data/data.csv

task_id,task_name,world_id,domain,prompt,task_input_files,expected_output,gold_response,gold_response_type,rubric
task_5ed3c6dd_purelife_uk,World132DATask08,world_d5110661,Management Consulting,"PureLife needs a validated UK market potential calculation for its vitamins and dietary supplements business. The current approach relies only on consumer behaviour metrics and overlooks the UK market's documented growth trajectory. Using PwC's research report shows the market is expanding faster than historical trends. Recalculate market potential by combining consumer behaviour inputs with PwC's growth insights to provide a forward-looking figure for strategic decisions. The final answer should be formatted to US$, rounded to 2 decimal points. Present your findings as a short reply here.",null,message_in_console,"The 2025 UK New Market Potential is $281.18.",text,"criteria: States the 2025 UK New Market Potential is $281.18; criteria: mentions forward-looking or growth-adjusted figure"
task_pharma_us_drug_market,World132DATask09,world_d5110661,Healthcare,"PharmaCo needs a validated US market potential calculation for its new oncology drug. The current approach relies only on diagnosed patient numbers (2.1M patients, $180 avg spend) and overlooks the market's documented CAGR. WHO's research indicates an 8.5% CAGR for oncology treatments. Recalculate the 2025 market potential by applying the growth rate to the base figure. Format as US$, rounded to 2 decimal points.",null,message_in_console,"The 2025 US Oncology Market Potential is $500.00.",text,"criteria: States the 2025 US Oncology Market Potential is $500.00; criteria: references CAGR or growth adjustment"
task_saas_tam_sizing,World212TAMTask01,world_a2231abc,Technology,"NovaSoft is sizing its Total Addressable Market (TAM) for B2B SaaS HR tools in North America. There are 1.2M SMBs (10-500 employees) in the region. Industry benchmarks show 22% are actively seeking HR software, with an average contract value of $4,200/year. Using a top-down market sizing approach, calculate the TAM. Format as US$ million, rounded to 2 decimal points.",null,message_in_console,"The North America B2B HR SaaS TAM is $110.88 million.",text,"criteria: States TAM is $110.88 million; criteria: uses top-down methodology with 22% adoption rate and $4,200 ACV"
task_realestate_cap_rate,World090RETask03,world_r9090zz,Real Estate,"UrbanAssets is evaluating a commercial property in Chicago. The property generates $840,000 in annual gross rental income with a 12% vacancy rate. Operating expenses (excluding mortgage) total $215,000/year. Comparable properties in the submarket trade at a 6.5% cap rate. What is the implied property value based on NOI and the market cap rate? Format as US$ million, rounded to 2 decimal points.",null,message_in_console,"The implied property value is $9.56 million.",text,"criteria: States implied value is $9.56 million; criteria: correctly applies NOI divided by cap rate; criteria: accounts for vacancy deduction"
task_dcf_terminal_value,World310FINTask05,world_f3100qq,Finance,"GreenTech Corp has stabilized EBITDA of $42M, growing at 2.5% in perpetuity. The WACC is 9.8% and tax rate is 26%. Using a Gordon Growth Model for terminal value (on EBIT after-tax, no D&A adjustments), calculate the terminal value. Format as US$ million, rounded to 2 decimal points.",null,message_in_console,"The terminal value is $429.65 million.",text,"criteria: States terminal value is $429.65 million; criteria: uses Gordon Growth Model; criteria: applies perpetuity growth rate of 2.5%"
task_logistics_breakeven,World180OPSTask02,world_o1800pp,Operations,"FleetCo operates last-mile delivery with fixed costs of $2.4M/month and variable cost of $3.80 per delivery. They charge $6.20 per delivery. How many monthly deliveries are required to break even? Round to the nearest whole number.",null,message_in_console,"FleetCo needs 1,000,000 deliveries per month to break even.",text,"criteria: States 1,000,000 deliveries; criteria: correctly divides fixed cost by contribution margin of $2.40"
task_cac_ltv_ratio,World220CRMTask04,world_c2200mm,Marketing,"RetailPulse acquires customers at $85 CAC. Average order value is $120, purchase frequency is 3.2x/year, gross margin is 45%, and average customer lifespan is 4 years. Calculate LTV and the LTV:CAC ratio. Report both values separated by a comma, formatted to 2 decimal points.",null,message_in_console,"LTV: $691.20, LTV:CAC Ratio: 8.13",text,"criteria: States LTV of $691.20; criteria: States LTV:CAC ratio of 8.13; criteria: uses gross margin in LTV calculation"
task_fx_hedging_exposure,World400FXTask06,world_x4000rr,Treasury,"GlobalMfg has EUR 15M in payables due in 90 days. Current EUR/USD spot is 1.0820. A 90-day forward contract is priced at 1.0875. If they hedge fully using the forward, what is the USD cost of hedging vs. leaving it unhedged at spot? Report the hedging premium in USD, rounded to 2 decimal points.",null,message_in_console,"The hedging premium is $82,500.00.",text,"criteria: States hedging premium is $82,500.00; criteria: calculates difference between forward and spot rates applied to EUR 15M notional"
task_ebitda_margin_target,World500CONTask07,world_k5000ss,Management Consulting,"TechRetail has revenue of $340M and current EBITDA of $28.9M. The board targets an EBITDA margin of 12% within 2 years. What incremental EBITDA improvement (in $M) is required? Round to 2 decimal points.",null,message_in_console,"TechRetail requires an incremental EBITDA improvement of $11.90M.",text,"criteria: States incremental EBITDA of $11.90M; criteria: correctly calculates 12% of $340M minus current $28.9M"
task_workforce_productivity,World600HRTask08,world_h6000tt,Human Resources,"ManuCo employs 2,400 workers producing 18M units/year. Industry benchmarks show best-in-class facilities achieve 9,200 units/worker/year. If ManuCo reaches benchmark productivity with the same headcount, what is the projected annual output? Format as millions of units, rounded to 2 decimal points.",null,message_in_console,"Projected annual output is 22.08 million units.",text,"criteria: States 22.08 million units; criteria: multiplies 2,400 workers by 9,200 units/worker benchmark"
dynamic_filing_73b00375,Filing_QA_27a0,world_filing,Finance,"What is the par value per share of Amazon.com, Inc.'s common stock as stated in the filing? Format as US$ per share.",,message_in_console,"The par value per share of Amazon.com, Inc.'s common stock is $0.01.",text,criteria: States the correct par value; criteria: includes unit (US$ per share).
dynamic_filing_0cf8d936,Filing_QA_5a7a,world_filing,Operations,"What is the I.R.S. Employer Identification Number (EIN) for Amazon.com, Inc. as listed in the filing?",,message_in_console,"The I.R.S. Employer Identification Number for Amazon.com, Inc. is 91-1646860.",text,criteria: States the correct 9-digit EIN; criteria: no additional characters or formatting.
dynamic_filing_b49b6dc4,Filing_QA_7757,world_filing,Finance,"For how many months has Amazon.com, Inc. been subject to the filing requirements under Section 13 or 15(d) of the Securities Exchange Act of 1934, based on the check mark in the filing?",,message_in_console,"Amazon.com, Inc. has been subject to the filing requirements for the past 12 months.",text,criteria: States the correct duration (12 months or shorter period); criteria: references the filing requirement explicitly.
dynamic_filing_4c1129fe,Filing_QA_1a7d,world_filing,Finance,"Calculate the par value of Amazon.com, Inc.'s common stock based on the filing. Format as US$ per share.",,message_in_console,"The par value of Amazon.com, Inc.'s common stock is $0.01 per share.",text,criteria: States the correct par value; criteria: specifies the unit (US$ per share)
dynamic_filing_d48220e3,Filing_QA_df7d,world_filing,Operations,"Determine the IRS Employer Identification Number (EIN) for Amazon.com, Inc. as listed in the filing.",,message_in_console,"The IRS Employer Identification Number for Amazon.com, Inc. is 91-1646860.",text,criteria: Provides the exact 9-digit EIN; criteria: no additional characters or formatting errors
dynamic_filing_578d6b0c,Filing_QA_7a37,world_filing,Finance,"Identify the Commission File Number assigned to Amazon.com, Inc. in this SEC filing.",,message_in_console,"The Commission File Number for Amazon.com, Inc. is 000-22513.",text,criteria: States the correct 10-digit file number; criteria: includes leading zeros if present
dynamic_filing_d4f1a829,Filing_QA_6399,world_filing,Finance,Calculate the total number of years from the earliest to the latest maturity date of Alphabet Inc.'s Senior Notes listed in the filing. Format as a whole number.,,message_in_console,The total number of years from the earliest to the latest maturity date is 25 years.,text,criteria: Correctly identifies the earliest and latest maturity years; criteria: Accurately calculates the difference in years.
dynamic_filing_c4b3c06e,Filing_QA_8aab,world_filing,Finance,"What is the weighted average coupon rate of Alphabet Inc.'s Senior Notes listed in the filing, assuming equal issuance amounts for each note? Format as a percentage rounded to two decimal places.",,message_in_console,The weighted average coupon rate is 266.15%.,text,criteria: Correctly sums the coupon rates; criteria: Divides by the correct number of notes; criteria: Rounds to two decimal places.
dynamic_filing_a6820024,Filing_QA_3b62,world_filing,Operations,Determine the number of distinct classes of common stock (excluding Senior Notes) registered by Alphabet Inc. under Section 12(b) of the Act. Format as a whole number.,,message_in_console,The number of distinct classes of common stock is 2.,text,criteria: Correctly identifies and counts the distinct classes of common stock; criteria: Excludes Senior Notes from the count.
dynamic_filing_1a2c3cff,Filing_QA_2544,world_filing,Finance,Calculate the total number of years from the earliest to the latest maturity date of Alphabet Inc.'s Senior Notes listed in the filing. Format as a whole number.,,message_in_console,The total number of years from the earliest to the latest maturity date is 25 years.,text,criteria: Correctly identifies the earliest and latest maturity years; criteria: Accurately calculates the difference in years.
dynamic_filing_c137f6b3,Filing_QA_5caf,world_filing,Finance,"What is the coupon rate of the Senior Notes due in 2054 as listed in the filing? Format as a percentage with two decimal places (e.g., 4.00%).",,message_in_console,The coupon rate of the Senior Notes due in 2054 is 40.00%.,text,criteria: Correctly identifies the coupon rate for the 2054 Senior Notes; criteria: Formats the answer as a percentage with two decimal places.
dynamic_filing_a558f1e9,Filing_QA_4cf2,world_filing,Operations,How many distinct classes of common stock (excluding Senior Notes) are registered by Alphabet Inc. under Section 12(b) of the Act? Format as a whole number.,,message_in_console,Alphabet Inc. has 2 distinct classes of common stock registered.,text,criteria: Correctly counts the distinct classes of common stock; criteria: Excludes Senior Notes from the count.
dynamic_filing_9fcb9754,Filing_QA_f17f,world_filing,Finance,Calculate the total number of years from the earliest to the latest maturity date of Alphabet Inc.'s Senior Notes listed in the filing. Format as a whole number.,,message_in_console,The total number of years from the earliest to the latest maturity date is 25 years.,text,criteria: Correctly identifies the earliest and latest maturity years; criteria: Accurately calculates the difference in years.
dynamic_filing_2054822c,Filing_QA_5aeb,world_filing,Finance,"What is the weighted average coupon rate of Alphabet Inc.'s Senior Notes listed in the filing, assuming equal issuance amounts for each note? Format as a percentage rounded to two decimal places.",,message_in_console,The weighted average coupon rate is 2.75%.,text,criteria: Correctly lists all coupon rates; criteria: Uses the formula for weighted average with equal weights; criteria: Rounds to two decimal places.
dynamic_filing_544a3411,Filing_QA_fcc4,world_filing,Operations,"Determine the par value of Alphabet Inc.'s Class A Common Stock and Class C Capital Stock in US dollars, given the par value per share and assuming 1 million shares outstanding for each class. Format as US$ million.",,message_in_console,"The total par value for each class is US$ 1,000.",text,criteria: Correctly identifies the par value per share; criteria: Accurately calculates total par value for 1 million shares; criteria: Converts to US$ million.