ARC Easy (PapersWithCode): leaderboard
AI2 Reasoning Challenge (Clark et al., 2018), Easy set: the grade-school science multiple-choice questions left after the harder Challenge set is removed. This board is the archived Papers With Code table of accuracies as each paper reported them, under that paper’s own setup, not a common evaluation run; higher is better.
Metric: Accuracy. Source: huggingface.co. Saturation forecast: Rough model projection: around 2026. 46 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | OPT-175B | 71.04 | #1507 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=arc-easy-paperswithcode · How It Works · Data refreshed daily, snapshot 2026-11-05.