ARC-Challenge
Unknown
7,787 science questions requiring reasoning. Challenge set contains harder questions that retrieval fails on.
Benchmark Stats
Models4
Papers4
Metrics1
SOTA History
Coming SoonVisual timeline of state-of-the-art progression over time will appear here.
accuracy
accuracy
Higher is better
| Rank | Model | Code | Score | Paper / Source |
|---|---|---|---|---|
| 1 | claude-35-sonnet | - | 96.7 | anthropic-blog |
| 2 | gpt-4o Grade-school science questions (challenge set). | - | 96.4 | openai-blog |
| 3 | gemini-15-pro | - | 94.8 | google-blog |
| 4 | llama-3-70b | HF | 93 | meta-blog |