Benchmark
InterGPS Benchmark
What is InterGPS?
Interpretable Geometry Problem Solver (Inter-GPS) with Geometry3K dataset of 3,002 geometry problems with dense annotation in formal language using theorem…
- Modality
- text
- Evaluates
- math, spatial reasoning
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 2
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/intergps?top_n=500
InterGPS results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Phi-3.5-vision-instruct | Microsoft | 0.363 | 2024-08-23 | evidence |
| Phi-4-multimodal-instruct | Microsoft | 0.486 | 2025-02-01 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.