APEX-Agents · Investment Banking
World221_HY_01
APEX-Agents task World221_HY_01 in AI Agents for M&A Legal Due Diligence. Compare dual-harness agent runs across models, scores, and public traces.
Task prompt
What the agent was asked to do
Using the merger model, assume BBDC's share price falls by 15% after deal announcement but before the new share issuance to TPVG shareholders. Using the 9M TTM 2025 financial account, calculate the revised pro forma balance sheet. Send me a reply with the following pro forma balance sheet line items: Total assets, Total liabilities, Total net assets, Total liabilities and net assets and Nav per share All dollar values in $’000 (whole numbers), except for NAV per share which should be rounded to two decimal places.
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-5.4 nano | dual | 5/5 | Pass | Run detailsPublic trace |
| Gemini 3.1 Pro | dual | 1/5 | Fail | Run detailsPublic trace |
| GPT-5.4 mini | dual | 1/5 | Fail | Run detailsPublic trace |
| GPT-5.5 | dual | 1/5 | Fail | Run detailsPublic trace |
Grading rubric
Rubric criteria
Runs are graded against these criteria. Open a run for model-specific verdicts.
States total assets is $3,548,790 thousand
States total liabilities is $2,135,557 thousand
States total net assets is $1,413,233 thousand
States total liabilities and net assets is $3,548,790 thousand
States Nav per share is $10.20