Skip to content

[EVAL] SciCode: reasearch coding benchmark #740

Open
@NathanHB

Description

@NathanHB

Evaluation short description

SciCode is a challenging benchmark designed to evaluate the capabilities of language models (LMs) in generating code for solving realistic scientific research problems. It has a diverse coverage of 16 subdomains from 6 domains: Physics, Math, Material Science, Biology, and Chemistry. Unlike previous benchmarks that consist of exam-like question-answer pairs, SciCode is converted from real research problems. SciCode problems naturally factorize into multiple subproblems, each involving knowledge recall, reasoning, and code synthesis. In total, SciCode contains 338 subproblems decomposed from 80 challenging main problems, and it offers optional descriptions specifying useful scientific background information and scientist-annotated gold-standard solutions and test cases for evaluation. OpenAI o1-preview, the best-performing model among those tested, can solve only 7.7% of the problems in the most realistic setting. Broadly, SciCode demonstrates a realistic and scientists' everyday workflow of identifying critical science concepts and facts and then transforming them into computation and simulation code. We believe SciCode not only helps demonstrate contemporary LLMs' progress towards a helpful assistant for scientists but also helps shed light on future building and evaluation of scientific AI.

Evaluation metadata

Provide all available

Metadata

Metadata

Assignees

No one assigned

    Labels

    Type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions