physics benchmark
IPhO 2025 Leaderboard
IPhO 2025 is a physics benchmark comprising all 3 theory problems from the official 2025 International Physics Olympiad competition.
Updated Oct 23, 2026
Models2
Model coverage2
MetricScore
EvidenceB
IPhO 2025 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelME | Score82.60% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelBY | Score79.30% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
IPhO 2025 Highlights
The leading models and scores on this benchmark.
IPhO 2025 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for IPhO 2025
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is IPhO 2025?
What IPhO 2025 measures and how its scores work.
A benchmark based on the theory portion of the official 2025 International Physics Olympiad competition.
It measures Score as a ratio, based on blinded human evaluation using guidelines based on the official competition scoring and validated by domain experts.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- IPhO 2025
- Modality
- text
- Primary category
- physics
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about IPhO 2025.
Which model scores highest on IPhO 2025?
Muse Spark is currently ranked first with 82.60%.
What are the top three models on IPhO 2025?
The current leaders are Muse Spark (82.60%) and Seed 2.1 Pro (79.30%).
Which IPhO 2025 model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among IPhO 2025 results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.