math benchmark
InterGPS
Interpretable Geometry Problem Solver (Inter-GPS) with Geometry3K dataset of 3,002 geometry problems with dense annotation in formal language using theorem knowledge and symbolic reasoning
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
InterGPS leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | MI | 48.6% | 100.0% | 2 | C | |
| 2 | MI | 36.3% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
InterGPS highlights
The top published results on this benchmark's own scale.
What is InterGPS?
Definition and scoring fields from the benchmark registry.
Interpretable Geometry Problem Solver (Inter-GPS) with Geometry3K dataset of 3,002 geometry problems with dense annotation in formal language using theorem knowledge and symbolic reasoning
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- InterGPS
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- intergps|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about InterGPS.
Which model scores highest on InterGPS?
Phi-4-multimodal-instruct is currently ranked first with 48.6%.
What does InterGPS measure?
Interpretable Geometry Problem Solver (Inter-GPS) with Geometry3K dataset of 3,002 geometry problems with dense annotation in formal language using theorem knowledge and symbolic reasoning
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.