ScienceQA
by Lu et al. / UCLA · open-source · Last verified 2026-03-17
ScienceQA is a multimodal benchmark of 21,000 science questions spanning natural science, language science, and social science at grade-school through high-school levels. Each question includes a natural-language or diagram context, multiple-choice answers, and an annotated lecture and explanation for rationale evaluation.
https://scienceqa.github.io ↗B
B—Above Average
Adoption: B+Quality: AFreshness: B+Citations: AEngagement: F
Specifications
- License
- CC BY-NC-SA 4.0
- Pricing
- open-source
- Capabilities
- evaluation, multimodal-reasoning, science-qa
- Integrations
- Use Cases
- model-evaluation, multimodal-ai, educational-ai
- API Available
- No
- Evaluated Models
- gpt-4o, claude-opus-4, gemini-2-5-pro, llava-1.6
- Metrics
- accuracy
- Methodology
- 21,208 multiple-choice questions across 26 topics. Models answer with or without context images; performance averaged across image/text-only subsets. Chain-of-thought explanations optionally evaluated for rationale quality.
- Last Run
- 2026-02-02
- Tags
- science, multimodal, k12, explanation, multiple-choice
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
68Adoption
76
Quality
88
Freshness
73
Citations
80
Engagement
0