A unified, precise, and extensible toolkit to benchmark LLMs on various mathematical tasks 🧮✨.

🔴🚀 Important Notice: We've identified variances above 5% in results from diverse math evaluation frameworks. To ensure fair and standardized comparisons across research, our toolkit strives to harmonize evaluation methods, promoting consistent and reliable math evaluation.

🌟 In Practice: Esteemed projects like ToRA (ICLR'24) and DeepSeek-Coder have leveraged this suite!

• Models: Seamless compatibility with models from Hugging Face 🤗 and vLLM.

• Datasets: An extensive array of datasets including minerva_math, math, math_oai, gsm8k, gsm_hard, svamp, asdiv, mawps, tabmwp, finqa, theorem_qa, bbh, mmlu_stem, sat_math, mathqa, hungarian_exam.

• Prompts: Diverse prompting paradigms, from Direct to Chain-of-Thought (CoT), Program-of-Thought (PoT/PAL), and Tool-Integrated Reasoning (ToRA).

conda create -n math_eval python=3.10
conda activate math_eval

We suggest using vLLM docker directly:

docker run --network host --cap-add=SYS_ADMIN --privileged -d \
    --entrypoint '' --name vllm \
    --runtime nvidia --gpus all \
    --security-opt apparmor:unconfined \
    --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 \
    -v /mnt:/mnt \
    -p 8000:8000 \
    vllm/vllm-openai:latest \
    sleep infinity

git clone https://github.com/ZubinGou/math-evaluation-harness.git
cd math-evaluation-harness
pip install -r requirements.txt

1. Configure model and data settings in scripts/run_math_eval.sh, and set the PROMPT_TYPE variable accordingly:

   • For base models, choose from: direct, cot, pal, or tool-integrated.
   • For SFT models, your options include: tora, wizard_zs, deepseek-math, etc.
     • To add new models, update the construct_prompt function in utils.py to include your new prompt template.

2. Run the script:

bash scripts/run_eval.sh $PROMPT_TYPE $MODEL_NAME_OR_PATH

PROMPT_TYPE=cot

PROMPT_TYPE=tora

PROMPT_TYPE=deepseek-math

This project is still under active development. We welcome any contributions, including bug reports, feature requests, and pull requests.

• https://github.com/microsoft/ToRA
• https://github.com/openai/prm800k
• https://github.com/wellecks/lm-evaluation-harness
• https://github.com/deepseek-ai/DeepSeek-Math