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, 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 |
|---|---|---|---|---|
| fireworks models Kimi K2 | dual | 1/1 | Pass | Run detailsPublic trace |
| Gemini 3 Flash | dual | 1/1 | Pass | Run detailsPublic trace |
| Gemini 3.1 Pro | dual | 1/1 | Pass | Run detailsPublic trace |
| GPT-5.4 | 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 |
| GPT-5.4 mini | 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 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