Long-VITA-16K: benchmark results
Provider: Tencent. Released 2025-03-05. Access: Open.
Aggregate Rating 1502 ± 25, rank #2330 of 10916 rated models, from 207 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM Video - MVBench - Object Shuffle | 44.5 | Accuracy (%) | 97.2 |
| OpenVLM MMBench V1.1 CN - OCR | 98.9 | Accuracy (%) | 94 |
| OpenVLM MMBench V1.1 EN - Image Scene | 91 | Accuracy (%) | 93.5 |
| OpenVLM MMBench V1.1 EN - OCR | 98.9 | Accuracy (%) | 93.3 |
| OpenVLM MMBench V1.1 CN - Image Topic | 98.9 | Accuracy (%) | 90.3 |
| OpenVLM Video - MVBench - Scene Transition | 94.5 | Accuracy (%) | 90.3 |
| OpenVLM MMMU - Design | 83.3 | Accuracy (%) | 86.7 |
| OpenVLM MathVista - LOG | 32.4 | Accuracy (%) | 85.7 |
| OpenVLM AI2D - Rock Strata | 82.9 | Accuracy (%) | 84.8 |
| OpenVLM MMMU - Management | 66.7 | Accuracy (%) | 84.5 |
| OpenVLM MMMU - Geography | 60 | Accuracy (%) | 83.7 |
| OpenVLM Video - MLVU - Action Count | 42.2 | Accuracy (%) | 83.3 |
Interactive version: theaggregate.ai/model?slug=long-vita-16k · How It Works · Data refreshed daily, snapshot 2026-11-08.