reasoning benchmark
Frontier Science
Frontier Science is a benchmark of exceptionally challenging scientific reasoning problems spanning advanced natural-science domains, designed to test expert-level scientific understanding and multi-step reasoning.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
Frontier Science Ranking
Higher score ranks better on this benchmark.
| 01 | MI | 58.2% | 100.0% | 1 | C |
Frontier Science Highlights
The leading models and scores on this benchmark.
What is Frontier Science?
What Frontier Science measures and how its scores work.
Frontier Science is a benchmark of exceptionally challenging scientific reasoning problems spanning advanced natural-science domains, designed to test expert-level scientific understanding and multi-step reasoning.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Frontier Science
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- frontier-science|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Frontier Science.
Which model scores highest on Frontier Science?
MAI-Code-1-Flash is currently ranked first with 58.2%.
What does Frontier Science measure?
Frontier Science is a benchmark of exceptionally challenging scientific reasoning problems spanning advanced natural-science domains, designed to test expert-level scientific understanding and multi-step reasoning.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.