physics benchmark
IPhO 2025
International Physics Olympiad 2025 (theory) comprises all 3 theory problems from the official 2025 IPhO competition. Results are based on blinded human evaluation with guidelines based on the official competition scoring, validated by domain experts.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
IPhO 2025 leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | ME | 82.6% | 100.0% | 2 | C | |
| 2 | BY | 79.3% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
IPhO 2025 highlights
The top published results on this benchmark's own scale.
What is IPhO 2025?
Definition and scoring fields from the benchmark registry.
International Physics Olympiad 2025 (theory) comprises all 3 theory problems from the official 2025 IPhO competition. Results are based on blinded human evaluation with guidelines based on the official competition scoring, validated by domain experts.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- IPhO 2025
- Modality
- text
- Primary category
- physics
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- ipho-2025|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about IPhO 2025.
Which model scores highest on IPhO 2025?
Muse Spark is currently ranked first with 82.6%.
What does IPhO 2025 measure?
International Physics Olympiad 2025 (theory) comprises all 3 theory problems from the official 2025 IPhO competition. Results are based on blinded human evaluation with guidelines based on the official competition scoring, validated by domain experts.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 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.