APEX-Agents · Investment Banking
world227_tg_09
APEX-Agents task world227_tg_09 in AI Agents for Tax Due Diligence. Compare dual-harness agent runs across models, scores, and public traces.
Task prompt
What the agent was asked to do
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 the tax stream, assuming the following using the MFC model: * The province receives 1/3 share of the corporate tax (the other 2/3 going to the federal government) * Given its "super-priority", the discount rate on the tax stream is 4% * The terminal growth rate of the tax stream is expected to be the 2032 revenue growth rate of MFC Please provide your response to me here, in millions of dollars that are rounded to the nearest million.
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 mini | dual | 1/1 | Pass | Run detailsPublic trace |
| GPT-5.4 nano | dual | 1/1 | Pass | Run detailsPublic trace |
| GPT-5.5 | dual | 1/1 | Pass | Run detailsPublic trace |
| Gemini 3.1 Pro | dual | 0/1 | Fail | Run detailsPublic trace |
Grading rubric
Rubric criteria
Runs are graded against these criteria. Open a run for model-specific verdicts.
States that total value of privatization is $7,464 million