reasoning benchmark
AI2 Reasoning Challenge (ARC)
A dataset of 7,787 genuine grade-school level, multiple-choice science questions assembled to encourage research in advanced question-answering. The dataset is partitioned into a Challenge Set and Easy Set, where the Challenge Set contains only questions answered incorrectly by both retrieval-based and word co-occurrence algorithms. Covers multiple scientific domains including biology, physics, earth science, and chemistry, requiring scientific reasoning, causal understanding, and conceptual knowledge beyond simple fact retrieval. Includes a supporting corpus of over 14 million science sentences.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
AI2 Reasoning Challenge (ARC) leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | OP | 96.3% | 100.0% | 1 | C |
AI2 Reasoning Challenge (ARC) highlights
The top published results on this benchmark's own scale.
What is AI2 Reasoning Challenge (ARC)?
Definition and scoring fields from the benchmark registry.
A dataset of 7,787 genuine grade-school level, multiple-choice science questions assembled to encourage research in advanced question-answering. The dataset is partitioned into a Challenge Set and Easy Set, where the Challenge Set contains only questions answered incorrectly by both retrieval-based and word co-occurrence algorithms. Covers multiple scientific domains including biology, physics, earth science, and chemistry, requiring scientific reasoning, causal understanding, and conceptual knowledge beyond simple fact retrieval. Includes a supporting corpus of over 14 million science sentences.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- AI2 Reasoning Challenge (ARC)
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- ai2-reasoning-challenge-(arc)|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about AI2 Reasoning Challenge (ARC).
Which model scores highest on AI2 Reasoning Challenge (ARC)?
GPT-4 is currently ranked first with 96.3%.
What does AI2 Reasoning Challenge (ARC) measure?
A dataset of 7,787 genuine grade-school level, multiple-choice science questions assembled to encourage research in advanced question-answering. The dataset is partitioned into a Challenge Set and Easy Set, where the Challenge Set contains only questions answered incorrectly by both retrieval-based and word co-occurrence algorithms. Covers multiple scientific domains including biology, physics, earth science, and chemistry, requiring scientific reasoning, causal understanding, and conceptual knowledge beyond simple fact retrieval. Includes a supporting corpus of over 14 million science sentences.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.