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.

100
Duration
23s
Input Tokens
89703
Output Tokens
175
Cost
$0.00
Context
Input
What LLM (model name) was used to drive context retrieval in the SWOT analysis of Reddit S-1 done by the Opper team
Expected output
Openai's o1-mini
Model output
According to the context, o1-mini from OpenAI was used to drive context retrieval in the SWOT analysis of Reddit S-1 done by the Opper team. Specifically, the text states: 'We used o1-mini to generate subquestions that will drive the context retrieval. We used the opper.call API to call the model. Note that we ask the model to return List[str] for a structured set of subquestions to iterate over for retrieval.'