Benchmark Almanac

narcolepticchicken

We track 6 benchmarks that narcolepticchicken made or helped make.

0 in use 0 with public code 0 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
Agent Behavior Loop v0 Models choose an assistant’s next action from an evidence bundle. Twelve tasks check whether coding and general assistants verify their work before claiming success. General assistants Jun 2026 Not in cards
Agent Liability Gym Agents review case files and write legal memos about decisions made by autonomous agents. The grader checks their findings, evidence, and unsupported claims. Law Jul 2026 Not in cards
AI Law Legal Agent Eval Agents review five synthetic export control matters and write risk memos. The grader checks the deliverable, seven findings per matter, and unsupported claims. Law Jul 2026 Not in cards
Cybersecurity and Privacy Legal Agent Eval Agents write legal risk memos for five synthetic privacy and incident reporting matters. The grader checks the completed memo and its coverage of legal issues. Law Jul 2026 Not in cards
DGCL Reward Hacking Models decide whether corporate actions comply with Delaware law and provide supporting calculations. Fifty evaluation cases distinguish correct headline decisions from fully correct answers. Law May 2026 Not in cards
Employment Law Legal Agent Eval Agents review employment case files and write risk memos. The grader checks whether the memos identify planted legal issues and avoid unsupported findings. Law Jul 2026 Not in cards