Xingyao Wang f45a2ff04e [Agent, Eval] Fixes LLM config issue for delegation & Add eval to measure the delegation accuracy (#2948) vor 1 Jahr
..
EDA 959d21c48f remove useless code (#2922) vor 1 Jahr
agent_bench c68478f470 Customize LLM config per agent (#2756) vor 1 Jahr
biocoder 959d21c48f remove useless code (#2922) vor 1 Jahr
bird 8f76587e5c docs: updated docstrings using ruff's autofix feature (#2923) vor 1 Jahr
browsing_delegation f45a2ff04e [Agent, Eval] Fixes LLM config issue for delegation & Add eval to measure the delegation accuracy (#2948) vor 1 Jahr
gaia 8f76587e5c docs: updated docstrings using ruff's autofix feature (#2923) vor 1 Jahr
gorilla 8f76587e5c docs: updated docstrings using ruff's autofix feature (#2923) vor 1 Jahr
gpqa 8f76587e5c docs: updated docstrings using ruff's autofix feature (#2923) vor 1 Jahr
humanevalfix 8f76587e5c docs: updated docstrings using ruff's autofix feature (#2923) vor 1 Jahr
logic_reasoning c68478f470 Customize LLM config per agent (#2756) vor 1 Jahr
miniwob c68478f470 Customize LLM config per agent (#2756) vor 1 Jahr
mint 8f76587e5c docs: updated docstrings using ruff's autofix feature (#2923) vor 1 Jahr
ml_bench 8f76587e5c docs: updated docstrings using ruff's autofix feature (#2923) vor 1 Jahr
regression 8f76587e5c docs: updated docstrings using ruff's autofix feature (#2923) vor 1 Jahr
static b2fdb963b6 Add detailed tutorial for adding new evaluation benchmarks (#1827) vor 1 Jahr
swe_bench 8f76587e5c docs: updated docstrings using ruff's autofix feature (#2923) vor 1 Jahr
toolqa 2df1d67007 History clean up (#2849) vor 1 Jahr
utils d37b2973b2 Refactoring: event stream based agent history (#2709) vor 1 Jahr
webarena d37b2973b2 Refactoring: event stream based agent history (#2709) vor 1 Jahr
README.md ebafb702e5 Add ML-Bench Evaluation with OpenDevin (#2015) vor 1 Jahr
TUTORIAL.md c68478f470 Customize LLM config per agent (#2756) vor 1 Jahr
__init__.py 2406b901df feat(SWE-Bench environment) integrate SWE-Bench sandbox (#1468) vor 1 Jahr

README.md

Evaluation

This folder contains code and resources to run experiments and evaluations.

Logistics

To better organize the evaluation folder, we should follow the rules below:

  • Each subfolder contains a specific benchmark or experiment. For example, evaluation/swe_bench should contain all the preprocessing/evaluation/analysis scripts.
  • Raw data and experimental records should not be stored within this repo.
  • Important data files of manageable size and analysis scripts (e.g., jupyter notebooks) can be directly uploaded to this repo.

Supported Benchmarks

Result Visualization

Check this huggingface space for visualization of existing experimental results.

Upload your results

You can start your own fork of our huggingface evaluation outputs and submit a PR of your evaluation results to our hosted huggingface repo via PR following the guide here.