ARC-C
The AI2 Reasoning Challenge (ARC) Challenge Set is a multiple-choice question-answering benchmark containing grade-school level science questions that require advanced reasoning capabilities. ARC-C specifically contains questions that were answered incorrectly by both retrieval-based and word co-occurrence algorithms, making it a particularly challenging subset designed to test commonsense reasoning abilities in AI systems.
Llama 3.1 405B Instruct from Meta currently leads the ARC-C leaderboard with a score of 0.969 across 33 evaluated AI models.
What ARC-C measures
ARC-C is a text benchmark that evaluates large language models on reasoning and general tasks. LLM Stats tracks 33 models on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.8, with the leader reaching 1.0.
Compare leaders on the best AI for reasoning and best AI for general leaderboards.
Publication
- Paper
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Authors
- Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, and 3 others
- Published
- arXiv
- 1803.05457
Abstract
We present a new question set, text corpus, and baselines assembled to encourage AI research in advanced question answering. Together, these constitute the AI2 Reasoning Challenge (ARC), which requires far more powerful knowledge and reasoning than previous challenges such as SQuAD or SNLI. The ARC question set is partitioned into a Challenge Set and an Easy Set, where the Challenge Set contains only questions answered incorrectly by both a retrieval-based algorithm and a word co-occurence algorithm. The dataset contains only natural, grade-school science questions (authored for human tests), and is the largest public-domain set of this kind (7,787 questions). We test several baselines on the Challenge Set, including leading neural models from the SQuAD and SNLI tasks, and find that none are able to significantly outperform a random baseline, reflecting the difficult nature of this task. We are also releasing the ARC Corpus, a corpus of 14M science sentences relevant to the task, and implementations of the three neural baseline models tested. Can your model perform better? We pose ARC as a challenge to the community.
Llama 3.1 405B Instruct leads with 96.9%, followed by 
Claude 3 Opus at 96.4% and 
Nova Pro at 94.8%.
Progress Over Time
Interactive timeline showing model performance evolution on ARC-C
ARC-C Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | 405B | — | — | |||
| 2 | Anthropic | — | — | — | ||
| 3 | Amazon | — | — | — | ||
| 3 | 70B | — | — | |||
| 5 | Anthropic | — | — | — | ||
| 6 |  AI21 Labs | 398B | — | — | ||
| 7 | Amazon | — | — | — | ||
| 8 |  Mistral AI | 24B | — | — | ||
| 9 |  Microsoft | 60B | — | — | ||
| 10 | Amazon | — | — | — | ||
| 11 | Anthropic | — | — | — | ||
| 12 | AI21 Labs | 52B | — | — | ||
| 13 | Microsoft | 4B | — | — | ||
| 14 | Microsoft | 4B | — | — | ||
| 15 | 8B | — | — | |||
| 16 | 3B | — | — | |||
| 17 | Mistral AI | 8B | — | — | ||
| 18 |  Google | 27B | — | — | ||
| 19 |  Cohere | 104B | — | — | ||
| 20 |  Alibaba Cloud / Qwen Team | 32B | — | — | ||
| 21 | Alibaba Cloud / Qwen Team | 33B | — | — | ||
| 22 | 70B | — | — | |||
| 23 | Alibaba Cloud / Qwen Team | 72B | — | — | ||
| 24 | Google | 9B | — | — | ||
| 25 | Alibaba Cloud / Qwen Team | 15B | — | — | ||
| 26 |  Nous Research | 70B | — | — | ||
| 27 | Google | 8B | — | — | ||
| 27 | 2B | — | — | |||
| 29 | Alibaba Cloud / Qwen Team | 7B | — | — | ||
| 30 | 2B | — | — | |||
| 30 | Google | 8B | — | — | ||
| 32 | 8B | — | — | |||
| 33 |  Baidu | 21B | — | — |
FAQ
Common questions about ARC-C.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions