Raycaster / evalsAll benchmarks

Cross-benchmark category

SaaS Due Diligence

Compare AI agent runs for SaaS Due Diligence: prompts, scores, grades, and public traces. This page showcases APEX-Agents tasks that test whether AI agents can perform SaaS due diligence, including churn, CAC, ARR multiples, and product engagement analysis.

SaaS PE diligence AIChurn, CAC, ARR multiple, product engagement
56Tasks
4Primary
1Benchmarks

Published model evidence

A quick view of shareable runs in this category. Open task and trace pages for the prompt, response, files, and grading details.

gpt-5.4-mini50% pass

28/56 runs · avg score 60%

Gemini 3 Flash48% pass

11/23 runs · avg score 73%

GPT-5.443% pass

23/53 runs · avg score 56%

gpt-5.4-nano39% pass

22/56 runs · avg score 53%

Gemini 3.1 Pro39% pass

22/56 runs · avg score 50%

Kimi K239% pass

9/23 runs · avg score 55%

Primary tasks

4 tasks with this category as their main focus.

  1. SP Task 02 World 129APEX-Agents(task_4372ee27c60f4589884be8cc9d6d8bd8)1/2 · Fail

    Use the baseline seat utilization data against the attached 2025 strategic targets for the following two metrics. 1) What is the Seat Purchased Surplus (Actual Seats minus Target Seats) for the Mediu…

  2. Task 14APEX-Agents(task_0cc6381ab1db4902bdac1c95b3ffcc45)6/9 · Fail

    Can you use the feature usage file and identify the average adoption rate percentage, average monthly usage, and average retention impact score for each tier except Team? Print the output for me here.…

  3. Task o88f1452APEX-Agents(task_cb7189ae4502436085b4367bf7c64169)0/2 · Fail

    We need to redo the analysis of the new survey response dataset. Can you re-calculate the standard deviation for Brightpath Software's efficiency dataset? Using both the recalculated average efficie…

  4. Word_129_PJ_01 APEX-Agents(task_0233800d9daf4459bc464ce2f1f822a8)1/1 · Pass

    I want to forecast total annual revenue for ServiceNow based on the competition's price benchmarking information available to us. For this analysis, calculate revenue for each of their tier/plan (like…

Related tasks

52 tasks that also exercise this work as part of a broader assignment.

  1. CW134 Aditi 01APEX-Agents(task_11c9d4cb0cf3401b8de7cff9969fc223)8/8 · Pass

    For each of the four competitor firms use use our financial dataset for 2016 - 2025 to calculate the average customer acquisition cost (US$) for 2016-24 and identify the competitor with the highest ch…

  2. CW134 Aditi 03APEX-Agents(task_21b14fd7ec454ab38e07d2c4055d1fff)2/6 · Fail

    To better understand the market dynamics, the client wants to analyze customer engagement with the mobile app features. Use the feature dataset for competitors from 2016-24 to calculate the following …

  3. Law_World_434_sg_01APEX-Agents(task_981f4f72a55c4e7598b6f23f3e576e54)0/10 · Fail

    HarborView requires all customer documents to be sent to their offices in the Cayman Islands headquarters, including information of Hong Kong customers. We’ve also already sent them documents as part …

  4. LawWorld417_ANB_04APEX-Agents(task_075c6f8ffb1548508e94e67e4ba04bbb)1/1 · Pass

    Chasing Streams fired its entire facilities department and Head of Production before ParaZon acquired it. Sarah Rodriguez filed a Complaint on July 4, 2025 against ParaZon claiming not enough notice w…

  5. LawWorld417_AS_02APEX-Agents(task_43de2db73b5a4d899660f13394e80085)5/10 · Fail

    As you know, the new artist montage reel is a hit. Unfortunately, one of the artists featured is not a fan of the wardrobe upgrade - Mara Sings sent a takedown notice, and we initially complied, but w…

  6. LawWorld417_AS_03APEX-Agents(task_01fef67b5576468d854319d4d8a84988)5/7 · Fail

    As you know, “Bare Bones Decor” - Ava Kim’s limited series - is near completion. We have been collaborating with Ava on this production for months, with the understanding that Streams would retain the…

  7. LawWorld417_NE_06APEX-Agents(task_76c43bb44ab54ab8b42269303dedf83a)1/6 · Fail

    We will layoff our Head of Production Sarah Rodriguez as part of the upcoming merger. Please review Section IV of Sarah's layoff and WARN Notice and let me know if the language violates WARN. Answer t…

  8. LawWorld433_ANB_01APEX-Agents(task_de1ec76029b54126ae1105921e4202d4)3/3 · Pass

    Susan Whitaker has filed three successive Complaints against Magnolia Gardens. The first is the original Complaint, the second Is the First Amended Complaint, and the third is the Second Amended Compl…

  9. Shiva Task 01 World 129APEX-Agents(task_f69f5d19990b4292809009a331e1bbe9)2/3 · Fail

    Using the estimated market share chart and Brightpath customer segmentation, please calculate the potential revenue for the SMB Accounting segment if it achieved the target share. Include an analysis …

  10. SP Task 02 World 128APEX-Agents(task_18482ca6de9943ce814d70f2f742497f)3/3 · Pass

    I need to compare our results from the autonomous vehicle survey and the survey questionnaire against the attached 2025 launch targets. For these three metrics, calculate the percentage points gap bet…

  11. SP Task 03 World 129APEX-Agents(task_aac22560bcdc434eb7942bce0631d8bb)2/2 · Pass

    Can you use the files on Deal Win Rate Target and the transaction history in Brightpath Deal Transactions to determine the Implied Deal Volume required to reach the Expansion target share of revenue f…

  12. Task 4APEX-Agents(task_0a4ad19b76cf4602914e6b8a4f263690)3/3 · Pass

    For 2024 Won/Upsold deals with NCV ≥ 50k, determine the policy-friction risk per deal as NCV × Discount × tier multiplier × tier PFI, where tier PFI is the benchmark mix-weighted sum of Software Custo…

  13. Task 5k4j7555APEX-Agents(task_f23cb148241641f1b7c5dfbecfd3835f)0/1 · Fail

    Using the discount approval logs and the KPI chart, I'd like to get one number that tells me how risky our discounting behavior is right now. Looking at deals where the final approved discount exceede…

  14. Task 7APEX-Agents(task_593cb247c14e46b2afc4d1a810add11f)4/4 · Pass

    I would like to analyze the current proportion of Brightpath Churn and Annual Recurring Revenue. 1. Based on the ARR from the discount approval file and the Churned ARR from customer segmentation fi…

  15. Task he84c0f2APEX-Agents(task_a138d5329a0a494996a505f2adda0a65)6/6 · Pass

    Use the churn and WinLoss data, and assume the following: - Competitor Loss Ratio = (Total Contract Value of Lost deals/Total Contract Value of all deals) - If competitor-lost deal value exceeds the…

  16. Task jhp9ccb4APEX-Agents(task_a7c1daf7049b46ada402eada03ad7865)2/3 · Fail

    A real-time Rapid Response Content (RRC) update is automatically delivered and it causes performance degradation in a customer’s environment. The customer did not stage deployments, had no rollback pl…

  17. W134 Nancy Task 06APEX-Agents(task_4abd78ac38024a0094fa9ae0cfd31625)3/5 · Fail

    Create a new slide pptx, summarizing the comparable SaaS deals' target company name, purchase price, ARR, and ARR multiple. Include all targets for which we have an individual case study and use only…

  18. W134 Nancy Task 07APEX-Agents(task_d46f8183d88541c8ab7f2692aca28b5f)0/2 · Fail

    The LATAM market customer count is expected to continue growing at its 2024-2025B CAGR. Complisure could capture a quarter to half of the two largest LatAm players’ latest share of customers if they w…

  19. W134 Nancy Task 09APEX-Agents(task_56967ae9f77e42eeb5a0a5a272b34fe5)1/2 · Fail

    If competitors continue growing by their 2021-2024 revenue CAGR, while their operating margin % stays flat from 2025, which players will have better operating income than CompliSure by 2030? How much …

  20. W134 Nancy Task 10APEX-Agents(task_2bd66e1e194a4ce89ccf6432cbdce451)2/2 · Pass

    Can you use the customer usage and customer contracts files to state the impact on ARR and the new ARR if Complisure switches to the attached usage-based pricing model? Treat the payment discounts fr…

  21. W134 Nancy Task 11APEX-Agents(task_2fad87f261ae44d487187d8b737e11c5)4/4 · Pass

    Based on the attached table, with the asking price for each company, which competitors would have a higher 2024 ARR multiple than CompliSure even if their SMB customer count declined by 75%? State the…

  22. World 129_CY_Task 2APEX-Agents(task_4bdc188e9a7f4860b818c3cb3013e676)0/3 · Fail

    Refer to the latest (v1.0) customer segmentation data and the final pricing model. Calculate the % change of Customer Segmentation expected revenue (use target customers and average ARR for the pricin…

  23. World 129_CY_Task 3APEX-Agents(task_66b157482bf640cbb5c1725765e6ca9e)0/4 · Fail

    Using the latest pricing version, the revenue data by segment, and the discount approval logs, determine the average discount percentage for each of the Business and Growth tiers separately (use the m…

  24. World 129_CY_Task 5APEX-Agents(task_1e19e170dbac46ae98a24930a70b4b73)1/1 · Pass

    Using the latest renewal / churn data (v1.0) and pricing log, identify the average seat changes (increase or decrease) by Brightpath customers from every renewal with seat changes. When doing the calc…

  25. World 129_CY_Task 6APEX-Agents(task_d8d2c6bd61d548cba10f59af2d6c9559)8/8 · Pass

    Using Brightpath's Discount Approval Logs, review each approver’s total score and rank. Reply to me with a short message here, outlining your findings. Scores are determined using four criteria: 1. …

  26. World 134 Nancy Task 02APEX-Agents(task_3763fab0373b4f59a98f11a97eedcb15)0/1 · Fail

    If CompliSure experiences the changes outlined in the attachment starting in 2026, what is the expected impact to free cash flow in 2030? Assume Interest Expense remains the same % of EBIT, and Inco…

  27. World 134 Nancy Task 04APEX-Agents(task_b7b8e91422ef483f8464df1538f575e8)1/7 · Fail

    We anticipate the following developments in 2026: 1) Market growth is forecast to stall to 0% over 2025 market size (per our latest 5 year forecast, which also includes all required CompliSure financ…

  28. World 134 Nancy Task 05APEX-Agents(task_683366bd76004f968ebfc93828c076bc)0/6 · Fail

    Assume a scenario where CompliSure can achieve best-in-class R&D rates (low) and gross margin rates based on 2024 competitor benchmarks for years 2025 through 2030, if best-in-class is better than the…

  29. World 134_RG_01APEX-Agents(task_ded0b246614049ab85ad985d45e44a30)1/1 · Pass

    Estimate and provide the Manufacturing SOM for CompliSure for the year 2035. Use the 2025-29 CAGR from the manufacturing SAM forecast in the vertical deep-dive manufacturing report as a constant annua…

  30. World 134_RG_02APEX-Agents(task_749eeedb6a2b4a8a98ddd46fed5ac7b7)0/1 · Fail

    Calculate overall customer sentiment score using the customer surveys. For each section, compute the section sentiment score as the simple average of the available question-level scores within that se…

  31. World 134_RG_03APEX-Agents(task_a1449f78d0c3427e9b34e65a08621976)0/1 · Fail

    Can you please help me re-evaluate and state the adjusted 2030 net income for Complisure? The 2030 adjusted net income will be based on the three key assumptions: 1) New Sales and marketing spend, a…

  32. World 134_RG_04APEX-Agents(task_d87f70c7f8d74665ac3ddcbef5a8d67a)0/6 · Fail

    One of CompliSure’s primary competitors, TrainIQ, is expected to lose a portion of its market share. Use the estimates provided by each research firm (A, B, C), provided in the attached report, as sep…

  33. World 134_RG_05APEX-Agents(task_f029be9cd145432599e5627d4111af24)0/3 · Fail

    Based on the attached findings from the top 3 research firms, what is CompliSure’s expected revenue ($M) in 2030 for each scenario? For each scenario, please assume that the overall market size in 20…

  34. World224_OS_Task01APEX-Agents(task_dc0a54118f21451f891311e869b1847c)0/1 · Fail

    Return the Year 1 - Year 5 CAGR for Adjusted EBITDA. Round to two decimal places and display percentages with %. Write your answer straight back. I want you to use this info to update values in the …

  35. World224_OS_Task02APEX-Agents(task_db355b58e80749a1879a9d79681d05cc)1/4 · Fail

    I want you to tell me for Year 1 - Year 5: (1) Total revenue CAGR(2) Subscription Cost of Revenue CAGR (3) Sales and Marketing Expenses CAGR (4) EBITDA CAGR But first adjust revenue growth rate to be…

  36. World224-HS-11APEX-Agents(task_2299b89dcaf64a4da4f3d03f8aac7215)0/3 · Fail

    Assess if the sponsor can still meet the 20% IRR target at the Year 5 exit, given higher cost of revenues. 1. Increase subscription cost as % of subscription revenues by 1 percentage point in Year 1,…

  37. world415_aeu_01APEX-Agents(task_7952b3923473458ab7c415da7be74810)4/10 · Fail

    We want to get ahead of preparing a settlement agreement for the Delta matter. Can you let me know which of Delta’s original causes of actions are no longer live as we head into the pre-trial conferen…

  38. World415_DM_01APEX-Agents(task_3fa64829d31f43348113cc74f457b3ec)3/3 · Pass

    MLT is a CrowdStrike customer severely affected by the outage. MLT filed a lawsuit for negligence seeking to recover damages arising from the outage. Additionally, MLT successfully transferred venue t…

  39. World416_DM_01APEX-Agents(task_68bcf4d7fc5045b58045dc9f2f23ce5c)0/3 · Fail

    Due to a riot occurring in response to an Executive Order that resulted in the closure of its factories, TAC sought relief from performance under the force majeure section of the Master Supply Agreeme…

  40. World418_AH_01APEX-Agents(task_4c76ef32414a490ebdf5a68aac57e6ca)1/1 · Pass

    Review the shipbuilding contract ("Contract") and draft assignment agreement for the Contract (the "Assignment"). The Assignment will be used by LNG SHIPPING INC. ("LNG") to assign the Contract to its…

  41. World418_BA_01APEX-Agents(task_9509d6400e0c4e67a2222316744e7ded)2/10 · Fail

    Does any agreement between us and BlueAnchor create any non-disclosure obligations preventing our owner from publicly announcing the deal? Write me a short reply back that I can review and send.

  42. World418_EK_01APEX-Agents(task_08c22c6bd072423284c2da7fb190b8bd)3/5 · Fail

    Does assigning the shipbuilding contract to the JV require any other member consents (under the JV Operating Agreement) that we don't already have? Write out your answer to me here, and give a short …

  43. World418-TK-02APEX-Agents(task_3bb0664007a140a981193fb43ba1be7b)1/1 · Pass

    Can you please let me know if the canceling date of the shipbuilding contract is 180 days? Just a quick yes or no here is fine.

  44. World418-Tk-03APEX-Agents(task_f1998108c25b4e448ec6cdce9f40321e)2/2 · Pass

    BlueLNG sued Nakamura in the Southern District of New York based on the shipbuilding contract. Given that Nakamura has no office in the district, can BlueLNG seek Rule B attachment of a US$ wire trans…

  45. World419_AH_03APEX-Agents(task_c24da23b0e1042238997125c77506557)0/2 · Fail

    On November 20, 2024, the M/V Red Room struck a submerged object on the bed of the Ohio River. The Incident resulted in a hull breach and the discharge of crude oil into the Ohio River. During subse…

  46. World420_SF_02APEX-Agents(task_d06f10ebd2ad4bb19ba47b00a590dd54)2/2 · Pass

    Livyra has decided to pay its independent contractors a fixed salary, consistent with fair market value, to sell Bencontra that is payable by government healthcare. Each independent contractor is give…

  47. World431_amk_01APEX-Agents(task_c7fc2009b5b849b4b769f0eafe64f461)0/2 · Fail

    MGR Real Estate Inc. (the "Lessor") and "AI Automation Group, LLC" (the "Lessee") entered into the final lease agreement on December 5, 2025 for 2020 Main Street, Irvine, CA (the "Premises"). On De…

  48. World431_DM_04APEX-Agents(task_cba85c18cb7c456da8497c1018c75b16)0/3 · Fail

    MGR Real Estate Inc. ("MGR") and "AI Automation Group, LLC" ("AIAG") entered into a letter of intent (“LOI”) on December 2, 2025 for 2020 Main Street, Irvine, CA (the "Building"). The letter included …

  49. World431_JS_04APEX-Agents(task_78b12b856287427d86e75dadc6ffa465)0/5 · Fail

    MGR REAL ESTATE INC. (The "Lessor") is leasing 2020 MAIN STREET, IRVINE, CA (The "Premises") to AI AUTOMATION GROUP, LLC (The "Lessee"). The Lessee asked their lawyers to identify provisions that are …

  50. World433_JS_01APEX-Agents(task_be78a90e872547eea75915f95ca35739)3/3 · Pass

    Magnolia Gardens has a contract with the Texas Department of Human Services (DHS) to provide services, as an assisted living facility, to DHS clients. Gregory Johns--a disabled DHS client who is in a …

  51. World434_JS_03APEX-Agents(task_c31f5ccdfdd948ac8142f47890aec9e1)3/3 · Pass

    During acquisition diligence, Apex Storage Asia Pte. Ltd. (the "Landlord") notifies of a claim it has just received from a tenant. The Landlord has a lease for part of one of its Singapore properties …

  52. World434-TK-01APEX-Agents(task_27a6c866aa224da5aeefc17533019924)1/3 · Fail

    Post-closing, the Fire Department issued a fine for pre-completion non-compliance at one of the facilities, and the buyer paid the fine to avoid operational disruption. Take a look at the Secure Box…