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.
f595a1d1-0d98-4fb4-a9cb-90d1f357d346
OpenAI/GPT 4o miniimage → textelau
4 days ago{image}11cb8827-6df6-49c9-b4d9-33454822a8f6
Perplexity/Perplexity Sonar Deep Researchtext → textelau
3 weeks agoLet's say I wait Graham's number of Planck times and then go back in time one googolplex ages of the universe for every atom in the observable universe from that point in time. What time will I have traveled to?
92fe8f86-d478-4367-bc08-6643d187a4f5
Google/Gemma 3 27Btext → textelau
1 month agoQ: {question}
A: {answer}
Task: Give a valid equation for which the answer is correct for the given question.f9052ca9-20fc-4d90-a6b2-89419e4e2328
OpenAI/GPT 4o minitext → textelau
1 month agotest {question}d2615b97-d54e-4b94-a30e-d9a81486d2df
Google/Gemini 2.0 Flash Litetext → textelau
1 month agotest
f069c030-c670-4ae5-ab7c-115eb686c0bc
OpenAI/GPT 4oimage → textelau
2 months ago{image}
{question}