APEX-Agents · Management Consulting
Task_128_PJ_2
APEX-Agents task Task_128_PJ_2 in AI Agents for Cross-Border Regulatory Review. Compare dual-harness agent runs across models, scores, and public traces.
Task prompt
What the agent was asked to do
What will the year 1 revenue across EM1, EM2 and EM3 be if we launch a solar system for households at $6,000 price point? Assume the company will be able to acquire 7.5% of users who are planning to install the solar system soon and have their maximum willingness to spend more than the price of solar system. The number of households across markets is as follows: EM1 - 200,000 EM2 - 400,000 EM3 - 700,000 Use the survey data for these markets for estimation. Report your responses here, and round revenue numbers to nearest integer.
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 | dual | 3/3 | Pass | Run detailsPublic trace |
| GPT-5.4 mini | dual | 3/3 | Pass | Run detailsPublic trace |
| Gemini 3.1 Pro | dual | 0/3 | Fail | Run detailsPublic trace |
| GPT-5.4 nano | dual | 0/3 | Fail | Run detailsPublic trace |
| GPT-5.5 | dual | 0/3 | Fail | Run detailsPublic trace |
Grading rubric
Rubric criteria
Runs are graded against these criteria. Open a run for model-specific verdicts.
States Year 1 revenue for EM1 is $14,326,531
States Year 1 revenue for EM2 is $22,773,723
States Year 1 revenue for EM3 is $18,069,767