mirror of
https://github.com/All-Hands-AI/OpenHands.git
synced 2026-04-29 03:00:45 -04:00
a081935fd8
* Start simplifying eval code * Update * Add EDA * Updated GAIA * Update gpqa * Add humanevalfix * Fix logic_reasoning * Add miniwob * Add mint and ml_bench * toolqa * Added swe-bench * Fixed webarena * Refactor parameters
Logic Reasoning Evaluation
This folder contains evaluation harness for evaluating agents on the logic reasoning benchmark ProntoQA and ProofWriter.
Configure OpenDevin and your LLM
Create a config.toml file if it does not exist at the root of the workspace.
Add the following configurations:
[core]
max_iterations = 100
cache_dir = "/tmp/cache"
ssh_hostname = "localhost"
enable_auto_lint = true
# TODO: Change these to the model you want to evaluate
[eval_gpt4_1106_preview]
model = "gpt-4-1106-preview"
api_key = "XXX"
temperature = 0.0
[eval_some_openai_compatible_model]
model = "openai/MODEL_NAME"
base_url = "https://OPENAI_COMPATIBLE_URL/v1"
api_key = "XXX"
temperature = 0.0
Run Inference on logic_reasoning
The following code will run inference on the first example of the ProntoQA dataset with model gpt-4o, using OpenDevin 0.6.2 version.
./evaluation/logic_reasoning/scripts/run_infer.sh ProntoQA gpt-4o 0.6.2 1