APEX-Agents · Law
LawWorld433_ANB_05
APEX-Agents task LawWorld433_ANB_05 in AI Agents for Healthcare and Senior Living Legal Risk. Compare dual-harness agent runs across models — rubric criteria, scores, and public traces.
Task prompt
What the agent was asked to do
Sarah Lee was deposed in the case brought by Plaintiff, Daisy Buchanan. Plaintiff intends to call Ms. Lee to testify at trial. Identify which statements in paragraph 8 of her deposition transcript are objectionable based on the New York Rule of Evidence 10.03. Respond with one paragraph, write it out 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 |
|---|---|---|---|---|
| GPT-5.5showcase | dual | 1/1 | Pass | Share pagePublic trace |
| fireworks models Kimi K2 | dual | 1/1 | Pass | Share pagePublic trace |
| Gemini 3 Flash | dual | 1/1 | Pass | Share pagePublic trace |
| Gemini 3.1 Pro | dual | 1/1 | Pass | Share pagePublic trace |
| GPT-5.4 | dual | 1/1 | Pass | Share pagePublic trace |
| GPT-5.4 mini | dual | 0/1 | Fail | Share pagePublic trace |
| GPT-5.4 nano | dual | 1/1 | Pass | Share pagePublic trace |
Grading rubric
Criteria and grader verdict (showcase run)
States that Ms. Lee's statement "The BGL was recorded by the external EMT team as being extremely high, exceeding the limits of the monitor," is objectionable under the best evidence rule
PassEvidence: The response identifies as objectionable “the BGL testimony that ‘the BGL was recorded by the external EMT team as being extremely high, exceeding the limits of the monitor’” and says “the proper objection is best evidence.” Assessment: The criterion requires stating that this specific BGL statement is objectionable under the best evidence rule; pass because the response explicitly says so.