Best Free AI for Case Interview Math Practice (2026)

The best free AI for case interview math is ChatGPT or Claude for prompt volume plus a graded consulting drill for scoring; for raw math reps, see our case interview math practice drills. The five tools below cover different case-math jobs, so choose by the feedback you need, not by the model name.

What Does Case Math Practice Actually Look Like?

Case interview math is not a math test. A useful self-review checks four things: the formula, the staged calculation, the units, and the business read. Not "the answer is 12 percent" but "revenue grew 12 percent year over year; we need price and volume data to explain what drove that growth."

These are practice checkpoints, not a published four-part scoring rubric shared by every firm.

That is why ChatGPT's default math drills feel off. A prompt that asks only whether "5,000 times 1.08 equals 5,400" need not elicit a review of the formula, units or business meaning. The right free stack fills that gap.

The Five Best Free AI Tools for Case Math

ChatGPT (free tier)

• What it does. ChatGPT (https://chatgpt.com/) generates custom math drills within its current usage limits if you prompt it correctly. Best when you give it a role ("act as an MBB interviewer"), constraints ("messy numbers, no calculator, 45 second target"), and grading rules ("check setup, units, and business interpretation, not just the final answer").

• Price. Free, with usage limits on the top model and broader access to the lighter model in 2026.

• Strengths. High-volume drill generation, voice mode when available, fast iteration on prompt tuning, broad business context.

• Limitations. Feedback and arithmetic can be wrong. Ask for specific corrections, check the calculations, and maintain an error log instead of assuming the chat provides a complete practice history.

• Best for. High-volume daily drills once you have a strong prompt template. Pair with Road to Offer's Math Drill for the weekly graded rep.

Claude (free tier)

• What it does. Claude (https://claude.ai/) offers the same drill function as ChatGPT, with support for discussing longer case passages within the selected model's limits. You can paste an entire case prompt or a one-page exhibit and ask Claude to drill you on the math inside.

• Price. Free, with daily message limits.

• Strengths. Long context (handles full case prompts in one paste), more consistent on chained calculations, better at sensitivity and what-if math, less prone to inventing intermediate numbers.

• Limitations. Free tier rate-limited, no voice mode, smaller community of shared prompts.

• Best for. Chained calculations (sensitivity, multi-driver profitability, top-down market sizing), pasting full case prompts to drill the embedded math, and getting a second AI opinion on a hard problem.

Google Gemini (free tier)

• What it does. Gemini (https://gemini.google.com/) pulls from Google Search, so it is the strongest free model for generating realistic industry numbers and market context. Use it to build a case prompt with plausible figures, or to sanity-check the inputs you are about to size a market with.

• Price. Free, with limits on the top model.

• Strengths. Live data grounding, good for realistic market-sizing inputs (population, household size, average spend), useful for building case prompts that feel current.

• Limitations. Less consistent as a strict interviewer than ChatGPT or Claude, can still hallucinate, weaker at holding a long calculation chain together.

• Best for. Generating realistic numbers before a market-sizing or industry case, then handing the drill itself to ChatGPT, Claude, or Road to Offer.

Perplexity

• What it does. Perplexity (https://www.perplexity.ai/) returns sourced answers fast, which makes it ideal for a quick industry primer before a case. Before a healthcare or retail case you can ground your market-sizing assumptions in real, cited data in about five minutes.

• Price. Free, with limits on advanced models.

• Strengths. Sourced, fast research, good for the pre-case primer, useful for checking whether an assumption ("US households spend roughly X on groceries per month") is in the right range.

• Limitations. Not built to run a mock case or grade your math. It researches, it does not interview.

• Best for. The 5-minute sourced primer before a case so your assumptions are not pulled from thin air.

Road to Offer Math Drill (consulting prompts with numeric grading)

AI-scored cases

92

drills

550+

firm test simulators

6

1 of 3

• What it does. Road to Offer's Math Drill checks your requested numerical answer against the drill's reference and tolerance, including the units. The numeric score primarily reflects answer correctness: a correct number can earn full credit without working. Feedback can refer to the work you submit, but the tool does not guarantee separate scores for formula, calculation, units and business interpretation.

• Price. The free tier gives you 1 full AI-graded case, daily drill practice, one free resume review, plus the first two BCG Casey-style simulator questions with no account.

• Strengths. Consulting-specific prompts, a reference answer and feedback in the same drill flow. Use guided cases for guided practice or explore Voice Mode for full-case spoken practice; those are separate surfaces with their own access conditions.

• Limitations. A high numeric score is not proof that your reasoning or interview delivery was strong. Use a partner or coach when you need someone to challenge assumptions and follow your explanation in context.

• Scope. The Math Drill is one surface in Road to Offer's full consulting-interview prep platform, alongside 92 active practice cases, a 550+ drill bank across 6 skill types plus timed Quick Math, assessment simulators covering four Solve practice formats alongside a BCG Casey-style simulator with 10 original cases and the first two questions free with no account plus a CCA-style simulator, behavioral and McKinsey PEI practice, Learning Mode, a free consulting resume grader, an application tracker, and a free case-book vault.

• Best for. Repeated consulting math questions with answer checking and feedback. Add the self-review below to practise explaining the result, and use live case practice to test that explanation under questions.

Road to Offer offers one complete free run in each of four Solve practice formats: Red Rock's full Study and six Cases on a 35-minute advisory clock, all three Sea Wolf sites on a 30-minute Simulation clock, all 13 SFL Classic decisions without a countdown, and SFL Island onboarding plus three project days on a 30-minute Simulation clock. Start without an account; create a free account to finish and keep your score, point breakdown and worked feedback on each submitted decision. Worked visuals include highlighted calculations and charts in Red Rock, constraint and treatment visuals in Sea Wolf, decision and dependency diagrams in Classic, and evidence chains, placement maps and team feedback in Island. No payment is required for those first runs or their worked reviews. Learning mode is paid: the matching game pack, Solve pack or qualifying Annual access includes its step-by-step coaching and feedback, untimed in the clocked games. The free Solve plan asks your invitation length and test date, then gives dated practice steps for up to 28 days; a free account is needed to view and save it.

The online tests McKinsey, BCG and Bain give before the case interview

AllMcKinseyBCGBain

Sustainable Futures Lab (Island)Start free runSustainable Futures Lab (Classic)Start free runSea WolfStart free runRed RockStart free run

Casey simulatorStart free runCCA numerical prepStart free runSOVAStart free runTestGorilla-style practiceStart free run

Comparison: How the Five Tools Stack Up

• ChatGPT prompt. "Act as an MBB interviewer. Give a profitability problem with messy numbers. Time me at 45s.

  Grade setup, units, and business read."

• Claude prompt. "Here is a full case. Drill me on the math one calculation at a time. After each, grade my equation, units, and what the number means."

• Gemini prompt. "Give me current, sourced numbers for a US specialty-coffee market sizing, then quiz me on the staged calculation."

• Perplexity prompt. "Summarize the US dialysis market: size, growth, top players, with sources." Use it to ground assumptions, not to run the case.

• Road to Offer. Submit an answer with your working. Read the feedback, then review the four checkpoints yourself.

How can you check reasoning as well as the answer?

Worked teaching example, not a recorded product grading result. Use it to check your own explanation before opening a fresh Road to Offer math drill.

Prompt: A product's price rises from $50 to $55. What is the maximum volume loss that keeps revenue flat?

Worked answer: Start with 100 units, so old revenue is 100 × $50 = $5,000. At the new price, flat revenue requires $5,000 ÷ $55 = 90.9 units. The business can therefore lose about 9.1% of volume before revenue falls.

That is a revenue-neutral threshold, not proof that profit or customer lifetime value will improve.

• Formula. New volume = old revenue ÷ new price.
• Units. Dollars and units stay visible on each line.
• Business meaning. A 9.1% volume-loss ceiling for flat revenue.

What Road to Offer is, exactly

Road to Offer is a full consulting interview prep platform powered by AI, not a single case grader. It carries 92 active practice cases run by voice or guided text and scored on a seven-dimension rubric, a 550+ drill bank across 6 skill types plus timed Quick Math, 8 online assessment formats (a BCG Casey-style simulator with 10 original cases, first two questions free with no account, a CCA-style simulator, McKinsey Red Rock, Sea Wolf and Sustainable Futures Lab Classic and Island, and Bain SOVA and TestGorilla practice), behavioral and McKinsey PEI practice, step-by-step Learning Mode lessons, a free consulting resume grader, an application tracker, and a free case book vault.

The free tier includes 1 full AI-graded case, 1 teaching session that earns 1 case credit, daily drill practice across the 550+ bank, and a free resume review, with no card required. Signing up grants 1 case credit, so that first full case runs in Voice Mode for free. Pro is $49/month or $249/year. Road to Offer is AI-only: no human coaching, no hourly coaching rates, and no peer-matching marketplace. The trade is instant scored feedback on every rep instead of scheduling a partner.

4.5/5 from 242 in-app practice ratings in the 90 days preceding 20 September 2026. These ratings are separate from the selected written testimonials on our candidate reviews page.

“Since I started using it, my structuring is sharper, I'm faster under pressure, and I walk into cases with a repeatable process instead of winging it.”

“It tailored to my practice and the voice cases are useful and realistic. Helped me for my BCG R1.”

“I tried several resources to learn and practice cases, this one is clearly the best, without any doubt.”

“Had an interview for Bain was stressed and found this on some blogs. I recommend it’s been great so far!”

M

“After just a few weeks, I already feel more confident and better prepared, especially when tackling unfamiliar case prompts.”

“It’s a really good webpage to use, really intuitive and there is a lot of drills, tutorials, mock interviews to do.”

H

“Good product with varied drills to close skill gaps. Cases are also in the 2 usual consulting modes and in various industries.”

E

“I’ve done a lot of drills and it feels really natural the feedbacks are awesome.”

A

“Overall, RoadtoOffer gave me a much stronger level of preparation and helped me go into the interview feeling confident and ready.”

4.5

Worked Examples: The Five Calculations Every Case Math Drill Reduces To

A tool only helps if you already know the move. Here are the five calculations that nearly every case math question collapses into, each worked end to end with the arithmetic shown. Drill these until the setup is automatic, then let the AI time and grade you.

1. Percentage change. Revenue went from $80M to $100M. Growth = (new minus old) / old = (100 minus 80) / 80 = 20 / 80 = 0.25 = 25 percent. Business read: a 25 percent jump is large enough to ask whether it came from price, volume, or a one-off.

2. Growth rate over time (CAGR). $10M growing at 5 percent for two years = 10 × (1.05)^2 = 10 × 1.1025 = $11.0M. The fast in-interview shortcut: for small rates over a few periods, add the rate each year (5 + 5 ≈ 10 percent, so roughly $11M) and note you rounded down slightly because compounding adds a little more. For doubling time, use the Rule of 72: at 8 percent growth, money doubles in 72 / 8 = 9 years.

3. Breakeven. A machine costs $1,000,000. Each unit sells for $500 and costs $300 to make, so unit margin = 500 minus 300 = $200. Breakeven units = fixed cost / unit margin = 1,000,000 / 200 = 5,000 units.

Always state the unit: 5,000 units, not just "5,000." Interviewers dock points when you cannot say whether the number is units, customers, or dollars.

4. Profitability decomposition. Profit = revenue minus cost. A pharmacy fills 2.3M prescriptions at $87 net revenue each. Revenue = 2.3M × $87.

Drop zeros and decompose: 2.3 × 87 = (2.3 × 90) minus (2.3 × 3) = 207 minus 6.9 = 200.1, then add the six zeros back = about $200M. If costs are $170M, profit = 200 minus 170 = $30M, a 15 percent margin (30 / 200).

The decomposition step (split 87 into 90 minus 3) is the move that keeps you off the calculator.

5. Top-down market sizing. Size annual grocery spend in a city of 800,000 people. Penetration 70 percent = 560,000 shoppers. At 2.5 people per household, that is 560,000 / 2.5 = 224,000 households.

At $400 monthly spend: 224,000 × 400 = $89.6M per month, times 12 = about $1.08B per year. State every assumption aloud and sanity-check the final number against something you know (roughly $1B for a mid-size city is plausible).

Now run three of those five calculation types against a timer and a grader, on numbers you have not seen.

Which mental math apps help with consulting math?

The mental math apps that help most with consulting math time you on case-style prompts and check the setup, not just the final number. Generic arithmetic trainers build raw speed but skip units and business meaning, so pair them with a consulting-specific rep such as Road to Offer's timed Quick Math or the Math Drill above, or prompt ChatGPT or Claude with the grading rules in the prompts section below. If you want a free consulting math practice app, start with the free Math Drill and the shortcuts in mental math for case interviews.

Mental Math Shortcuts That Make the Drills Faster

Speed is a motor skill. These are the shortcuts consultants actually use, and the ones to bake into your reps before you let any AI time you. For the formulas behind them on one page, keep the case math cheat sheet open while you drill.

• The 10 percent and 1 percent anchors. 10 percent of any number is the number with one digit shifted. 10 percent of $160M = $16M, 5 percent is half that ($8M), 1 percent is $1.6M. Build any percentage from these anchors: 17 percent of $160M = 10 percent + 5 percent + 2 percent = $16M + $8M + $3.2M = $27.2M.
• Round, but never by more than about 10 percent. To multiply 398 × 21, do 400 × 20 = 8,000, then adjust. Rounding 17 percent to 20 percent for a quick pass is fine; rounding 17 percent to 10 percent distorts the answer too far.
• Decompose, do not grind. 24 × 18 = (24 × 10) + (24 × 8) = 240 + 192 = 432. 200 × 125 = (200 × 100) + (200 × 25) = 20,000 + 5,000 = 25,000.
• Drop zeros, track them with labels. 5 × 30M is 5 × 3 = 15 with seven zeros = 150M. Write the zeros back at the end so you do not lose them mid-calculation.
• Memorize fraction-to-percent conversions. 1/8 = 12.5 percent, 1/6 ≈ 16.7 percent, 1/3 ≈ 33 percent, 1/7 ≈ 14 percent. They turn ugly division into a lookup.

For a deeper drill set on these techniques, see the mental math for case interviews breakdown and the case interview math practice drill bank.

Copy-Paste Prompts That Make ChatGPT, Claude, and Gemini Useful

Generic prompts produce arithmetic, not case math. The five below force the AI to grade like a real interviewer. Copy them as written and swap the industry for one you are targeting.

Prompt 1: Profitability math drill

Act as an MBB interviewer. Give me a profitability case math problem set in the US specialty pharmacy industry with messy numbers (use figures like 2.3 million prescriptions filled, $87 average net revenue per prescription, 18 percent rebate compression). Time me at 60 seconds.

After I answer, grade four things: did I write the formula, did I calculate in clean stages, did I carry units, did I explain what the number means for the client.

Be strict. Do not say "great job" unless the answer would actually land in an interview.

Prompt 2: Growth rate (CAGR) drill

Generate ten compound annual growth rate problems with messy starting and ending values across five different industries. After each, ask me to estimate the CAGR before showing the exact answer. Penalize me if I do not state the formula and units before computing.

Prompt 3: Breakeven drill

Give me a breakeven analysis problem for a SaaS company with realistic fixed and variable costs. Walk me through the equation I should write before I compute. Then time me at 45 seconds for the calculation.

Grade whether my breakeven number is interpreted as units, customers, or revenue.

Prompt 4: Sensitivity drill

Here is a profitability scenario: revenue $1.2B, cost base $940M, three cost drivers (labor 45 percent, materials 30 percent, overhead 25 percent). Drill me on what happens to operating margin if labor rises 7 percent, materials rise 12 percent, and overhead falls 4 percent. After each chained calculation, grade my arithmetic and my business statement.

Prompt 5: Market sizing drill (Gemini for the inputs)

Give me five top-down market sizing problems across consumer goods, B2B SaaS, healthcare, energy, and retail. Use current, realistic numbers. For each, ask me to state assumptions, do the staged calculation aloud, and translate the final number into a business statement.

Penalize me if I forget units or skip the sanity check.

Use these prompts daily for high-volume practice. Then run one weekly Road to Offer Math Drill and review your working alongside the returned feedback.

Where Does Free AI Fall Short for Case Math?

Three failure modes show up when candidates rely only on the general models.

1. Overly agreeable feedback. General AI can praise a weak setup, even with strict prompts. Workaround: ask for specific failure modes ("tell me three things I did wrong") instead of "how did I do."

2. Progress needs a record. Keep a short error log with the problem, your answer and the correction. Do not assume a chat remembers earlier mistakes or that a numeric score identifies which reasoning checkpoint needs work. Choose the next rep from the pattern in your own record.

3. Hallucinated intermediate numbers. On long sensitivity or profitability chains, the general models occasionally drop a digit, swap units, or invent a number that was not in the prompt. Check every intermediate step regardless of the model. Rebuild the chain yourself before trusting the answer.

The stack: free AI daily for volume, Road to Offer's Math Drill for the weekly graded rep, and a coach for two or three final-round calibration sessions. Road to Offer's free tier gives you 1 full AI-graded case, daily drill practice, one free resume review, plus the first two BCG Casey-style simulator questions with no account.

How Do You Build a Free Math Practice Routine?

A working free routine looks like this.

Total time: about 15 minutes a day. Total cost: zero. Covers percentage change, growth, breakeven, sensitivity, and market sizing in a balanced rotation.

For broader prep beyond math, pair this with the AI case interview practice guide and the free AI tools for case interview prep hub. To turn the prompts above into a repeatable system, see how to use ChatGPT for case interview prep.

For a curated platform comparison beyond math, see the best AI drill platform for MBB prep and best AI platform for consulting prep guides. Switching industries into consulting? Start with case interview prep for career changers.

Verdict

• Daily volume. ChatGPT or Claude can generate repeated free prompts within their current limits.
• Assumptions. Gemini can help source assumptions and Perplexity can build a pre-case primer.
• Consulting feedback. Road to Offer's Math Drill adds consulting-specific grading within the full prep platform described above. None replaces a real coach for final-round calibration.

Read the feedback and review your own explanation after a graded rep. A correct score is one checkpoint, not a complete assessment of interview readiness.

Start with one free graded case, or pick the skill you want to fix first.

Full Comparison Data

The complete tables and notes behind this comparison, kept in full for readers who want every price, policy and source detail.

Full table: Comparison: How the Five Tools Stack Up

Sources (checked July 18, 2026)

• Road to Offer Math Drill: start a free math drill
• ChatGPT: chatgpt.com (https://chatgpt.com/)
• Claude: claude.ai (https://claude.ai/)
• Google Gemini: gemini.google.com (https://gemini.google.com/)
• Perplexity: perplexity.ai (https://www.perplexity.ai/)
• IGotAnOffer, Case interview maths (formulas, practice problems, tips): igotanoffer.com (https://igotanoffer.com/blogs/mckinsey-case-interview-blog/case-interview-maths)
• RocketBlocks, Case interview math: rocketblocks.me/blog/case-interview-math.php (https://www.rocketblocks.me/blog/case-interview-math.php)
• CaseBasix, Case interview mental math guide: casebasix.com/pages/case-interview-mental-math (https://www.casebasix.com/pages/case-interview-mental-math)
• Firmsconsulting, Case interview math (mental math) tools, formulas and tips: firmsconsulting.com/quarterly/case-interview-math (https://firmsconsulting.com/quarterly/case-interview-math/)
• Hacking the Case Interview, Best AI Tools for Case Interview Practice (2026): hackingthecaseinterview.com/pages/best-ai-tools-case-interview-practice (https://www.hackingthecaseinterview.com/pages/best-ai-tools-case-interview-practice)

Related Guides

• AI Case Interview Practice Guide
• Mental Math for Case Interviews
• Free AI Tools for Case Interview Prep
• Best Case Interview Prep Platforms 2026