| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Visual Question Answering | LingoQA | Accuracy69.9 | 16 | |
| Semantic Reasoning | LingoQA | Score68.6 | 15 | |
| Autonomous Driving Perception and Planning | LingoQA | PER. & PLA.69.9 | 12 | |
| Open-ended Question Answering | LingoQA | ROUGE-L32 | 8 | |
| Video Question Answering | LingoQA (test) | Ling-Judge60.8 | 8 | |
| Autonomous Driving Question Answering | LingoQA (val) | Lingo-J61 | 6 | |
| Driving Video Question Answering | LingoQA | LingoJudge70.8 | 5 | |
| Driving Video Question Answering | LingoQA 25% Token Retention | LingoJudge Score70.8 | 5 | |
| Visual Question Answering | LingoQA | Lingo-Judge67.2 | 4 |