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.
6b31ff74-cc0b-414e-b4f4-3d4913257f5d
Qwen/Qwen 2.5 Coder 32B Instructtext → text
ox
3 weeks agoFormat the following SQL statement properly onto one line. Respond with the formatted SQL statement and nothing else.
{output}
SQL:
num_tables
num_tables
c1c2168f-d6cb-48cd-b8be-6333263ee9b8
Meta/Llama 3.3 70B Instructtext → textox
3 weeks agoDetermine the number of tables used in the following SQL statement given the CREATE TABLE statements below it. Output the table names in a comma separated list.
The output format should be xml tags containing the number of tables used and the table names.
For example:
<num_tables>2</num_tables>
<tables>table_1,table_2</tables>
{input}
{response}conflict/main/ox-536
6bd3b681-4ae3-4181-94f2-190e72cd2529
OpenAI/GPT 4o minitext → textox
3 weeks agoDetermine the number of tables used in the following SQL statement given the CREATE TABLE statements below it. Output the table names in a comma separated list.
The output format should be xml tags containing the number of tables used and the table names.
For example:
<num_tables>2</num_tables>
<tables>table_1,table_2</tables>
{schema}
{output}main
num_tables