multimodal benchmark
ScienceQA Visual Leaderboard
ScienceQA Visual is a multimodal science question answering benchmark consisting of 21,208 multiple-choice questions from elementary and high school science curricula. The dataset covers 3 subjects (natural science, language science, social science), 26 topics, 127 categories, and 379 skills. 48.7% of questions include image context requiring multimodal reasoning. Questions are annotated with lectures (83.9%) and explanations (90.5%) to support chain-of-thought reasoning for science question answering.
Updated Aug 17, 2026
Models1
Model coverage1
MetricScore
EvidenceB
ScienceQA Visual Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMI | Score97.5% | Percentile100.0% | Participants1 | EvidenceC | Evaluated |
ScienceQA Visual Highlights
The leading models and scores on this benchmark.
The Top AI Models for ScienceQA Visual
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis scienceqa visual AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01MIPhi-4-multimodal-instructMicrosoft
- Score
- 97.5%
- Speed
- Up to 25 tok/s via DeepInfra
Strengths
- Ranks #1 of 1 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures ScienceQA Visual, not total model capability
Selection summary
Best AI Models for ScienceQA Visual
Phi-4-multimodal-instruct currently leads ScienceQA Visual with 97.5%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is ScienceQA Visual?
What ScienceQA Visual measures and how its scores work.
ScienceQA Visual is a multimodal science question answering benchmark consisting of 21,208 multiple-choice questions from elementary and high school science curricula. The dataset covers 3 subjects (natural science, language science, social science), 26 topics, 127 categories, and 379 skills. 48.7% of questions include image context requiring multimodal reasoning. Questions are annotated with lectures (83.9%) and explanations (90.5%) to support chain-of-thought reasoning for science question answering.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- ScienceQA Visual
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- scienceqa-visual|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about ScienceQA Visual.
Which model scores highest on ScienceQA Visual?
Phi-4-multimodal-instruct is currently ranked first with 97.5%.
What does ScienceQA Visual measure?
ScienceQA Visual is a multimodal science question answering benchmark consisting of 21,208 multiple-choice questions from elementary and high school science curricula. The dataset covers 3 subjects (natural science, language science, social science), 26 topics, 127 categories, and 379 skills. 48.7% of questions include image context requiring multimodal reasoning. Questions are annotated with lectures (83.9%) and explanations (90.5%) to support chain-of-thought reasoning for science question answering.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.