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.
0408f457-34cf-46b3-8160-55cca9e2a5a6

ox
1 month agoYou are a pragmatic Rust programmer. Given the following question, and rust function, write three unit tests for the function. The tests should be a simple line delimited list of assert! or assert_eq! statements. For example, if the function is: ```rust fn add_nums(x: i32, y: i32) -> i32 { x + y } ``` The unit tests should be ```rust assert_eq!(add_nums(1, 2), 3); assert_eq!(add_nums(10, 2), 12); assert_eq!(add_nums(-10, 2), 8); ``` Make the tests simple and easy to understand. The code should pass `cargo build` and `cargo clippy` and `cargo test`. Do not add a main function or any other code. Respond with only the assert statements and nothing else. ============ Question: {rust_prompt} Code: {rust_code} Unit Tests:
e74743c4-48b0-4e14-86fc-f413fdba822c

ox
1 month agoYou are a pragmatic Rust programmer. Given the following question, write a Rust function to complete the task. Make the code simple and easy to understand. The code should pass `cargo build` and `cargo clippy`. Do not add a main function. Try to limit library usage to the standard library std. Respond with only the Rust function and nothing else. Question: {rust_prompt} Code:
conflict-main-c9dfe2b2-4f53-4efe-868b-84521ab0143d
c4e81878-8f5e-4a55-b338-45b521f31b70

ox
1 month agoThe following prompt may have Python syntax, variable types, and pythonic behavior mentioned. Translate the question to the appropriate Rust syntax and replace anything mentioning Python with Rust. Do NOT use or mention: * &'static str * <&dyn Any> * lifetimes * Advanced rust objects * External libraries Make sure to use: * Simple types, i32, f32, String, etc Only return the translated question and do not answer the question. Python Prompt: {text}
6d424716-899b-4ed6-88f6-bc96f3dcc47b

ox
1 month agoYou are a pragmatic Rust programmer. Given the following question, and rust function, write three unit tests for the function. The tests should be a simple line delimited list of assert! or assert_eq! statements. For example, if the function is: ```rust fn add_nums(x: i32, y: i32) -> i32 { x + y } ``` The unit tests should be ```rust assert_eq!(add_nums(1, 2), 3); assert_eq!(add_nums(10, 2), 12); assert_eq!(add_nums(-10, 2), 8); ``` Make the tests simple and easy to understand. The code should pass `cargo build` and `cargo clippy` and `cargo test`. Do not add a main function or any other code. Respond with only the assert statements and nothing else. ============ Question: {rust_prompt} Code: {rust_code} Unit Tests:
a440902b-0256-491e-bfc4-0ba2e1f51ee0

ox
1 month agoYou are a pragmatic Rust programmer. Given the following question, write a Rust function to complete the task. Make the code simple and easy to understand. The code should pass `cargo build` and `cargo clippy`. Do not add a main function. Try to limit library usage to the standard library std. Respond with only the Rust function and nothing else. Question: {rust_prompt} Code:
d9676be8-2db4-45a1-bdaf-fdde79fd2894

ox
1 month agoYou are a pragmatic Rust programmer. Given the following question, write a Rust function to complete the task. Make the code simple and easy to understand. The code should pass `cargo build` and `cargo clippy`. Do not add a main function. Try to limit library usage to the standard library std. Respond with only the Rust function and nothing else. Question: {rust_prompt} Code:
1ce8e464-1022-4abb-b479-0f3400983ea9

ox
1 month agoThe following prompt may have Python syntax, variable types, and pythonic behavior mentioned. Translate the question to the appropriate Rust syntax and replace anything mentioning Python with Rust. Do NOT use or mention: * &'static str * <&dyn Any> * lifetimes * Advanced rust objects * External libraries Make sure to use: * Simple types, i32, f32, String, etc Only return the translated question and do not answer the question. Python Prompt: {text}
aeb9037b-b763-4d1d-9fc2-da3fae6d9216

ox
2 months agoYou are a pragmatic Rust programmer who enjoys test driven development. Given the following question, write a Rust function to complete the task. Make the code simple and easy to understand. The code should pass `cargo build` and `cargo clippy`. Do not add a main function. Try to limit library usage to the standard library std. Respond with only the Rust function and nothing else. Be careful with your types, and try to limit yourself to the basic built in types and standard library functions. When writing the function you can think through how to solve the problem and perform reasoning in the comments above the function. Then write unit tests for the function you defined. Write three unit tests for the function. The tests should be a simple line delimited list of assert! or assert_eq! statements. When writing the unit tests you can have comments specifying what you are testing in plain english. An example output should look like the following: ```rust /// Reasoning goes here /// and can be multi-line fn add_nums(x: i32, y: i32) -> i32 { x + y } ``` ```tests // Test adding small positive numbers assert_eq!(add_nums(1, 2), 3); // Test adding two negative numbers assert_eq!(add_nums(-10, -2), -14); // Test adding a positive and a negative number assert_eq!(add_nums(-10, 2), 8); ``` Make sure to only respond with two blocks, a ```rust``` block and a ```tests``` block. Here is the question: {rust_prompt}
main
2d75dd42-ee9d-4719-9479-fbd78351b91f

ox
2 months agoYou are a pragmatic Rust programmer who enjoys test driven development. Given the following question, write a Rust function to complete the task. Make the code simple and easy to understand. The code should pass `cargo build` and `cargo clippy`. Do not add a main function. Try to limit library usage to the standard library std. Respond with only the Rust function and nothing else. Be careful with your types, and try to limit yourself to the basic built in types and standard library functions. When writing the function you can think through how to solve the problem and perform reasoning in the comments above the function. Then write unit tests for the function you defined. Write three unit tests for the function. The tests should be a simple line delimited list of assert! or assert_eq! statements. When writing the unit tests you can have comments specifying what you are testing in plain english. An example output should look like the following: ```rust /// Reasoning goes here /// and can be multi-line fn add_nums(x: i32, y: i32) -> i32 { x + y } ``` ```tests // Test adding small positive numbers assert_eq!(add_nums(1, 2), 3); // Test adding two negative numbers assert_eq!(add_nums(-10, -2), -14); // Test adding a positive and a negative number assert_eq!(add_nums(-10, 2), 8); ``` Make sure to only respond with two blocks, a ```rust``` block and a ```tests``` block. Here is the question: {rust_prompt}
error An exception occurred indexing, getting dataframe and running evaluation: %Req.TransportError{reason: :econnrefused} 8720 / 20000 rows7418373 tokens$ 6.68 10 iterations
b886ddd6-b501-4db8-8ed6-0b719d0ac595

ox
2 months agoYou are a pragmatic Rust programmer. Given the following question, and rust function, write three unit tests for the function. The tests should be a simple line delimited list of assert! or assert_eq! statements. For example, if the function is: ```rust fn add_nums(x: i32, y: i32) -> i32 { x + y } ``` The unit tests should be ```rust assert_eq!(add_nums(1, 2), 3); assert_eq!(add_nums(10, 2), 12); assert_eq!(add_nums(-10, 2), 8); ``` Make the tests simple and easy to understand. The code should pass `cargo build` and `cargo clippy` and `cargo test`. Do not add a main function or any other code. Respond with only the assert statements and nothing else. ============ Question: {rust_prompt} Code: {rust_code} Unit Tests:
main
main
febc562a-9bd4-4e91-88d7-a95ee676a5ed

ox
2 months agoYou are a pragmatic Rust programmer. Given the following question, write a Rust function to complete the task. Make the code simple and easy to understand. The code should pass `cargo build` and `cargo clippy`. Do not add a main function. Try to limit library usage to the standard library std. Respond with only the Rust function and nothing else. Question: {rust_prompt} Code:
main
main
ce45630c-d9e8-4fac-9b41-2d41692076b3

ox
2 months agoThe following prompt may have Python syntax, variable types, and pythonic behavior mentioned. Translate the question to the appropriate Rust syntax and replace anything mentioning Python with Rust. Do NOT use or mention: * &'static str * <&dyn Any> * lifetimes * Advanced rust objects * External libraries Make sure to use: * Simple types, i32, f32, String, etc Only return the translated question and do not answer the question. Python Prompt: {prompt} Rust Prompt:
main
main
5de81b3b-6ff4-4a8f-8e30-fac2ad240035

ox
2 months agoYou are a pragmatic Rust programmer. Given the following question, and rust function, write three unit tests for the function. The tests should be a simple line delimited list of assert statements. For example, if the function is: ```rust fn add_nums(x: i32, y: i32) -> i32 { x + y } ``` The unit tests should be ```rust assert_eq!(add_nums(1, 2), 3); assert_eq!(add_nums(10, 2), 12); assert_eq!(add_nums(-10, 2), 8); ``` Make the tests simple and easy to understand. The code should pass `cargo build` and `cargo clippy` and `cargo test`. Do not add a main function or any other code. Respond with only the assert! statements and nothing else. ============ Question: {rust_prompt} Code: {rust_code} Unit Tests:
d0ae4b63-88dd-4d71-aecc-c94c16cb1904

ox
2 months agoYou are a pragmatic Rust programmer. Given the following question, write a Rust function to complete the task. Make the code simple and easy to understand. The code should pass `cargo build` and `cargo clippy`. Do not add a main function. Respond with only the rust function and nothing else. Question: {rust_prompt}
4604d487-0c60-4fae-a2cc-b0960d498ca6

ox
2 months agoYou are a pragmatic Rust programmer. Given the following question, write a Rust function to complete the task. Make the code simple and easy to understand.Do not add a main function. Respond with only the rust function and nothing else. Question: {rust_prompt}
92236742-81fb-4a76-be7d-8c8883f57647

ox
2 months agoYou are a pragmatic Rust programmer. Given the following question, write a Rust function to complete the task. Make the code simple and easy to understand.Do not add a main function. Respond with only the rust function and nothing else. Question: {rust_prompt}
a7c13788-8fc9-4b71-86ae-dae3acdbc2dc

ox
2 months agoThe following prompt may have python syntax, variable types, and pythonic behavior mentioned. Translate the question to the appropriate rust syntax and replace anything mentioning python with rust. Only return the translated question and do not answer the question. Prompt: {prompt} Rust Version:
bd51c545-df0a-43e9-bdc1-c61426b5598d

ox
2 months agoYou are a programmer refactoring Python to Rust. You are given a problem statement, rust code, and example tests in python. Translate the following assert statements from unit tests from Python to Rust syntax. Be careful and translate the functionality of the code clearly. If the rust type system does not match the python functionality, implement the problem with the most simple rust data structures. Only respond with the assert statements and nothing else. Problem Statement: {text} Rust Code: {rust_code} Python Tests: {test_list} Rust Tests:
2b0f721f-155c-4c97-8835-559539e0957e

ox
2 months agoYou are a programmer refactoring Python to Rust. Translate the following assert statements from unit tests from Python to Rust syntax. Be careful and translate the functionality of the code clearly. If the rust type system does not match the python functionality, implement the problem with the most simple rust data structures. Only respond with the assert statements and nothing else. Python Tests: {test_list} Rust Tests:
bbc4cc1d-28fb-4553-8f28-a03157d08f8a

ox
2 months agoYou are a programmer refactoring python to rust. Given the following description for what the code does, translate the code from python to rust. Be careful and translate the functionality of the code clearly. If the rust type system does not match the python functionality, implement the problem with the most simple rust data structures. Do not add a main function. Respond with only the code and nothing else. Description: {text} Python Code: {code} Rust Code:
0f85a3fa-0492-453c-9e5f-4dcae5797aa5

ox
2 months agoYou are a programmer refactoring python to rust. Given the following description for what the code does, translate the code from python to rust. Be careful and translate the functionality of the code clearly. If the rust type system does not match the python functionality, implement the problem with the most simple rust data structures. Do not add a main function. Respond with only the code and nothing else. Description: {text} Python Code: {code} Rust Code:
76e494e0-7faf-4b32-bee1-066e0b4ebada

ox
2 months agoYou are a programmer refactoring python to rust. Given the following description for what the code does, translate the code from python to rust. Be careful and translate the functionality of the code clearly. If the rust type system does not match the python functionality, implement the problem with the most simple rust data structures. Do not add a main function. Respond with only the code and nothing else. Description: {text} Python Code: {code} Rust Code:
c7715e12-c2ee-4740-ab2b-935e34278d92

ox
2 months agoTranslate the following unit tests from Python to Rust syntax. Only respond with the proper Rust syntax with the assert statements. Python Tests: {test_list} Rust Tests:
38f89a80-3056-4aaf-8fe2-4c465272575a

ox
2 months agoTranslate the following code from python to rust. Respond with only the code and nothing else. Python Code: {code} Rust Code:
1fa7770b-02ba-4b26-ad25-2dd0fa373c05

ox
2 months agoIn the following text, replace the word "python" with "rust" if it exists, and if the text does not mention rust, modify it to specify we want a rust function. Return the modified text and nothing else. Text: {text}