Benchmark tasks

Browse the prompts and compare model answers against their reference data.

C6 task catalogue. Project tags show research links; these are not separate benchmarks for every AgiMo subproject.

A7 · Reinforcement learning for mode choice decisions Show all tasks

probabilities prepared

Intercity choice · probability protocol v2

A traveller in the 1987 Sydney–Canberra–Melbourne non-business intercity sample has household income 35 thousand dollars. air: cost 59 dollars; waiting 69 min; in-vehicle 100 min; generalized cost 70 dollars. train: cost 31 dollars; waiting…

Open task →

Export results

Prompts, answer keys, model responses and scores.