Raycaster / evalsAll benchmarks

Cross-benchmark category

Infrastructure Finance

Compare AI agent runs for Infrastructure Finance: prompts, scores, grades, and public traces. This page showcases APEX-Agents tasks that test whether AI agents can analyze infrastructure finance scenarios, project debt, sovereign guarantees, and restructuring outcomes.

Project finance AIHydro debt, sovereign guarantee withdrawal, restructuring scenarios
49Tasks
26Primary
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.

Gemini 3 Flash50% pass

2/4 runs · avg score 81%

GPT-5.448% pass

10/21 runs · avg score 58%

gpt-5.4-mini45% pass

22/49 runs · avg score 56%

gpt-5.4-nano43% pass

21/49 runs · avg score 52%

gpt-5.539% pass

19/49 runs · avg score 49%

Gemini 3.1 Pro35% pass

17/49 runs · avg score 45%

Primary tasks

26 tasks with this category as their main focus.

  1. World 127 TJ Task 3.0APEX-Agents(task_1d41b5f121724ec6bd9e22efba29f969)3/6 · Fail

    Let's calculate how much capex is not spent due to supply chain delays and how that affects Helios' total cash position. Based on the assumption that only 80% of capex is spent during 2026-2027, the…

  2. World 131_MK_Task 1APEX-Agents(task_ec97a505112645f9b266df1954f2738d)0/2 · Fail

    Assuming Eurogrid goes through with the labor reallocation efforts described in the operational efficiency analysis, calculate both the % of total staff that is a manager and the average span of contr…

  3. World 131_MK_Task 2APEX-Agents(task_4b3c2dfc4d164a25831e8787397766c3)4/4 · Pass

    Identify the region with the highest average asset-level Total Score (defined as the sum of Criticality Score, Renewable Impact, and Risk Score), and the country within that region that has the highes…

  4. World 131_MK_Task 3APEX-Agents(task_ee6e8c8f7075427ba5381c453a14c71c)0/5 · Fail

    Please use EuroGrid's headcount per department and the attached benchmarks to calculate the estimated total cost of each of the departments' headcount. Round all final amounts to full USD. Provide yo…

  5. World131_acd_task09APEX-Agents(task_c0476484bd64414f87f46f1868cde2f1)0/3 · Fail

    EuroGrid wants to understand whether the root cause of its asset failures can be explained by age, load, and/or frequency of weather events. Identify the 3 manufacturers with the highest total failur…

  6. World131_acd_task10APEX-Agents(task_5b0050f41fc9495fa8c34b69f1184418)9/9 · Pass

    Take a look at our workforce distribution in the country where we've spent the most on OPEX from 2020-24. Knowing we need 2 line technicians per transmission line, 1 substation technician for each sub…

  7. World131_acd_task11APEX-Agents(task_f32cf6dbffac45eea7454b4f3a62eaf9)0/2 · Fail

    Identify the Phase 1 Assets from the 10 Year Roadmap, assuming that SAIFI / SAIDI hotspots can be defined as assets having SAIFI > 1.0 and SAIDI > 60. Ignore the key criteria for substations and the n…

  8. World131_acd_task12APEX-Agents(task_f9f2907c268c44f686496a4934f1fc15)2/3 · Fail

    Looking only at projects in the Connection Queue that have a status of "Approved" or "Connected", calculate the percentage of the Total Forecasted Demand for the years 2026, 2027, and 2028 that could …

  9. World131_DV_02APEX-Agents(task_d55fe268d7f64a74aacfce4fc374ea96)6/6 · Pass

    Can you calculate the annual EU implied revenue for each Eastern European TSO? Use the midpoint of their implied market share ranges and 40 billion euros as the total market size. Using the implied r…

  10. World131_DV_03APEX-Agents(task_a179d38b095f46eba5eff7baf8f7fd87)0/1 · Fail

    Calculate the NPV from the 12-year cash flow on renewable enablement benefits, considering the following assumptions: - The steady-state annual benefits from renewable enablement mentioned in the busi…

  11. World131_DV_05APEX-Agents(task_9d99126a403e41838e1473d33884ed2f)1/2 · Fail

    Can you state the total simple average of the average implementation cost values, across the various technologies? Use the attached implementation cost deck. Also, state how many technologies have a t…

  12. World131_DV_06APEX-Agents(task_806c8178532944a78b78d565e4bc0313)5/5 · Pass

    What is the net aggregate annual benefit (i.e., total annual savings minus total annual opex) of all of the use cases in the digital use case sizing analysis? According to the new transmission technol…

  13. World131_IB_05APEX-Agents(task_699ea5ca3b0243a5852ad33e33043f12)5/6 · Fail

    Find out the ratio between Curtailment_GWh and Redispatch_GWh and for the lowest average ratio of Country-Region pair, report the average Avoided Curtailment (MWh) and causes of curtailment. Represen…

  14. World131_IB_Task 12APEX-Agents(task_0ea0001d6cb34cc6abf9bf6dc4e8e30b)0/2 · Fail

    Using the Digital Twin Input and Additional bus datasets, identify the Bus IDs associated with renewable energy generation. For each of these Bus IDs, calculate the average (in GW) of their three high…

  15. World131_MD_01APEX-Agents(task_55a201bd877a42eeb0e1868fb6a84230)4/4 · Pass

    Tell me whether or not the asset type that has the highest average adjusted failure probability per outage is also responsible for the highest average Value of Lost Load (VOLL) per asset. VOLL is defi…

  16. World131_MD_03APEX-Agents(task_7acc98cded8b49de972ee79b0461107e)3/3 · Pass

    Investigate whether EuroGrid should consider increasing staffing. Determine if the number of working people per impacted asset is correlated with the expected economic impact of unforeseen downtime in…

  17. World223_AV_03APEX-Agents(task_1ada04b9f9814985a1a7b11180268a0b)1/1 · Pass

    In the Accretion / Dilution Model, use the capital structure and shares outstanding assumptions for Solventum (SOLV) to calculate levered free cash flow and price per share. Specifically, use the foll…

  18. World226_RM_08APEX-Agents(task_6f51cd66e3ff43829ebf500e5000b821)0/3 · Fail

    Using the LBO model, I want you to tell me updated values for: (1) Implied Net Debt, (2) Sponsor Equity Value and (3) IRR for Year 5. # Assumptions -Increase the interest rate of the secured term loa…

  19. World227_SK_Task03APEX-Agents(task_13ced851b9914058b39c89c8b5ba7c84)0/1 · Fail

    You have the MFC model. Calculate the implied sponsor equity at entry in FY2032 and report it in Canadian dollars (C$), rounded to the nearest million. Respond by printing out back to me. Reference t…

  20. World227_SK_Task04APEX-Agents(task_13a13a4b392745dc8b3d1bbfabe06016)1/1 · Pass

    You have the MFC model. Calculate the Total Debt / EBITDA in FY2030 and report it in multiple, rounded to one decimal place. Print your answer to me here. Reference the "Refinancing (Option A +B)” ta…

  21. World227_SK_Task07APEX-Agents(task_35fdfa4a534f453596a6c565f619ceb1)0/2 · Fail

    Use the MFC model to reply to me with the updated Retained Cash and ending Long-term debt in FY2030 under the following assumptions. Report in Canadian dollars (C$), rounded to the nearest million. …

  22. World227_SK_Task08APEX-Agents(task_dd96690dde6f4cbf9094070249749128)0/1 · Fail

    Calculate an updated implied sponsor equity at entry with FY2032 exit. Use the MFC LBO model and the assumptions below: - Reduce the TL-B leverage multiple from 3.0x LTM EBITDA while lowering the yie…

  23. world227_tg_04APEX-Agents(task_706f2a4dccbb4042b3aa3b770f2a54c5)0/1 · Fail

    Muskrat Falls Corp's (MFC) owners have decided to pursue option A (Case 1), i.e. the debt refinancing only option, and hold MFC as an investment and selling at the end of FY35. Assume the following: …

  24. world227_tg_06APEX-Agents(task_eb21017fa7e347659719536490c87cba)0/1 · Fail

    Use the MFC model we made. MFC has chosen to proceed with a debt-only refinancing at market rates (Option A / Case 1). At the start of each year, it decides to issue new debt up to a maximum of 4.0x …

  25. world227_tg_07APEX-Agents(task_c5e7a9bdd82444c9aeb0cead96d8f5bd)1/1 · Pass

    Muskrat Falls Corp (MFC) has decided on a debt-only refinancing at market rates, i.e. Option A (Case 1 of the model "toggle") in the MFC model. MFC is valued at 12x EV / NTM EBITDA. Please calculate …

  26. world227_tg_08APEX-Agents(task_da562f15d91a4d4290026386d2aa1c47)1/1 · Pass

    Please use assumptions below for a more aggressive financial forecast, which is termed the "SuperUpside" case: - The drivers of the SuperUpside case adds to the "Upside" case the difference between t…

Related tasks

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

  1. SP Task 01 World 128APEX-Agents(task_976f61c9753f494a9ad012af60b3309c)6/6 · Pass

    Can you look at the target Operating Mode standards and the competitor benchmark file to determine if Tesla is adhering to the capital intensity safety limit? Identify the difference between this targ…

  2. World 131_MK_Task 4APEX-Agents(task_1f6c5b8814fa40bdb25ae11bbd48b6ea)0/4 · Fail

    Please calculate how much Germany's and Netherlands' renewables pipelines (will be only 95%) will cover out of their total yearly loads in 2027 and 2028 in % terms. You can use their average historica…

  3. 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…

  4. World 219_AE_Task05APEX-Agents(task_719041266bc54f8e951908414f467daf)4/4 · Pass

    What is the EV and implied share price of CNS in the DCF model using both Gordon growth model and exit multiple approach if each business segment grows as outlined below over the projection period of …

  5. World_131_JR_1APEX-Agents(task_1dba146a5da645b3a27ea3212c0bffc4)4/6 · Fail

    Can you please evaluate the outage causes that affect each country the most, in terms of total outage duration? Categorize hazards relating to flooding or storms as the "Weather - Storm" cause and tho…

  6. World223_SMN_04APEX-Agents(task_973f357750e2416c90f45be924d87d7f)2/4 · Fail

    Using the 3Q 2025 3M 10Q and the accretion dilution model, calculate the following deliverables. Present all values in millions ($mm), number of shares in millions (mm), and round to whole numbers. Fo…

  7. World223_SMN_08APEX-Agents(task_8a0a32869f0946778e60441c0f179867)1/1 · Pass

    Calculate the intrinsic value per share of Solventum based on these assumptions. Use the accretion dilution model. - Lower the gross margin % to 52% for the forecast period 2026E through 2029E. - Ch…

  8. world225_AV_02APEX-Agents(task_a9ce195e45104521ac830136c86d0f69)5/5 · Pass

    Calculate Unlevered Free Cash Flow in 2025E, 2026E, 2027E, 2028E and 2029E. In the Golden Everest Financial Model, there is an error in the unlevered free cash flow build in the Projections, "Project…

  9. World225_BS_01APEX-Agents(task_d0adb2b01a094703ac75fedc1063ff98)0/3 · Fail

    Using the REIT model, consider the following assumptions for the projected period between 2025 to 2029: 1) Assume the revenue growth for its service business equivalent to the overall company revenue …

  10. World225_DK_01APEX-Agents(task_bab7ecdcc5ea4263b7c389d9b5496c68)0/1 · Fail

    Perform a DCF analysis for Golden Everest using the REIT model with the following parameters: - Hold EBITDA margin constant at 42% throughout the projection period - Hold Capex % of Revenue constant a…

  11. World225_DK_02APEX-Agents(task_37b6798e55064707aebe9b0817434404)0/1 · Fail

    For each year, calculate Levered FCF less Dividends Paid. Assuming a 9% discount rate, output the net present value (NPV) of Levered FCF less Dividends Paid over the projection period, rounded to a f…

  12. World225_RL_Task02APEX-Agents(task_d2bd4721fff0492bb51cb73ddd300534)1/1 · Pass

    I want the Output Levered FCF for 2029E, rounded to the nearest million. - Revenue growth: starts at 7.0% and increases by 0.5% per year in the projection period - EBITDA margin %: starts at 44.0% and…

  13. World226_BS_01APEX-Agents(task_ae92292a5cfb4594ae8746ee31ce498b)5/6 · Fail

    Planet Fitness is looking to divest its entire 281 stores, which it owns as of September 30, 2025, to a franchise owner. Round all results to two decimal places and present it in $mm. Using the LBO m…

  14. World226_BS_02APEX-Agents(task_5b98bfe5ef1c4832808e8a7ba4a53aaa)0/7 · Fail

    Planet Fitness is considering the acquisition of 100% stake in The Gym Group and taking it private in order to expand its presence within the UK. Using GYM H1 2025 and GYM annual 2024 docs, consider…

  15. World226_RM_04APEX-Agents(task_06a33a12bddc482fbbb01ae1752e1907)1/3 · Fail

    Update the LBO model to include an incentive payment structure of PLTF management post-transaction. Assess the impacts on the 5-year LBO analysis. Management is eligible for these payments each year …

  16. World227_JZ_Task03APEX-Agents(task_fc96166d8f374e4eb8d4d15784904b8e)0/3 · Fail

    The Private Equity Sponsor wants to extract cash via a "Dividend Recapitalization" at the end of 2027. Using the MFC model, you must size the Maximum Special Dividend the company can pay while remaini…

  17. World227_SK_Task06APEX-Agents(task_26f6f89af455429dabf2318469bf05ef)1/1 · Pass

    Use the MFC model to return Implied Total Enterprise Value (in Canadian dollars, C$, rounded to the nearest million) under the following assumptions. 1. Refinancing + EPP - Decrease the Refinancing +…

  18. World227_SK_Task09APEX-Agents(task_367f5673fd4641c4b09fd7a42a90e050)0/1 · Fail

    Calculate a normalized market capitalization for AES using data from the comps file and the following approach: - Calculate the volume‑weighted average price (VWAP) for AES Corporation over the 250 t…

  19. world227_tg_02APEX-Agents(task_9b9afdd77d4240a5bb3c13e83182b91b)0/1 · Fail

    Using Option B in the MFC model, the refinancing in conjunction with a equity private placement (preferred stock), update to upsize the preferred tranche to $1.5bn and for interest to be payment-in-ki…

  20. world227_tg_05APEX-Agents(task_1554cbb3f927433da51a461ae918db31)1/1 · Pass

    Assume that Muskrat Falls Corp's (MFC) owners have decided on an LBO process. Blackstone has decided to bid for the business via its infrastructure fund. Please calculate Blackstone's "ability to pay"…

  21. world227_tg_09APEX-Agents(task_9df937d993034a0a89d4abe8f32d8868)1/1 · Pass

    Please calculate the total value of a MFC privatization by the provincial government at a bid value of 11x LTM EBITDA, which composes of both the (a) upfront proceeds from the sale and (b) value of th…

  22. World246_SM_01APEX-Agents(task_7d11f0f8a4ac415599f715647d2a09e4)3/3 · Pass

    Reply back to me with the following values: - Implied share price. - Enterprise value - % weight of PV of terminal value in the total new EV. To get to the right answer, update the WACC calculation …

  23. World434_AH_04APEX-Agents(task_5ee798d029884a06bb17787179206c7a)1/4 · Fail

    We had an intern prepare a list of what needed to be done after closing and they made a mess of it. We've already established the holding company, reviewed insurance policies, and completed a complia…