reasoning benchmark
ARC-E
ARC-E (AI2 Reasoning Challenge - Easy Set) is a subset of grade-school level, multiple-choice science questions that requires knowledge and reasoning capabilities. Part of the AI2 Reasoning Challenge dataset containing 5,197 questions that test scientific reasoning and factual knowledge. The Easy Set contains questions that are answerable by retrieval-based and word co-occurrence algorithms, making them more accessible than the Challenge Set.
Updated Aug 7, 2026
Published models8
Registry coverage8
MetricScore
EvidenceB
ARC-E leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | GO | 88.6% | 100.0% | 8 | C | |
| 2 | GO | 88.0% | 85.7% | 8 | C | |
| 3 | NR | 83.0% | 71.4% | 8 | C | |
| 4 | GO | 81.6% | 57.1% | 8 | C | |
| 5 | GO | 81.6% | 42.9% | 8 | C | |
| 6 | GO | 75.8% | 28.6% | 8 | C | |
| 7 | GO | 75.8% | 14.3% | 8 | C | |
| 8 | BA | 60.7% | 0.0% | 8 | C |
Score distribution
Top published rows on the benchmark's original scale.
ARC-E highlights
The top published results on this benchmark's own scale.
What is ARC-E?
Definition and scoring fields from the benchmark registry.
ARC-E (AI2 Reasoning Challenge - Easy Set) is a subset of grade-school level, multiple-choice science questions that requires knowledge and reasoning capabilities. Part of the AI2 Reasoning Challenge dataset containing 5,197 questions that test scientific reasoning and factual knowledge. The Easy Set contains questions that are answerable by retrieval-based and word co-occurrence algorithms, making them more accessible than the Challenge Set.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- ARC-E
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- arc-e|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about ARC-E.
Which model scores highest on ARC-E?
Gemma 2 27B is currently ranked first with 88.6%.
What does ARC-E measure?
ARC-E (AI2 Reasoning Challenge - Easy Set) is a subset of grade-school level, multiple-choice science questions that requires knowledge and reasoning capabilities. Part of the AI2 Reasoning Challenge dataset containing 5,197 questions that test scientific reasoning and factual knowledge. The Easy Set contains questions that are answerable by retrieval-based and word co-occurrence algorithms, making them more accessible than the Challenge Set.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
8 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.