Raycaster/ Eval

APEX-Agents · Investment Banking

world225_AV_02

Best published5/5Pass

APEX-Agents task world225_AV_02 in AI Agents for Tax Due Diligence. Compare dual-harness agent runs across models, scores, and public traces.

AI Agents for Tax Due DiligenceInvestment Banking World 225Dual harnessGrader: rubric
task_a9ce195e45104521ac830136c86d0f69
Investment Banking World 225
message_in_console
4 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.

ModelHarnessScoreResultLinks
Gemini 3.1 Produal5/5Pass
GPT-5.4 minidual5/5Pass
GPT-5.5dual5/5Pass
GPT-5.4 nanodual0/5Fail

Grading rubric

Rubric criteria

Runs are graded against these criteria. Open a run for model-specific verdicts.

  1. States the Unlevered Free Cash Flow in 2025E is $663.35 million

  2. States the Unlevered Free Cash Flow in 2026E is $829.61 million

  3. States the Unlevered Free Cash Flow in 2027E is $931.47 million

  4. States the Unlevered Free Cash Flow in 2028E is $1,044.37 million

  5. States the Unlevered Free Cash Flow in 2029E is $1,095.98 million