Benchmark category
Spatial Reasoning evaluations, model coverage and rankings. Each benchmark keeps its original scale and methodology.
Data as of 2026-08-17
Select a benchmark to inspect model results, evidence fields and scoring direction.
Benchmark | Family | Modality | Metric | Coverage | Coverage tier | Evidence | Score eligible |
|---|
| BenchmarkRealWorldQA | FamilyRealWorldQA | Modalitymultimodal | MetricScore | Coverage29 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkScreenSpot Pro | FamilyScreenSpot Pro | Modalitymultimodal | MetricScore | Coverage25 | Coverage tierfeatured | EvidenceC | Score eligibleYes |
| BenchmarkERQA | FamilyERQA | Modalitymultimodal | MetricScore | Coverage24 | Coverage tierfeatured | EvidenceC | Score eligibleYes |
| BenchmarkPolyMATH | FamilyPolyMATH | Modalitymultimodal | MetricScore | Coverage23 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkARC-AGI v2 | FamilyARC-AGI v2 | Modalitymultimodal | MetricScore | Coverage17 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkMVBench | FamilyMVBench | Modalitymultimodal | MetricScore | Coverage17 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkScreenSpot | FamilyScreenSpot | Modalitymultimodal | MetricScore | Coverage16 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkBLINK | FamilyBLINK | Modalitymultimodal | MetricScore | Coverage15 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkGraphwalks BFS <128k | FamilyGraphwalks BFS <128k | Modalitytext | MetricScore | Coverage11 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkGraphwalks BFS >128k | FamilyGraphwalks BFS >128k | Modalitytext | MetricScore | Coverage11 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkGraphwalks parents <128k | FamilyGraphwalks parents <128k | Modalitytext | MetricScore | Coverage11 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
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.