reasoning benchmark
FrontierCS
FrontierCS is a benchmark of frontier computer-science problems requiring deep theoretical understanding and rigorous multi-step reasoning at the edge of the field.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
FrontierCS leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | BY | 50.8% | 100.0% | 2 | C | |
| 2 | BY | 46.3% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
FrontierCS highlights
The top published results on this benchmark's own scale.
What is FrontierCS?
Definition and scoring fields from the benchmark registry.
FrontierCS is a benchmark of frontier computer-science problems requiring deep theoretical understanding and rigorous multi-step reasoning at the edge of the field.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- FrontierCS
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- frontiercs|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about FrontierCS.
Which model scores highest on FrontierCS?
Seed 2.1 Turbo is currently ranked first with 50.8%.
What does FrontierCS measure?
FrontierCS is a benchmark of frontier computer-science problems requiring deep theoretical understanding and rigorous multi-step reasoning at the edge of the field.
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.