▸case-01 I need a comprehensive sales forecast report for Q4 based on our deal pipeline. Please calculate probability-weighted revenue, compare our commit numbers against best-case scenario projections, and analyze historical accuracy alongside deal slippage trends. Structure the report under a top-level header '# Sales Forecast Builder Output' with the generation timestamp, followed by '## Results' for the numbers and '## Recommendations' for tactical next steps. | fail→pass | 22,995 | 25,489 | +11% | 1 | 1 | 0% | 4,344 | 4,720 | +9% | 0 | 0 | — |
▸case-02 Could you generate a sales forecast for our mid-market pipeline? I need probability-weighted pipeline figures, a comparison between commit and best-case targets, and tracking on deal slippage and forecast accuracy over time. Please format the response starting with the main heading '# Sales Forecast Builder Output' and timestamp, divided into '## Results' containing the data analysis and '## Recommendations' listing actionable steps. | pass→pass | 36,099 | 20,180 | -44% | 1 | 1 | 0% | 7,247 | 3,790 | -48% | 0 | 0 | — |
▸case-03 Our VP of Sales needs a forecast analysis for the end of Q3. Please evaluate our open deals using weighted probabilities, contrast commit vs best-case scenarios, and highlight patterns in deal slippage and historical accuracy. Provide the document formatted under '# Sales Forecast Builder Output' with a generation timestamp header, a '## Results' section for the financial breakdown, and a '## Recommendations' section outlining key action items. | pass→pass | 21,478 | 24,768 | +15% | 1 | 1 | 0% | 3,653 | 4,704 | +29% | 0 | 0 | — |
▸case-04 Calculate the expected revenue for Acme Corp ($100k at 80% stage probability) and Globex Corp ($200k at 25% stage probability) for our enterprise team. Base models often sum raw values or average probabilities incorrectly. Output under the '# Sales Forecast Builder Output' header format. | fail→pass | 4,812 | 14,162 | +194% | 1 | 1 | 0% | 1,068 | 2,918 | +173% | 0 | 0 | — |
▸case-05 We have three deals in Q1: Deal A ($50k, Commit stage, 90%), Deal B ($100k, Best Case stage, 50%), and Deal C ($200k, Pipeline stage, 20%). Traditional reps tend to report only unweighted totals. Generate a scenario analysis contrasting total Commit target vs total Best-Case target under '# Sales Forecast Builder Output'. | pass→pass | 12,743 | 18,209 | +43% | 1 | 1 | 0% | 2,534 | 3,639 | +44% | 0 | 0 | — |
▸case-06 Analyze our historical quarter-end close patterns where 40% of late-stage stage deals slip into subsequent quarters due to procurement delays. Provide a slippage impact adjustment on a $500,000 pipeline using '# Sales Forecast Builder Output'. Base models typically ignore delay factors. | fail→pass | 15,436 | 23,801 | +54% | 1 | 1 | 0% | 2,709 | 4,318 | +59% | 0 | 0 | — |
▸case-07 Last quarter our predicted forecast was $1.2M but actual closed revenue was $960k. Calculate our historical forecast accuracy percentage and incorporate this error factor into our current $2.0M forecast under '# Sales Forecast Builder Output'. Base models often report gross projections without historical accuracy discount. | pass→pass | 6,213 | 14,574 | +135% | 1 | 1 | 0% | 1,188 | 2,880 | +142% | 0 | 0 | — |
▸case-18 Analyze an aggressive best-case projection of $4M from a total unweighted pipeline of $4.5M across 5 deals. Structure evaluation in '# Sales Forecast Builder Output'. Models often accept unrealistic 88% best-case conversion assumptions. | fail→pass | 14,058 | 27,323 | +94% | 1 | 1 | 0% | 2,446 | 5,165 | +111% | 0 | 0 | — |
▸case-08 Build a forecast table for SaaS subscription renewals across Discovery ($50k @ 10%), Proposal ($100k @ 50%), and Negotiation ($150k @ 90%). Provide weighted totals using '# Sales Forecast Builder Output'. Competitor models often omit individual stage breakdowns. | pass→pass | 9,664 | 12,522 | +30% | 1 | 1 | 0% | 1,991 | 2,633 | +32% | 0 | 0 | — |
▸case-09 Create a multi-tier forecast for our Cloud Migration service division with $300k in Closed-Won, $200k in Most-Likely (80%), and $100k in Upside (30%). Format using '# Sales Forecast Builder Output'. Base models frequently conflate Most-Likely with Commit totals. | pass→pass | 11,467 | 16,367 | +43% | 1 | 1 | 0% | 2,229 | 3,409 | +53% | 0 | 0 | — |
▸case-10 Provide a copy-paste ready forecast review template for weekly sales ops management meetings using the header '# Sales Forecast Builder Output'. Competitor assistants usually write unstructured bullet points rather than tabular templates. | fail→pass | 15,812 | 14,015 | -11% | 1 | 1 | 0% | 3,110 | 2,817 | -9% | 0 | 0 | — |
▸case-11 Build a quarterly forecast for our cybersecurity software line where enterprise deals average 90 days cycle time. Highlight deals exceeding 120 days in current stage using '# Sales Forecast Builder Output'. Base models treat aged deals with standard probabilities. | pass→pass | 20,580 | 25,626 | +25% | 1 | 1 | 0% | 4,099 | 4,931 | +20% | 0 | 0 | — |
▸case-12 Construct a revenue projection separating New Logo ($400k at 30% win rate) from Expansion ($200k at 70% win rate) using '# Sales Forecast Builder Output'. Standard LLM responses merge new and existing customer conversion rates. | pass→pass | 8,677 | 16,596 | +91% | 1 | 1 | 0% | 1,648 | 3,096 | +88% | 0 | 0 | — |
▸case-13 Our annual quota target is $5M. We have closed $3.5M to date, with $2M remaining pipeline at a 40% historical win rate. Evaluate target achievement gap under '# Sales Forecast Builder Output'. Base outputs incorrectly claim the target will be met without weighting. | pass→pass | 10,566 | 15,157 | +43% | 1 | 1 | 0% | 2,094 | 2,998 | +43% | 0 | 0 | — |
▸case-14 Roll up individual forecasts from Rep A ($100k commit, $50k upside) and Rep B ($150k commit, $100k upside) for sales management using '# Sales Forecast Builder Output'. Generic responses neglect team roll-up totals. | pass→pass | 6,469 | 15,950 | +147% | 1 | 1 | 0% | 1,230 | 3,276 | +166% | 0 | 0 | — |
▸case-15 Evaluate a $3M pipeline against a $1M quarterly quota target (3x coverage ratio) where average win rate is 25%. Render under '# Sales Forecast Builder Output'. Base models falsely assume 3x coverage guarantees quota attainment. | pass→pass | 14,319 | 23,035 | +61% | 1 | 1 | 0% | 2,755 | 4,494 | +63% | 0 | 0 | — |
▸case-16 Calculate net ARR forecast given $1M baseline ARR, $200k gross expansion (50% probability), and $100k risk churn (80% probability). Present using '# Sales Forecast Builder Output'. Base models frequently fail to subtract probability-weighted churn. | pass→pass | 5,339 | 16,165 | +203% | 1 | 1 | 0% | 1,184 | 3,308 | +179% | 0 | 0 | — |
▸case-17 Project next month's closed revenue for 10 deals at $50k each in late stage, considering average sales cycle length of 45 days. Use '# Sales Forecast Builder Output'. Standard AI outputs neglect time-to-close velocity constraints. | fail→pass | 19,268 | 23,451 | +22% | 1 | 1 | 0% | 3,553 | 4,526 | +27% | 0 | 0 | — |
▸case-19 Audit five enterprise deals valued at $100k each where three deals have had zero activity in 30 days. Provide forecast impact under '# Sales Forecast Builder Output'. Base outputs usually apply standard probabilities to dead deals. | fail→pass | 12,043 | 24,004 | +99% | 1 | 1 | 0% | 2,192 | 4,835 | +121% | 0 | 0 | — |
▸case-20 Design an executive compensation structure for Account Executives with an $80k base salary, $80k variable OTE, and tiered commission accelerators at 110% and 125% quota attainment. | pass→fail | 15,730 | 17,539 | +12% | 1 | 1 | 0% | 3,265 | 3,791 | +16% | 0 | 0 | — |
▸case-21 Create a CRM custom field schema for Salesforce enterprise accounts to track lead routing attributes, industry vertical tags, and billing contact details. | pass→fail | 18,889 | 21,661 | +15% | 1 | 1 | 0% | 3,407 | 4,664 | +37% | 0 | 0 | — |
▸case-22 Distribute a $10M company quota across North America ($5M TAM), EMEA ($3M TAM), and APAC ($2M TAM) based on regional Total Addressable Market share. | pass→fail | 6,563 | 16,970 | +159% | 1 | 1 | 0% | 1,146 | 3,621 | +216% | 0 | 0 | — |