APEX-Agents · Investment Banking

World228_SM_Task04

2/2Pass

APEX-Agents task World228_SM_Task04 in AI Agents for Employment Law Analysis. Compare dual-harness agent runs across models — rubric criteria, scores, and public traces.

AI Agents for Employment Law AnalysisInvestment Banking World 228Dual harnessGrader: rubric

Task IDtask_00db129e3bd9497da0acf6470a1d33d2

WorldInvestment Banking World 228

Expected outputmessage_in_console

Published runs4 models · dual config

Task prompt

What the agent was asked to do

Please access the 2024 Huhtamaki Annual Report and calculate the Net Sales per employee at end of period for 2023 and 2024. Reply to me here with the the Euros per Employee, rounded to the nearest full Euro amount.

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	2/2	Pass	Share page Public trace
Gemini 3.1 Pro	dual	2/2	Pass	Share page Public trace
GPT-5.4 mini	dual	0/2	Fail	Share page Public trace
GPT-5.4 nano	dual	2/2	Pass	Share page Public trace

Grading rubric

Criteria and grader verdict (showcase run)

States 2024 Net Sales per Employee for Huhtamaki is 231,893 Euros
Pass
Evidence: TEXT_RESPONSE states “- 2024: €231,893 per employee.” Assessment: Criterion requires stating 2024 Net Sales per Employee for Huhtamaki is 231,893 Euros; pass because the response gives exactly that amount.
States 2023 Net Sales per Employee for Huhtamaki is 232,769 Euros
Pass
Evidence: TEXT_RESPONSE states “- 2023: €232,769 per employee.” Assessment: Criterion requires stating 2023 Net Sales per Employee for Huhtamaki is 232,769 Euros; pass because the response gives exactly that amount.