R1-Onevision-7B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1483 ± 37, rank #2630 of 10916 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| VidPair-Halluc | 35.52 | Binary-QA weighted accuracy wAcc (%): question-pair and vide | 85.7 |
| VidPair-Halluc - Open-Ended Description | 42.37 | Open-ended description score (%) judged by GPT-4o on VidPair | 57.1 |
| We-Math | 30 | Avg Strict (%) | 53.1 |
| MCSBench - L3 | 20.61 | Accuracy (%) | 39.5 |
| MathVision | 29.9 | Overall Accuracy (%) | 35 |
| MCSBench - L2 | 38.6 | Accuracy (%) | 31.6 |
| SaLAD - Safe Queries | 97.67 | Accuracy rate (%; GPT-4o judge; 943 benign queries answered | 29.4 |
| MCSBench - Overall | 35.4 | Accuracy (%) | 28.9 |
| SaLAD | 56.53 | Accuracy rate (%; GPT-4o judge; all 2,013 image-text queries | 23.5 |
| SaLAD - Unsafe Queries | 20.28 | Accuracy rate (%; GPT-4o judge; 1,070 hazardous daily-life q | 23.5 |
| MCSBench - L1 | 41.38 | Accuracy (%) | 17.1 |
| VidPair-Halluc - Multi-Choice F1 | 29.23 | Multiple-choice F1 (%) for assessing and ranking clip-level | 14.3 |
Interactive version: theaggregate.ai/model?slug=r1-onevision-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.