APEX-Agents · Law
World 420_ZT_02
Best published1/1Pass
APEX-Agents task World 420_ZT_02 in AI Agents for FDA and Pharma Promotional Compliance. Compare dual-harness agent runs across models, scores, and public traces.
AI Agents for FDA and Pharma Promotional ComplianceLaw World 420Dual harnessGrader: rubric
Task prompt
What the agent was asked to do
Review the attached email (stored as a docx file), as well as the cases available in the world. Write a message to me, outlining whether John’s actions constitute unlawful off-label promotion.
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 mini | dual | 1/1 | Pass | Run detailsPublic trace |
| GPT-5.4 nano | dual | 1/1 | Pass | Run detailsPublic trace |
| GPT-5.5 | dual | 1/1 | Pass | Run detailsPublic trace |
| fireworks models Kimi K2 | dual | 0/1 | Fail | Run detailsPublic trace |
| Gemini 3 Flash | dual | 0/1 | Fail | Run detailsPublic trace |
| Gemini 3.1 Pro | dual | 0/1 | Fail | Run detailsPublic trace |
| GPT-5.4 | dual | 0/1 | Fail | Run detailsPublic trace |
Grading rubric
Rubric criteria
Runs are graded against these criteria. Open a run for model-specific verdicts.
States that John's actions do not constitute an unlawful off-label promotion