step-1v-32k: benchmark results
Provider: StepFun. Access: API.
Aggregate Rating 1478 ± 48, rank #2677 of 10489 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CoreCognition Image only Permanence | 87.5 | Accuracy (%) | 96.7 |
| CoreCognition Image only Hierarchy | 68.04 | Accuracy (%) | 96.1 |
| CoreCognition Image only Mean | 64.5 | Accuracy (%) | 90.8 |
| CoreCognition Image only Mechanicalreasoning | 60.32 | Accuracy (%) | 90.8 |
| CoreCognition Image only Intentionality | 77.06 | Accuracy (%) | 88.2 |
| CoreCognition Image only Spatiality | 69.13 | Accuracy (%) | 88.2 |
| CoreCognition Image only Toolusing | 98.96 | Accuracy (%) | 82.2 |
| CoreCognition Image only Boundary | 76.5 | Accuracy (%) | 78.9 |
| CoreCognition Image only Perceptualconstancy | 65.5 | Accuracy (%) | 76.3 |
| CoreCognition Image only Intuitivephysics | 56.03 | Accuracy (%) | 60.5 |
| CoreCognition Image only Continuity | 61.33 | Accuracy (%) | 56.6 |
| CoreCognition Image only Perspective | 33.05 | Accuracy (%) | 41.4 |
Interactive version: theaggregate.ai/model?slug=step-1v-32k · How It Works · Data refreshed daily, snapshot 2026-11-20.