math benchmark
FunctionalMATH
A functional variant of the MATH benchmark that tests language models' ability to generalize reasoning patterns across different problem instances, revealing the reasoning gap between static and functional performance.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
FunctionalMATH leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | GO | 64.6% | 100.0% | 2 | C | |
| 2 | GO | 53.6% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
FunctionalMATH highlights
The top published results on this benchmark's own scale.
What is FunctionalMATH?
Definition and scoring fields from the benchmark registry.
A functional variant of the MATH benchmark that tests language models' ability to generalize reasoning patterns across different problem instances, revealing the reasoning gap between static and functional performance.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- FunctionalMATH
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- functionalmath|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about FunctionalMATH.
Which model scores highest on FunctionalMATH?
Gemini 1.5 Pro is currently ranked first with 64.6%.
What does FunctionalMATH measure?
A functional variant of the MATH benchmark that tests language models' ability to generalize reasoning patterns across different problem instances, revealing the reasoning gap between static and functional performance.
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.