UniSense Study - Audio-Image - DocVQA s: leaderboard
UniSense (2026): Audio-Image-text evaluation from the main paper table. Video-MME has no subtitles; audio-image variants provide spoken questions. Different input modes are separate benchmarks; source-reported comparison results retain their original identities. Score (%); higher is better.
Metric: Score (%). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | UniSense-9B | 87.2 | |
| 2 | Lyra-Base-9B | 85.5 | |
| 3 | UniSense-2B | 80 | |
| 4 | Intern-Omni | 79.9 | |
| 5 | Qwen3-Omni-30B-A3B | 76.4 | |
| 6 | Lyra-Mini-3B | 74.8 |
Interactive version: theaggregate.ai/benchmark?slug=unisense-study-audio-image-docvqa-s · How It Works · Data refreshed daily, snapshot 2026-10-21.