Graduate physics problems in QSA format, targeting the visual-reasoning weaknesses measurable on MMMU Physics and OlympiadBench MM.
Available Now · Sample Available
Multimodal Physics QSA
Graduate physics problems anchored in spectra and experimental figures.
Volume
0
Volume
Scalable Volume
Coverage
Grad, PhD, Physics
Model Benchmark
0.0
%
Frontier Model · Pass at k
Targets
MMMU-Pro, OlympiadBench (MM physics), HLE (MM), MMMU (Physics), MathVista
Modality & Delivery
ImageText→Text
Formats
Excel (.xlsx)Images
What You Receive
Coverage
Problems paired with spectra, experimental figures, and structural diagrams.
Package Structure
Differentiators
- Structured question, worked solution, and final answer record format.
- Pairs domain questions with task-relevant visual evidence.
Record Schema
| Field | Description |
|---|---|
answer | The concise final answer associated with the question. |
image_ref | Reference to the image associated with the record, when supplied. |
question | The question or task presented in the dataset record. |
solution | The worked solution or supporting reasoning for the question. |
Results
| Model | Metric | Result |
|---|---|---|
| Frontier Model | Pass@1 | |
| Claude Opus 5 | Pass@1 | |
| Claude Opus 5 | Pass@3 |
Methodology & Quality
Methodology
Questions are expert-authored, then split across an SME pool for complexity validation before benchmarking.
SME involvement
Domain-expert curated with up to L2 review
Stressors
Combined visual interpretation and domain reasoning.
Design criteria
- Keep the question, supporting solution, and final answer as distinct record components.
- Require visual extraction together with domain-specific reasoning.
Build assumptions
Quality approach
Known limitations
Customization & Scalability
Custom sets available. Additional volume in progress