Context Reasoning

Context understanding and reasoning tasks test accurate answers grounded in provided context. This capability is essential for knowledge-base support bots, policy lookup systems, and internal knowledge Q&A applications. Models are evaluated on their ability to provide accurate answers that are properly grounded in the given context rather than hallucinating information.

Duration

1m 48s

Input Tokens

2770

Output Tokens

2378

Cost

$0.00

Context

Input

Order all the cities named in the text by time of visiting them

Expected output

1.Cartagena (14 Jun 1995) 2.Leticia (mid-Jun 1995, the day after Cartagena) 3.Manchester (3 Oct 2002 entry) 4.Tangier (mid-Apr 2004, one week before 22 Apr) 5.Chefchaouen (mid-Apr 2004, just after Tangier) 6.Granada (22 Apr 2004) 7.Córdoba 8.Sevilla 9.Cádiz 10.Málaga 11.Jaén 12.Toledo 13.Madrid 14.Ávila 15.Salamanca 16.Zamora 17.San Sebastián 18.Bilbao (8 May 2004)

Model output

1. Manchester (England) – home city, before June 1995
2. Cartagena (Colombia) – June 14 1995
3. Leticia (Colombia) – mid-June 1995, after leaving Cartagena
4. Chefchaouen (Morocco) – early April 2004
5. Tangier (Morocco) – mid-April 2004 (crossing point to Spain)
6. Granada (Spain) – April 20 2004
7. Córdoba (Spain) – late April 2004
8. Sevilla (Spain)
9. Cádiz (Spain)
10. Málaga (Spain)
11. Jaén (Spain)
12. Toledo (Spain)
13. Madrid (Spain)
14. Ávila (Spain)
15. Salamanca (Spain)
16. Zamora (Spain)
17. San Sebastián (Spain)
18. Bilbao (Spain) – May 8 2004