Evaluations
Run models against your data
Introducing Evaluations, a powerful feature designed to enable you to effortlessly test and compare a selection of AI models against your datasets.
Whether you're fine-tuning models or evaluating performance metrics, Oxen evaluations simplifies the process, allowing you to quickly and easily run prompts through an entire dataset.
Once you're happy with the results, output the resulting dataset to a new file, another branch, or directly as a new commit.
9a894265-0e13-4c10-9e59-1d489dbd4478
OpenAI/o1 minitext → text
mathias
5 months agoAnswer the following question only using facts from the facts given after the question.
Keep your answer grounded in the facts given.
If no facts given after the question, return 'None'.
Question:
{query}
Facts:
{context}3874d584-6546-453f-b219-3bcde65c2928
Google/Text Embedding 004text → embeddings
ox
5 months agoquery
d956c3ff-c6eb-4e5e-9b6c-d2148ac41404
OpenAI/GPT 4otext → textox
5 months agoAre the following two answers equivalent? If the answers contain numeric values, only compare the numbers and not the words. Answer "true" or "false". All lowercase.
Answer 1: {answer}
Answer 2: {prediction}gemini-flash-results
gemini-flash-results-judge
660bf91a-1dc4-42b8-b4ca-35bd32a12a64
Google/Gemini 1.5 Flashtext → textox
5 months agoWhat is the answer to the question given the context? Only reply with text that is contained in the context.
Question:
{query}
Context:
{context}
Answer:gemini-flash-results
521f0ef3-6bf8-4359-86fc-08d072ae99b6
OpenAI/GPT 4otext → textox
5 months agoAre the following two answers equivalent? If the answers contain numeric values, only compare the numbers and not the words. Answer "true" or "false". All lowercase.
Answer 1: {answer}
Answer 2: {prediction}openai-answer-extract
openai-answer-judgements
aa5a77d7-7852-47df-bba4-0998fe94c176
OpenAI/GPT 4o minitext → textox
5 months agoWhat is the answer to the question given the context? Only reply with text that is contained in the context.
Question:
{query}
Context:
{context}
Answer:
openai-answer-extract