Available Benchmarks#
Use get_available_benchmarks() to list the built-in
benchmarks and load_benchmark() to load one by name.
from locodellm.bench import get_available_benchmarks, load_benchmark
# List available benchmarks
for name, description in get_available_benchmarks().items():
print(f"{name}: {description}")
# Load a benchmark
bench = load_benchmark("basic")
Built-in Benchmarks#
basic#
<<<
from locodellm.bench import load_benchmark
bench = load_benchmark("basic")
print(bench.description)
print()
print(f"**{len(bench.tests)} prompt tests:**")
print()
print(".. list-table::")
print(" :header-rows: 1")
print(" :widths: 5 60 10")
print()
print(" * - #")
print(" - Task")
print(" - Expected results")
for i, test in enumerate(bench.tests, 1):
prompt = test.prompt
if len(prompt) > 80:
prompt = prompt[:77] + "..."
print(f" * - {i}")
print(f" - {prompt}")
print(f" - {len(test.expected)}")
>>>
10 Python function prompts with growing difficulty, from returning a constant string to computing an edit distance.
10 prompt tests:
# |
Task |
Expected results |
|---|---|---|
1 |
write a python function called hello that returns the string “hello” |
2 |
2 |
write a python function called add that takes two numbers and returns their sum |
3 |
3 |
write a python function called reverse_string that takes a string and returns… |
3 |
4 |
write a python function called find_max that takes a list of numbers and retu… |
3 |
5 |
write a python function called is_prime that takes an integer and returns Tru… |
4 |
6 |
write a python function called factorial that takes a non-negative integer n … |
4 |
7 |
write a python function called char_count that takes a string and returns a d… |
3 |
8 |
write a python function called is_palindrome that takes a string and returns … |
4 |
9 |
write a python function called fibonacci that takes a non-negative integer n … |
4 |
10 |
write a python function called edit_distance that takes two strings a and b a… |
4 |