APEX-Agents · Investment Banking
World225_MB_03
APEX-Agents task World225_MB_03 in AI Agents for Tax Due Diligence. Compare dual-harness agent runs across models — rubric criteria, scores, and public traces.
Task prompt
What the agent was asked to do
Using the 'Projections (C-Corp)' tab in Golden_Everest_REIT_Analysis compute the Net Income for 2029E given the following scenario: - Assume tax rates are 15.0% for 2025E through 2029E - If net income exceeds $1,300M in a given year, update the revenue growth % for all subsequent years. - Use the average of the growth rates shown on the "Projected Financials" slide in the Project_Titan_Presentation v3.pptx file. Compare the 2029E Net Income computed for the above scenario to the original 2029E Net Income by providing each Net Income figure and their dollar difference. Present in $M and round to nearest whole number. Write back your answers as a message.
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 | 3/3 | Pass | Share pagePublic trace |
| Gemini 3.1 Pro | dual | 3/3 | Pass | Share pagePublic trace |
| GPT-5.4 mini | dual | 3/3 | Pass | Share pagePublic trace |
| GPT-5.4 nano | dual | 3/3 | Pass | Share pagePublic trace |
Grading rubric
Criteria and grader verdict (showcase run)
States that the original 2029E Net Income is $1,360 million
PassEvidence: TEXT_RESPONSE table states "Original | $1,360M" for 2029E Net Income. Assessment: Criterion requires stating original 2029E Net Income is $1,360 million; pass.
States that the New 2029E Net Income is $1,499 million
PassEvidence: TEXT_RESPONSE table states "Scenario | $1,499M" and text says "the scenario 2029E Net Income". Assessment: Criterion requires stating New 2029E Net Income is $1,499 million; pass.
States that the difference between New and Original 2029E Net Income is $139 million
PassEvidence: TEXT_RESPONSE table states "Difference | +$139M" and final sentence says "$139M higher than the original." Assessment: Criterion requires stating the difference between New and Original 2029E Net Income is $139 million; pass.