Benchmark category
Spatial Reasoning evaluations, model coverage and rankings. Each benchmark keeps its original scale and methodology.
Data as of 2026-08-11
Select a benchmark to inspect model results, evidence fields and scoring direction.
| RealWorldQA | RealWorldQA | multimodal | Score | 26 | featured | B | Yes |
| ScreenSpot Pro | ScreenSpot Pro | multimodal | Score | 25 | featured | C | Yes |
| ERQA | ERQA | multimodal | Score | 23 | featured | C | Yes |
| PolyMATH | PolyMATH | multimodal | Score | 23 | featured | B | Yes |
| MVBench | MVBench | multimodal | Score | 17 | featured | B | Yes |
| ARC-AGI v2 | ARC-AGI v2 | multimodal | Score | 16 | featured | B | Yes |
| ScreenSpot | ScreenSpot | multimodal | Score | 16 | featured | B | Yes |
| BLINK | BLINK | multimodal | Score | 13 | featured | B | Yes |
| Graphwalks BFS <128k | Graphwalks BFS <128k | text | Score | 11 | featured | B | Yes |
| Graphwalks BFS >128k | Graphwalks BFS >128k | text | Score | 11 | featured | B | Yes |
| Graphwalks parents <128k | Graphwalks parents <128k | text | Score | 11 | featured | B | Yes |
Leading results from high-coverage benchmarks with at least two models.
How this category is assembled on llmboard.ai.
This page groups benchmarks whose primary or display category matches spatial reasoning. It does not average incompatible metrics into a new category score.
Open an individual benchmark to inspect score direction, evidence level, participant count and model results.
Benchmarks are grouped by their primary and display categories.