 300.00: right. | $0.0021 | 20.4 s |
| Revenue change from July to AugustEveryday | Passed: Final answer 67.4%: right. | $0.0043 | 15.8 s |
| A median, filtered two waysHard | Passed: Final answer 6.25: right. | $0.0011 | 3.9 s |
| Correlation between ad spend and sign-upsHard | Passed: Final answer 0.97: right. | $0.0091 | 35.0 s |
Every data analysis reply from Mistral Large 4
The region with the most revenue
An everyday prompt: “The region with the most revenue”, in full.
Passed: Final answer North, 1,085.00: right.
Revenue by region (quantity × price): **West:** (2×45) + (1×310) + (2×120) + (5×45) = 90 + 310 + 240 + 225 = **$865** **East:** (1×120) + (3×45) + (1×310) + (3×120) = 120 + 135 + 310 + 360 = **$925** **North:** (4×45) + (2×120) + (2×310) + (1×45) = 180 + 240 + 620 + 45 = **$1,085** Final answer: North, $1,085.00
646 tokens in, 722 out (335 of them reasoning) · 6.8 s · $0.0019 · 1 message on Pro · answered by mistralai/mistral-large-4-0 via Mistral ·
Average order value in August
An everyday prompt: “Average order value in August”, in full.
Passed: Final answer 300.00: right.
August 2026 orders: - 1007: 2 × 120.00 = 240.00 - 1008: 1 × 310.00 = 310.00 - 1009: 2 × 310.00 = 620.00 - 1010: 5 × 45.00 = 225.00 - 1011: 3 × 120.00 = 360.00 - 1012: 1 × 45.00 = 45.00 Total revenue: 240 + 310 + 620 + 225 + 360 + 45 = 1800.00 Number of orders: 6 Average: 1800.00 / 6 = 300.00 Final answer: 300.00
653 tokens in, 814 out (439 of them reasoning) · 20.4 s · $0.0021 · 1 message on Pro · answered by mistralai/mistral-large-4-0 via Mistral ·
Revenue change from July to August
An everyday prompt: “Revenue change from July to August”, in full.
Passed: Final answer 67.4%: right.
July 2026 revenue: (2×45) + (1×120) + (1×310) + (4×45) + (3×45) + (2×120) = 90 + 120 + 310 + 180 + 135 + 240 = **$1,075** August 2026 revenue: (2×120) + (1×310) + (2×310) + (5×45) + (3×120) + (1×45) = 240 + 310 + 620 + 225 + 360 + 45 = **$1,800** Percentage change: ((1,800 − 1,075) / 1,075) × 100 = (725 / 1,075) × 100 ≈ 67.4% Final answer: 67.4%
658 tokens in, 1,825 out (1,082 of them reasoning) · 15.8 s · $0.0043 · 1 message on Pro · answered by mistralai/mistral-large-4-0 via Mistral ·
A median, filtered two ways
A hard prompt: “A median, filtered two ways”, in full.
Passed: Final answer 6.25: right.
Filtering to Billing team + high priority: 5.5, 2, 9, 7, 26, 4. Sorted: 2, 4, 5.5, 7, 9, 26. Six values, so median = average of 3rd and 4th = (5.5 + 7) / 2 = 6.25. Final answer: 6.25
518 tokens in, 377 out (180 of them reasoning) · 3.9 s · $0.0011 · 1 message on Pro · answered by mistralai/mistral-large-4-0 via Mistral ·
Correlation between ad spend and sign-ups
A hard prompt: “Correlation between ad spend and sign-ups”, in full.
Passed: Final answer 0.97: right.
Using \(r=\dfrac{\sum (x-\bar x)(y-\bar y)}{\sqrt{\sum (x-\bar x)^2 \sum (y-\bar y)^2}}\): - \(\bar x = 6150/8 = 768.75\), \(\bar y = 434/8 = 54.25\) - \(\sum (x-\bar x)(y-\bar y) = 23912.5\) - \(\sum (x-\bar x)^2 = 624687.5\) - \(\sum (y-\bar y)^2 = 971.5\) \(r = \dfrac{23912.5}{\sqrt{624687.5 \times 971.5}} = \dfrac{23912.5}{24635.01} \approx 0.9707\) Final answer: 0.97457 tokens in, 4,217 out (2,008 of them reasoning) · 35.0 s · $0.0091 · 1 message on Pro · answered by mistralai/mistral-large-4-0 via Mistral ·
How it compares on data analysis
Mistral Large 4 beside the job's picks among every model. 15 models share the hard-problems pick, Mistral Large 4 among them.
| Model | Passed | On Pro | Cost per reply |
|---|---|---|---|
| GLM 5.3Our pick: hard problems (shared), best value | 5 of 5 | 250 a month on Pro | $0.0019 |
| GPT-6 LunaOur pick: hard problems (shared), everyday | 5 of 5 | 60 a day on Pro | $0.0002 |
| Mistral Large 4Our pick: hard problems (shared) | 5 of 5 | 250 a month on Pro | $0.0037 |
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 data analysis
Mistral Large 4 against each model on the same 5 data analysis 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 3.2× later (15.8 s to 4.9 s), cost 7.6× less, and passed 5 of 5 to its 5.
Against Claude Opus 5.5: Mistral Large 4 answered 3.5× later (15.8 s to 4.6 s), cost 3.5× less, and passed 5 of 5 to its 5.
Against Claude Sonnet 5.5: Mistral Large 4 answered 6.9× later (15.8 s to 2.3 s), cost 1.3× less, and passed 5 of 5 to its 5.
Against Claude Sonnet 5: Mistral Large 4 answered 3.0× later (15.8 s to 5.3 s), cost 1.8× less, and passed 5 of 5 to its 4. Only Mistral Large 4 passed Correlation between ad spend and sign-ups.
Against Claude Haiku 5.5: Mistral Large 4 answered 4.8× later (15.8 s to 3.3 s), cost 10.4× more, and passed 5 of 5 to its 5.
Against Claude Haiku 4.5: Mistral Large 4 answered 5.8× later (15.8 s to 2.7 s), cost 1.5× more, and passed 5 of 5 to its 3. Only Mistral Large 4 passed Average order value in August; Correlation between ad spend and sign-ups.
Against GPT-6 Astra: Mistral Large 4 answered 4.8× later (15.8 s to 3.3 s), cost 4.1× less, and passed 5 of 5 to its 5.
Against GPT-6.1 Sol: Mistral Large 4 answered 5.3× later (15.8 s to 3.0 s), cost 2.3× more, and passed 5 of 5 to its 5.
Against GPT-6 Sol: Mistral Large 4 answered 5.7× later (15.8 s to 2.8 s), cost 1.1× more, and passed 5 of 5 to its 5.
Against GPT-6 Luna: Mistral Large 4 answered 6.3× later (15.8 s to 2.5 s), cost 21.2× more, and passed 5 of 5 to its 5.
Against Gemini 3.1 Pro (preview): Mistral Large 4 answered 1.8× later (15.8 s to 8.6 s), cost 4.2× less, and passed 5 of 5 to its 5.
Against Gemini 3.8 Flash: Mistral Large 4 answered 2.9× later (15.8 s to 5.4 s), cost 1.3× more, and passed 5 of 5 to its 4. Only Mistral Large 4 passed Correlation between ad spend and sign-ups.
Against DeepSeek V4.1 Flash: Mistral Large 4 answered 18.3× later (15.8 s to 0.9 s), cost 4.4× more, and passed 5 of 5 to its 5.
Against DeepSeek V4 Pro: Mistral Large 4 answered 3.9× later (15.8 s to 4.1 s), cost 1.3× more, and passed 5 of 5 to its 5.
Against Grok 4.7: Mistral Large 4 answered 1.8× later (15.8 s to 8.9 s), cost 3.0× less, and passed 5 of 5 to its 5.
Against Kimi K3: Mistral Large 4 answered 4.5× later (15.8 s to 3.5 s), cost 1.8× less, and passed 5 of 5 to its 5.
Against GLM 5.3: Mistral Large 4 answered 8.2× later (15.8 s to 1.9 s), cost 1.9× more, and passed 5 of 5 to its 5.
Against GLM 5.3 Flash: Mistral Large 4 answered 1.6× later (15.8 s to 9.8 s), cost 9.7× more, and passed 5 of 5 to its 4. Only Mistral Large 4 passed Correlation between ad spend and sign-ups.
How these runs were done
Final answer. Automatic. The reply's last “Final answer:” line must hold the right value.
Mistral Large 4, and data analysis, elsewhere
- Mistral Large 4: price, limits and messages on every plan
- Mistral Large 4 for coding: our test runs
- Mistral Large 4 for writing: our test runs
- Mistral Large 4 for math: our test runs
- Analyze a CSV with code: the prompt, and its price
- AI prompts for business, tested on four models
- Our test runs: 50 prompts on every model
Questions
Is Mistral Large 4 good for data analysis?
In our test runs it passed 5 of 5 data analysis prompts, tied 1st 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 data analysis 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.