Benchmark

ARC-E

reasoning general text

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.

语言EN
满分1
参评模型6

模型排名

名次 模型 机构 分数 来源
1 Gemma 2 27B Google 88.6 来源 ↗
2 Gemma 2 9B Google 88.0 来源 ↗
3 Gemma 3n E4B Google 81.6 来源 ↗
4 Gemma 3n E4B Instructed LiteRT Preview Google 81.6 来源 ↗
5 Gemma 3n E2B Google 75.8 来源 ↗
6 Gemma 3n E2B Instructed LiteRT (Preview) Google 75.8 来源 ↗