yueqis 82d4d25b09 feat: support ToolQA benchmark (#2263) 1 an în urmă
..
EDA 9ada36e30b fix: restore python linting. (#2228) 1 an în urmă
agent_bench 208b1461ca [AgentBench evaluation] set run_as_devin to true (#2269) 1 an în urmă
bird 05b84df9cb chore: fix some comments (#2234) 1 an în urmă
gaia 9ada36e30b fix: restore python linting. (#2228) 1 an în urmă
humanevalfix 05b84df9cb chore: fix some comments (#2234) 1 an în urmă
logic_reasoning 9ada36e30b fix: restore python linting. (#2228) 1 an în urmă
miniwob 48151bdbb0 [feat] WebArena benchmark, MiniWoB++ benchmark and related arch changes (#2170) 1 an în urmă
mint 0584e428b2 [Mint evaluation] Fix bug in stopping when the agent reaches max steps or solution proposals (#2268) 1 an în urmă
ml_bench beabcce16d [Hotfix] Fix ML-Bench continue ``run_inference.py`` (#2284) 1 an în urmă
regression e89cc8f19b Feat: add stream output to exec_run (#1625) 1 an în urmă
static b2fdb963b6 Add detailed tutorial for adding new evaluation benchmarks (#1827) 1 an în urmă
swe_bench ae815b20d2 Improved logs (#2272) 1 an în urmă
toolqa 82d4d25b09 feat: support ToolQA benchmark (#2263) 1 an în urmă
webarena 48151bdbb0 [feat] WebArena benchmark, MiniWoB++ benchmark and related arch changes (#2170) 1 an în urmă
README.md ebafb702e5 Add ML-Bench Evaluation with OpenDevin (#2015) 1 an în urmă
TUTORIAL.md 75cecf68e0 docs: update tutorial docs (#1912) 1 an în urmă
__init__.py 2406b901df feat(SWE-Bench environment) integrate SWE-Bench sandbox (#1468) 1 an în urmă

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.