Benchmark

HiPhO Benchmark

What is HiPhO?

HiPhO is a high-school physics olympiad benchmark evaluating multimodal reasoning over physics problems that include diagrams and figures.

Modality
multimodal
Evaluates
multimodal, reasoning, science, vision
Openness
unknown
Importer
LLM Stats
Reported scores
1

Source provenance

HiPhO results and reported scores

LLM Stats

ModelOrganizationReported valueReportedEvidence
Qwen3.7-PlusQwen0.8412026-05-31evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.

Which sources cite HiPhO?

Related multimodal, reasoning, science, vision benchmarks