APEX-Agents · Investment Banking

world225_AV_02

5/5Pass

APEX-Agents task world225_AV_02 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 225Dual harnessGrader: rubric

Task IDtask_a9ce195e45104521ac830136c86d0f69

WorldInvestment Banking World 225

Expected outputmessage_in_console

Published runs4 models · dual config

Task prompt

What the agent was asked to do

Calculate Unlevered Free Cash Flow in 2025E, 2026E, 2027E, 2028E and 2029E. In the Golden Everest Financial Model, there is an error in the unlevered free cash flow build in the Projections, "Projections (C-Corp)", tab. Please use the correct formula to calculate Unlevered Free Cash Flow based on the Projections. Additionally, use the following assumptions: - Change in Working Capital: -1.0% of Revenues between 2025E and 2029E - D&A: 11.50% of Revenues in 2025E and 12.0% of Revenues from 2026E through 2029E - Capex: 24.0% of Revenues in 2025E, 22.0% of Revenues in 2026E, 21.0% of Revenues in 2027E, and 20% of Revenues in 2028E and 2029E Round output financial figures to 2 decimal points. $ must be in millions. Give me your response as a reply right here.

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	5/5	Pass	Share page Public trace
Gemini 3.1 Pro	dual	5/5	Pass	Share page Public trace
GPT-5.4 mini	dual	5/5	Pass	Share page Public trace
GPT-5.4 nano	dual	0/5	Fail	Share page Public trace

Grading rubric

Criteria and grader verdict (showcase run)

States the Unlevered Free Cash Flow in 2025E is $663.35 million
Pass
Evidence: TEXT_RESPONSE table lists “2025E | $663.35” under Unlevered Free Cash Flow ($mm). Assessment: Criterion asks whether it states 2025E UFCF is $663.35 million; pass because the response states exactly that value in $mm.
States the Unlevered Free Cash Flow in 2026E is $829.61 million
Pass
Evidence: TEXT_RESPONSE table lists “2026E | $829.61” under Unlevered Free Cash Flow ($mm). Assessment: Criterion asks whether it states 2026E UFCF is $829.61 million; pass because the response states exactly that value in $mm.
States the Unlevered Free Cash Flow in 2027E is $931.47 million
Pass
Evidence: TEXT_RESPONSE table lists “2027E | $931.47” under Unlevered Free Cash Flow ($mm). Assessment: Criterion asks whether it states 2027E UFCF is $931.47 million; pass because the response states exactly that value in $mm.
States the Unlevered Free Cash Flow in 2028E is $1,044.37 million
Pass
Evidence: TEXT_RESPONSE table lists “2028E | $1,044.37” under Unlevered Free Cash Flow ($mm). Assessment: Criterion asks whether it states 2028E UFCF is $1,044.37 million; pass because the response states exactly that value in $mm.
States the Unlevered Free Cash Flow in 2029E is $1,095.98 million
Pass
Evidence: TEXT_RESPONSE table lists “2029E | $1,095.98” under Unlevered Free Cash Flow ($mm). Assessment: Criterion asks whether it states 2029E UFCF is $1,095.98 million; pass because the response states exactly that value in $mm.