APEX-Agents · Investment Banking

world227_tg_09

1/1Pass

APEX-Agents task world227_tg_09 in AI Agents for Tax Due Diligence. Compare dual-harness agent runs across models — rubric criteria, scores, and public traces.

AI Agents for Tax Due DiligenceInvestment Banking World 227Dual harnessGrader: rubric

Task IDtask_9df937d993034a0a89d4abe8f32d8868

WorldInvestment Banking World 227

Expected outputmessage_in_console

Published runs4 models · dual config

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-5.5showcase	dual	1/1	Pass	Share page Public trace
Gemini 3.1 Pro	dual	0/1	Fail	Share page Public trace
GPT-5.4 mini	dual	1/1	Pass	Share page Public trace
GPT-5.4 nano	dual	1/1	Pass	Share page Public trace

Grading rubric

Criteria and grader verdict (showcase run)

States that total value of privatization is $7,464 million
Pass
Evidence: The response table shows “**Total value of privatization** | **7,464**” and states “**Answer: $7,464 million.**” Assessment: The criterion asks whether it states that total value of privatization is $7,464 million; pass, because the response explicitly gives that exact value.