APEX-Agents · Investment Banking
World226_RM_01
APEX-Agents task World226_RM_01 in AI Agents for M&A Legal Due Diligence. Compare dual-harness agent runs across models — rubric criteria, scores, and public traces.
Task prompt
What the agent was asked to do
Update the LBO analysis tab "Copy of LBO". It needs to include a single potential add on acquisition in FY2027E. Assess the impacts on the 5-year LBO analysis. Use SOFR actual data. Add to that tab, the total debt, total enterprise value, and sponsor IRR. Round $ to millions and others to 1 decimal point. General assumptions: -Target EBITDA at time of acquisition is $41mm -Assume target EBITDA grows at the same CAGR as Planet Fitness standalone EBITDA forecast from 27-30 -Acquisition EBITDA multiple of 10.0x -No synergies -Acquisition funded first by all available cash on hand (less minimum cash), then by a revolver. Revolver assumptions: *The revolver was left undrawn at purchase *Priced at SOFR + 400 (for the purpose of this analysis, pricing will be fixed throughout the forecast at the 30-day Average SOFR as of 11/21 in attached file titled "SOFR (Actual).xlsx") *Maximum revolver capacity of $1,000mm *Unused revolver commitment fee of 0.25% *Revolver paydown is prioritized before cash sweep to any other debt
Published trajectories
Agent runs on this task
Curated dual-harness runs (parsed + original sandbox). Best scored run per model.
| Model | Harness | Score | Result | Links |
|---|---|---|---|---|
| GPT-5.5showcase | dual | 0/3 | Fail | Share pagePublic trace |
| Gemini 3.1 Pro | dual | 0/3 | Fail | Share pagePublic trace |
| GPT-5.4 mini | dual | 0/3 | Fail | Share pagePublic trace |
| GPT-5.4 nano | dual | 0/3 | Fail | Share pagePublic trace |
Grading rubric
Criteria and grader verdict (showcase run)
States Total Debt ($mm) is $1,534
FailEvidence: <TEXT_RESPONSE> table lists “Total debt | $0mm | $223mm | $223mm.” Assessment: Criterion requires that the response “States Total Debt ($mm) is $1,534”; the stated total debt is $223mm, not $1,534mm, so fail.
States Total Enterprise Value ($mm) is $19,549
FailEvidence: <TEXT_RESPONSE> table lists “Total enterprise value | $18,270mm | $19,223mm | $953mm.” Assessment: Criterion requires that the response “States Total Enterprise Value ($mm) is $19,549”; the stated PF + Add-On TEV is $19,223mm, not $19,549mm, so fail.
States Sponsor IRR (%) is 15.5%
FailEvidence: <TEXT_RESPONSE> table lists “Sponsor IRR | 16.2% | 16.8% | 0.6%.” Assessment: Criterion requires that the response “States Sponsor IRR (%) is 15.5%”; the stated PF + Add-On Sponsor IRR is 16.8%, not 15.5%, so fail.