ARC: AI2 Reasoning Challenge

Dataset of natural, grade-school science multiple-choice questions (authored for human tests).

Overview

ARC is a benchmark using natural science questions to evaluate a model’s knowledge and reasoning capabilities. The dataset ships with Easy and Challenge sets.

Usage

Installation

Install with pip install inspect-evals, or uv sync from a checkout of this repository.

Running evaluations

uv run inspect eval inspect_evals/arc_easy --model openai/gpt-5-nano
uv run inspect eval inspect_evals/arc_challenge --model openai/gpt-5-nano

To run multiple tasks simultaneously use inspect eval-set:

uv run inspect eval-set inspect_evals/arc_easy inspect_evals/arc_challenge

You can also import tasks as normal Python objects and run them from python:

from inspect_ai import eval, eval_set
from inspect_evals.arc import arc_easy, arc_challenge
eval(arc_easy)
eval_set([arc_easy, arc_challenge], log_dir='logs-run-42')

Drop uv run if you manage dependencies yourself. Log viewing (inspect view) and default-model setup are documented in the Inspect Evals README.

Options

You can control a variety of options from the command line. For example:

uv run inspect eval inspect_evals/arc_easy --limit 10 --sample-shuffle
uv run inspect eval inspect_evals/arc_challenge --max-connections 10
uv run inspect eval inspect_evals/arc_easy --temperature 0.5

See uv run inspect eval --help for all available options.

Parameters

arc_easy, arc_challenge

No task parameters.

Dataset

The ARC dataset is a dataset of 7,787 genuine grade-school level, multiple-choice science questions. Here is an example prompt (after being further process by Inspect):

Answer the following multiple choice question. The entire content of your response should be of the following format: ’ANSWER: $LETTER (without quotes) where LETTER is one of A,B,C,D.

An astronomer observes that a planet rotates faster after a meteorite impact. Which is the most likely effect of this increase in rotation?

A) Planetary density will decrease.  
B) Planetary years will become longer.  
C) Planetary days will become shorter.  
D) Planetary gravity will become stronger.  

The model is then tasked to pick the correct choice.

Scoring

A simple accuracy is calculated over the datapoints.

Changelog

[2-A] - 2026-02-16

  • Migrate version to new scheme. See #907.

[1.0.1] - 2025-12-18

  • Adds backoff policy for functions that connect to huggingface servers.