Wikibench

ARC-E

reasoning official site →

Multilingual: no

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.

Methodology

Imported from llm-stats public benchmark metadata. Modality: text. Max score: 1. Categories: general, reasoning. Language: en. Verified by llm-stats: no.

Leaderboard

Showing 8 of 8 results

  1. Gemma 2 27B self-reported llm-stats
    88.6%
  2. Gemma 2 9B self-reported llm-stats
    88.0%
  3. Hermes 3 70B self-reported llm-stats
    83.0%
  4. Gemma 3n E4B self-reported llm-stats
    81.6%
  5. Gemma 3n E4B Instructed LiteRT Preview self-reported llm-stats
    81.6%
  6. Gemma 3n E2B self-reported llm-stats
    75.8%
  7. Gemma 3n E2B Instructed LiteRT (Preview) self-reported llm-stats
    75.8%
  8. ERNIE 4.5 self-reported llm-stats
    60.7%