OpenBookQA
OpenBookQA is a question-answering dataset modeled after open book exams for assessing human understanding. It contains 5,957 multiple-choice elementary-level science questions that probe understanding of 1,326 core science facts and their application to novel situations, requiring combination of open book facts with broad common knowledge through multi-hop reasoning.
5rows
scoreprimary metric
2026-05-06sampled
Metadata
Metrics
Score, Normalized Score
| Rank | Subject | Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | Phi-3.5-MoE-instruct | 0.90 | — | Self-reported | 2026-05-06 |
| 2 | Phi-3.5-mini-instruct | 0.79 | — | Self-reported | 2026-05-06 |
| 2 | Phi 4 Mini | 0.79 | — | Self-reported | 2026-05-06 |
| 4 | Mistral NeMo Instruct | 0.61 |  Mistral: Mistral Nemo mistralai-mistral-nemo | Self-reported | 2026-05-06 |
| 5 | Hermes 3 70B | 0.49 | — | Self-reported | 2026-05-06 |
No matching rows.