SenseNova-V6-Pro: benchmark results
Provider: SenseTime. Released 2025-04-10. Access: API.
Aggregate Rating 1636 ± 27, rank #720 of 10916 rated models, from 150 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM HallusionBench - aAcc | 79.3 | Accuracy (%) | 100 |
| OpenVLM MM-Vet - Spatial Awareness | 92.7 | Score | 100 |
| OpenVLM MMBench V1.1 EN - FP-S | 95.6 | Accuracy (%) | 100 |
| OpenVLM MMBench V1.1 EN - Object Localization | 95.2 | Accuracy (%) | 100 |
| OpenVLM MM-Vet - OCR | 91.4 | Score | 99.8 |
| OpenVLM MMBench V1.1 CN - Object Localization | 92.4 | Accuracy (%) | 99.8 |
| OpenVLM MMMU - Computer Science | 86.7 | Accuracy (%) | 99.8 |
| HallusionBench | 67.1 | Overall Score | 99.7 |
| MM-Vet | 88.2 | Score | 99.7 |
| OpenVLM AI2D - Photosynthesis and Respiration | 94.9 | Accuracy (%) | 99.6 |
| OpenVLM HallusionBench - fAcc | 62.1 | Accuracy (%) | 99.6 |
| OpenVLM HallusionBench - qAcc | 59.8 | Accuracy (%) | 99.6 |
Interactive version: theaggregate.ai/model?slug=sensenova-v6-pro · How It Works · Data refreshed daily, snapshot 2026-11-08.