VeBrain: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1554 ± 31, rank #1645 of 10916 rated models, from 34 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| NutriBench-Kitchen - Memory Management (Hard) | 68.7 | Score (%; the memory management task family, hard regime: di | 90.9 |
| NutriBench-Kitchen - Ingredient Entry (Easy) | 34.7 | Score (%; the ingredient entry task family, easy regime: sin | 81.8 |
| NutriBench-Kitchen - Memory Management (Easy) | 40.7 | Score (%; the memory management task family, easy regime: si | 81.8 |
| NutriBench-Kitchen - Recipe Query (Easy) | 67.3 | Score (%; the recipe query task family, easy regime: single- | 81.8 |
| NutriBench-Kitchen - Recipe Query (Hard) | 66.3 | Score (%; the recipe query task family, hard regime: differe | 81.8 |
| NutriBench-Kitchen | 52.6 | Average score (%; unweighted mean of the ten task-regime cel | 72.7 |
| NutriBench-Kitchen - Short-Term Planning (Hard) | 53.3 | Score (%; the short-term planning task family, hard regime: | 63.6 |
| NutriBench-Kitchen - Long-Term Planning (Hard) | 57.3 | Score (%; the long-term planning task family, hard regime: d | 59.1 |
| NutriBench-Kitchen - Short-Term Planning (Easy) | 52 | Score (%; the short-term planning task family, easy regime: | 54.5 |
| EPIC-Bench - Placement Region | 32.3 | Manipulation score (0-100) on placement region (where an obj | 40.9 |
| EPIC-Bench - Ground Detection | 29.56 | Navigation score (0-100) on ground detection (localizing tra | 39.8 |
| FlagEval EmbodiedVerse - BLINK (val) | 66.91 | Score | 39.1 |
Interactive version: theaggregate.ai/model?slug=vebrain · How It Works · Data refreshed daily, snapshot 2026-11-08.