Doubao-1.5-Thinking-Vision-Pro-250428: benchmark results
Provider: ByteDance.
Aggregate Rating 1651 ± 32, rank #619 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OmniTraffic - Temporal Reasoning | 50.7 | Accuracy (%) on temporal reasoning (order frames and track q | 80 |
| OmniTraffic - Scene Attributes | 85 | Accuracy (%) on scene attributes (weather and pedestrians in | 65 |
| OmniTraffic - Multi-View Comparison | 85.2 | Accuracy (%) on multi-view comparison (compare vehicle count | 50 |
| OmniTraffic - Special Event Recognition | 71.7 | Accuracy (%) on special event recognition (obstructions and | 50 |
| BABE (Biology Arena) | 31.71 | Average score (%), the paper's fixed weighting of its strong | 31.2 |
| BABE (Biology Arena) - Weak Correlation | 31.28 | Score (%) on the weak-correlation triplets of independent qu | 31.2 |
| OmniTraffic - Signal Phase Analysis | 72.8 | Accuracy (%) on signal phase analysis (vehicles and events p | 30 |
| OmniTraffic - View-BEV Mapping | 26 | Accuracy (%) on view to bird-eye-view mapping (map between a | 30 |
| BABE (Biology Arena) - Strong Correlation | 32.12 | Score (%) on the strong-correlation triplets, where each que | 25 |
| OmniTraffic | 53.4 | Overall accuracy (%) over all eleven task categories, multip | 20 |
| OmniTraffic - Road Infrastructure | 40.3 | Accuracy (%) on road infrastructure (lane counts and lane fu | 20 |
| OSWorld | 33.8 | Success Rate (%) | 19.7 |
Interactive version: theaggregate.ai/model?slug=doubao-1-5-thinking-vision-pro-250428 · How It Works · Data refreshed daily, snapshot 2026-11-08.