multimodal benchmark
HiPhO
HiPhO is a high-school physics olympiad benchmark evaluating multimodal reasoning over physics problems that include diagrams and figures.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
HiPhO leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 84.1% | 100.0% | 1 | C |
HiPhO highlights
The top published results on this benchmark's own scale.
What is HiPhO?
Definition and scoring fields from the benchmark registry.
HiPhO is a high-school physics olympiad benchmark evaluating multimodal reasoning over physics problems that include diagrams and figures.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- HiPhO
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- hipho|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about HiPhO.
Which model scores highest on HiPhO?
Qwen3.7-Plus is currently ranked first with 84.1%.
What does HiPhO measure?
HiPhO is a high-school physics olympiad benchmark evaluating multimodal reasoning over physics problems that include diagrams and figures.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.