APEX-Agents · Management Consulting
World131_acd_task12
APEX-Agents task World131_acd_task12 in AI Agents for Infrastructure Finance. Compare dual-harness agent runs across models, scores, and public traces.
Task prompt
What the agent was asked to do
Looking only at projects in the Connection Queue that have a status of "Approved" or "Connected", calculate the percentage of the Total Forecasted Demand for the years 2026, 2027, and 2028 that could be covered by these renewable energy projects. Our focus here is only the Netherlands. Use the data from the renewables and load forecast. Assume the percentages will be cumulative year over year and that renewables capacity is available in the full connection year and in all subsequent years (ignore 2025 connections and use 2026 as the base year). Round your final answers to whole percentages. Print your response to me 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 |
|---|---|---|---|---|
| Gemini 3.1 Pro | dual | 2/3 | Fail | Run detailsPublic trace |
| GPT-5.4 mini | dual | 2/3 | Fail | Run detailsPublic trace |
| GPT-5.4 nano | dual | 2/3 | Fail | Run detailsPublic trace |
| GPT-5.5 | dual | 2/3 | Fail | Run detailsPublic trace |
| GPT-5.4 | 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 that the percentage of the Total Forecasted Demand covered by renewable energy projects in the Netherlands in 2026 is 8%
States that the percentage of the Total Forecasted Demand covered by renewable energy projects in the Netherlands in 2027 is 13%
States that the percentage of the Total Forecasted Demand covered by renewable energy projects in the Netherlands in 2028 is 18%