APEX-Agents · Investment Banking

WORLD223_ES_02

6/6Pass

APEX-Agents task WORLD223_ES_02 in AI Agents for M&A Legal Due Diligence. Compare dual-harness agent runs across models — rubric criteria, scores, and public traces.

AI Agents for M&A Legal Due DiligenceInvestment Banking World 223Dual harnessGrader: rubric

Task IDtask_0ea7fa030cbe4d8ca517b48da89086e2

WorldInvestment Banking World 223

Expected outputedit_existing_sheet

Published runs4 models · dual config

Task prompt

What the agent was asked to do

Evaluate the sensitivity of EPS impact to synergies and cost of new debt for the acquisition of SOLV by MMM using the accretion dilution model. Create a new tab in the file, with a table to show EPS impact (accretion or dilution). - Show synergies in increments of $300 million (300m, 600m). - Show cost of new debt in increments of 5ppts (15%, 20%). - Show the price premium per share at different synergy levels. - Assume the price premium per share is 25% for no synergies and increases by 2.5ppt every $100 million in synergies. - Two dec points only.

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	6/6	Pass	Share page Public trace
Gemini 3.1 Pro	dual	6/6	Pass	Share page Public trace
GPT-5.4 mini	dual	6/6	Pass	Share page Public trace
GPT-5.4 nano	dual	6/6	Pass	Share page Public trace

Grading rubric

Criteria and grader verdict (showcase run)

States EPS impact at 15.00% cost of new debt, $300M in synergies is -13.02%
Pass
Evidence: <TEXT_RESPONSE> table shows row “300.00” with “EPS Impact @ 15% Debt Cost” as “-13.02% Dilution.” Assessment: Criterion asks “States EPS impact at 15.00% cost of new debt, $300M in synergies is -13.02%”; pass because the response states the exact percentage.
States EPS impact at 15.00% cost of new debt, $600M in synergies is -8.98%
Pass
Evidence: <TEXT_RESPONSE> table shows row “600.00” with “EPS Impact @ 15% Debt Cost” as “-8.98% Dilution.” Assessment: Criterion asks “States EPS impact at 15.00% cost of new debt, $600M in synergies is -8.98%”; pass because the response states the exact percentage.
States EPS impact at 20.00% cost of new debt, $300M in synergies is -34.67%
Pass
Evidence: <TEXT_RESPONSE> table shows row “300.00” with “EPS Impact @ 20% Debt Cost” as “-34.67% Dilution.” Assessment: Criterion asks “States EPS impact at 20.00% cost of new debt, $300M in synergies is -34.67%”; pass because the response states the exact percentage.
States EPS impact at 20.00% cost of new debt, $600M in synergies is -31.64%
Pass
Evidence: <TEXT_RESPONSE> table shows row “600.00” with “EPS Impact @ 20% Debt Cost” as “-31.64% Dilution.” Assessment: Criterion asks “States EPS impact at 20.00% cost of new debt, $600M in synergies is -31.64%”; pass because the response states the exact percentage.
States price premium for synergies at $300M is 32.50%
Pass
Evidence: <TEXT_RESPONSE> table shows row “Synergies ($mm) 300.00” with “Price Premium %” as “32.50%.” Assessment: Criterion asks “States price premium for synergies at $300M is 32.50%”; pass because the response states the exact price premium.
States price premium for synergies at $600M is 40.00%
Pass
Evidence: <TEXT_RESPONSE> table shows row “Synergies ($mm) 600.00” with “Price Premium %” as “40.00%.” Assessment: Criterion asks “States price premium for synergies at $600M is 40.00%”; pass because the response states the exact price premium.