APEX-Agents · Law
World416_JS_03
APEX-Agents task World416_JS_03 in AI Agents for Tariff and Trade Law Analysis. Compare dual-harness agent runs across models — rubric criteria, scores, and public traces.
Task prompt
What the agent was asked to do
TRIDENT AUTO CORPORATION (The "Plaintiff") has filed a claim in the United States District Court for the District of Columbia against several federal government agencies (The "Defendants"). The Claim alleges that the Defendants have violated the Administrative Procedure Act (The "APA") by implementing several tariffs issued by Donald Trump under the International Emergencies Economic Powers Act ("IEEPA"). The claim is being heard in the United States District Court for the District of Columbia. The presiding Judge is Rudolph Contreras. Will the Plaintiffs succeed in their claim? Reply back to me with a Yes or No answer and a single sentence explanation.
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 pagePublic trace |
| fireworks models Kimi K2 | dual | 2/2 | Pass | Share pagePublic trace |
| Gemini 3 Flash | dual | 2/2 | Pass | Share pagePublic trace |
| Gemini 3.1 Pro | dual | 2/2 | Pass | Share pagePublic trace |
| GPT-5.4 | dual | 2/2 | Pass | Share pagePublic trace |
| GPT-5.4 mini | dual | 2/2 | Pass | Share pagePublic trace |
| GPT-5.4 nano | dual | 2/2 | Pass | Share pagePublic trace |
Grading rubric
Criteria and grader verdict (showcase run)
States Yes, the Plaintiffs will succeed in their claim that the Defendants violated the Administrative Procedure Act
PassEvidence: TEXT_RESPONSE says, “Yes” and “Trident’s APA challenge is likely to succeed before him.” Assessment: The criterion requires stating that the Plaintiffs will succeed in their APA claim; this is clearly conveyed. Pass.
States that the Defendants implemented tariffs that the President did not have authority to issue
PassEvidence: TEXT_RESPONSE explains that Judge Contreras held “IEEPA does not authorize the President to impose tariffs.” Assessment: The criterion requires stating that the tariffs implemented by Defendants were ones the President lacked authority to issue; the response clearly states the President lacked statutory authority to impose the tariffs underlying the APA challenge. Pass.