LLM Evaluation Report
| Model | Date | Total Response Time (s) | Tests Passed | Mean CodeBLEU (0-1) | Mean Usefulness Score (0-4) | Mean Functional Correctness Score (0-4) |
|---|---|---|---|---|---|---|
gpt-4o-mini | 2024-10-18 | 180.098 | 113 | 0.331988 | 3.66463 | 3.65854 |
gemini-1.5-pro | 2024-10-18 | 533.694 | 104 | 0.338663 | 3.55488 | 3.59756 |
claude-3-5-sonnet-20240620 | 2024-10-18 | 339.244 | 112 | 0.300819 | 3.68293 | 3.65854 |
gpt-4o | 2024-10-18 | 201.997 | 128 | 0.314057 | 3.75 | 3.71951 |
o1-mini | 2024-10-18 | 773.989 | 130 | 0.335063 | 3.71951 | 3.71951 |
o1-preview | 2024-10-18 | 2207.5 | 127 | 0.322271 | 3.60366 | 3.60976 |
claude-3-opus-20240229 | 2024-10-18 | 1056.03 | 114 | 0.322514 | 3.7439 | 3.67683 |
Total Response Time (s): The total time taken by the model to generate all the outputs.
Tests passed: The number of unit tests that the model has passed during evaluation, out of a total of 164 tests.
Mean CodeBLEU: Average CodeBLEU score, a metric for evaluating code generation quality based on both syntactic and semantic correctness.
Mean Usefulness Score: Average rating of the model's output usefulness as rated by a LLM model.
0: Snippet is not at all helpful, it is irrelevant to the problem.
1: Snippet is slightly helpful, it contains information relevant to the problem, but it is easier to write the solution from scratch.
2: Snippet is somewhat helpful, it requires significant changes (compared to the size of the snippet), but is still useful.
3: Snippet is helpful, but needs to be slightly changed to solve the problem.
4: Snippet is very helpful, it solves the problem.
Mean Functional Correctness Score: Average score of the functional correctness of the model's outputs, assessing how well the outputs meet the functional requirements, rated by a LLM model.
0 (failing all possible tests): The code snippet is totally incorrect and meaningless.
4 (passing all possible tests): The code snippet is totally correct and can handle all cases.
Last updated