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.

A1 · Innovative survey designs for better understanding human (travel) behavior Show all tasks

probabilities prepared

Klang Valley mode use · probability protocol v2

A resident of the Klang Valley in Malaysia is described as follows. Male, aged 40 years old and above, Malay, education ≥ degree, Working, household income group M40. Children under 12 in the household: Yes. Owns a private motorised vehicle…

Open task →

Export results

Prompts, answer keys, model responses and scores.