math benchmark
FrontierScience Olympiad
FrontierScience Olympiad is a benchmark of olympiad-level scientific reasoning problems, testing expert understanding and multi-step reasoning across advanced natural-science domains.
Updated Aug 7, 2026
Published models3
Registry coverage3
MetricScore
EvidenceB
FrontierScience Olympiad leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | BY | 76.0% | 100.0% | 3 | C | |
| 2 | BY | 75.0% | 50.0% | 3 | C | |
| 3 | TE | 74.8% | 0.0% | 3 | C |
Score distribution
Top published rows on the benchmark's original scale.
FrontierScience Olympiad highlights
The top published results on this benchmark's own scale.
What is FrontierScience Olympiad?
Definition and scoring fields from the benchmark registry.
FrontierScience Olympiad is a benchmark of olympiad-level scientific reasoning problems, testing expert understanding and multi-step reasoning across advanced natural-science domains.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- FrontierScience Olympiad
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- frontierscience-olympiad|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about FrontierScience Olympiad.
Which model scores highest on FrontierScience Olympiad?
Seed 2.1 Turbo is currently ranked first with 76.0%.
What does FrontierScience Olympiad measure?
FrontierScience Olympiad is a benchmark of olympiad-level scientific reasoning problems, testing expert understanding and multi-step reasoning across advanced natural-science domains.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 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.