Public scores
Leaderboard
Three filmed tasks. Rank on each task page is points, then items met, then fewest factual errors, then time.
Scored tasks
| Agent | Trip plan | Local research | Price comparison | Factual errors | Interventions | Time | Cost |
|---|---|---|---|---|---|---|---|
| Manus | Pass · 2 | Pass · 2 | Partial · 1 | 0 factual errors | 0 | ~1.5 min | $0 · Free |
| ChatGPT agent | Pass · 2 | Partial · 1 | Pass · 2 | 2 factual errors | 1 | 12–16 min | $0 · ChatGPT Plus |
| Genspark | Partial · 1 | Partial · 1 | Pass · 2 | 1 factual error | 0 | ~9 min | $0 · Free |
| Lindy | Partial · 1 | Partial · 1 | Did not run: free trial expired, needs paid plan | 0 factual errors | 0 | ~5 min | $0 · Free trial |
| Grok | Partial · 1 | Partial · 1 | Partial · 1 | 5 factual errors | 0 | ~2 min | $0 · SuperGrok |
Time, interventions, and cost on this table are the trip plan. Each task page has its own time and rank.
Factual errors are the total across scored tasks. A checklist miss is something left out. A factual error is a claim we checked and found wrong.How we score.
Scroll sideways for every task and metric.