Small Benchmarks for LM Agents
Project description
SmallBench
Small, simple agent task environments for training and evaluation.
Designed to challenge a broad spectrum of lm-agent abilities.
Spinning Up
uv venv smallbench-dev
source smallbench-dev/bin/activate
uv sync
uv run ruff format .
Easy Benchmarks
BigCodeBench - Agent Harness
This benchmark provides a stateful environment for lm-based agents to solve coding problems from the BigCodeBench dataset. Agents are given a scratchpad (soon), a way to prepare and use unit tests, editing handlers, and a way to submit their solution.
Please see the BigCodeBench page for more information about the underlying dataset.
Get Started
Local
add GROQ_API_KEY and any other API keys supported by the apropos-ai library to the .env file.
- Note: Groq, Google, and possibly other providers offer free tiers.
If you use a Docker backend, ensure you have the Docker app running. If you use Modal, please add all necessary credentials.
Then, run the test script:
uv run python -m src.smallbench.benchmarks.bcb_a.test
Colab
Check out the Colab if you prefer to run the benchmark in the cloud.
Medium Benchmarks
TBD
Hard Benchmarks
TBD
Difficult Benchmarks
TBD
Caveats
- This repository is still under very active development.
- In particular, certain details regarding the agent computer interface contexts are very much subject to change, and there's a bit of response model instability. Let me know if you run into issues in the issues tab of the GitHub!
- For this reason, scores will likely be artificially low until further notice. Don't take them too seriously.
Scores - Extremely Preliminary
BigCodeBench - Agent Harness
LM | Success Rate (out of 100%) | Sample Size |
---|---|---|
claude-3-5-sonnet-20240620 | ??? | 30 |
gpt-4o-2024-08-06 | 10% | 30 |
gpt-4o-mini-2024-07-18 | 13.3% | 30 |
Animation credits: ZZ
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for smallbench-0.1.10-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5cdcde9c1bc9feb2d5839a89d893c867373d67cb8a5561a9f735d5577b1cf64f |
|
MD5 | 7f44c5237a11eae3311c79f15c6c9984 |
|
BLAKE2b-256 | 90d2a29e2db6fa26c73d20ee4b3f9137d76135a7434ed1f3ee40aaa5529a32ee |