Time-R1-7B: benchmark results
Provider: Other.
Aggregate Rating 1590 ± 52, rank #1042 of 10552 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EG-VQA - Evidence Grounding | 16.46 | Evidence-grounded F1 (%, EG-F1 at temporal IoU 0.3 and seman | 87.5 |
| MMVIAD - Defect Classification | 31.3 | Accuracy (%; MMVIAD-Standard test split, 1,101 rendered 2-se | 60 |
| EG-VQA - Counterfactual | 21.15 | Strict accuracy (%) on counterfactual questions (outcomes of | 50 |
| MMVIAD | 42.1 | Mean of three accuracies and visible-time mIoU (%; MMVIAD-St | 50 |
| MMVIAD - Unseen Categories | 46.2 | Mean of three accuracies and visible-time mIoU (%; MMVIAD-Un | 50 |
| MMVIAD - Anomaly Visible-Time Localization | 31.1 | Mean temporal IoU (%; MMVIAD-Standard test split, predicted | 45 |
| MMVIAD - Anomaly Detection | 40.8 | Accuracy (%; MMVIAD-Standard test split, 1,101 rendered 2-se | 40 |
| MMVIAD - Object Classification | 65 | Accuracy (%; MMVIAD-Standard test split, 1,101 rendered 2-se | 40 |
| EG-VQA | 15.66 | Strict accuracy (%): share of answers the judge rates fully | 37.5 |
| EG-VQA - Descriptive | 10.52 | Strict accuracy (%) on descriptive questions (directly obser | 37.5 |
| EG-VQA - Relaxed Accuracy | 30.44 | Relaxed accuracy (%): fully correct answers count 1 and part | 37.5 |
| EG-VQA - Temporal | 7.74 | Strict accuracy (%) on temporal questions (event order and p | 37.5 |
Interactive version: theaggregate.ai/model?slug=time-r1-7b · How It Works · Data refreshed daily, snapshot 2026-11-16.