LingoQA
Qwen 3.8 Max 84.8% leads since Aug 2026 In use Models answer free-form questions about short driving videos. A trained classifier, Lingo-Judge, scores whether each answer is truthful.
In the authors’ words
We introduce LingoQA, a novel dataset and benchmark for visual question answering in autonomous driving. The dataset contains 28K unique short video scenarios, and 419K annotations. Evaluating state-of-the-art vision-language models on our benchmark shows that their performance is below human capabilities, with GPT-4V responding truthfully to 59.6% of the questions compared to 96.6% for humans. For evaluation, we propose a truthfulness classifier, called Lingo-Judge, that achieves a 0.95 Spearman correlation coefficient to human evaluations, surpassing existing techniques like METEOR, BLEU, CIDEr, and GPT-4. We establish a baseline vision-language model and run extensive ablation studies to understand its performance. We release our dataset and benchmark as an evaluation platform for vision-language models in autonomous driving.
- Level
- Everyday Most adults, without training
- Scored
- Graded by a model A language model scores each response, usually against a rubric.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
Qwen 3.8 Max leads with 84.8% among models released by Aug 2026
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in Aug 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 Qwen 3.8 Max 84.8%
- 2 Qwen3.7-Plus 83.4%
- 3 Qwen3.5 397B-A17B 81.6%
- 4 Qwen3.5-122B-A10B 80.8%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Qwen 3.8 Max | 84.8% | Aug 2026 | Model card | |
| 2 | Qwen3.7-Plus | 83.4% | Jun 2026 | Model card | |
| 3 | Qwen3.5 397B-A17B | 81.6% | Feb 2026 | Model card | |
| 4 | Qwen3.5-122B-A10B | 80.8% | Feb 2026 | Model card |
3 models have held number one since its release in Dec 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
One lab put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 3 Aug 2026 | Qwen 3.8 Max | 84.8 | LingoQA |
| 1 Jun 2026 | Qwen3.7-Plus | 83.4 | LingoQA |
| 24 Feb 2026 | Qwen3.5-122B-A10B | 80.8 | LingoQA |
| 16 Feb 2026 | Qwen3.5 397B-A17B | 81.6 | LingoQA |
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. GPT-5.1 85.4%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. Kimi K3.1 Pro 84.1%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy. Qwen 3.8 Max 97.7%
- ChartQA In use Models answer human-written and generated questions about chart images that need visual and arithmetic reasoning. Scored by relaxed accuracy with a 5 percent numeric tolerance.
Command A Vision 90.9% - DocVQA In use Models answer 50,000 questions about 12,000 scanned document images by reading their text and layout. Scoring is ANLS, a string similarity to reference answers.
Seed1.5-VL 96.9%