# RealWorldQA

> A grounded visual QA benchmark focused on answering practical questions about real-world images and scenes.

Canonical page: https://benchlm.ai/benchmarks/realworldqa

- Category: [Multimodal & Grounded](/multimodal-grounded)
- Last updated: September 27, 2026

## About RealWorldQA

- Year: 2026
- Tasks: Real-world visual question answering
- Format: Image-grounded QA
- Difficulty: General visual reasoning
- Paper: [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6)

RealWorldQA is useful because it emphasizes practical perception and grounded answering on realistic images rather than synthetic or purely academic multimodal tasks.

RealWorldQA is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (12 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Qwen3.8-Flash-Next](/models/qwen3-8-flash-next) | Alibaba | 88.5% |
| 2 | [Qwen3.8 Max](/models/qwen3-8-max) | Alibaba | 88.0% |
| 3 | [Qwen3.8-Omni-Flash](/models/qwen3-8-omni-flash) | Alibaba | 87.7% |
| 4 | [Qwen3.7 Plus](/models/qwen3-7-plus) | Alibaba | 86.9% |
| 5 | [Qwen3.8-27B](/models/qwen3-8-27b) | Alibaba | 85.9% |
| 6 | [Qwen3.6-35B-A3B](/models/qwen3-6-35b-a3b) | Alibaba | 85.3% |
| 7 | [Qwen3.6-27B](/models/qwen3-6-27b) | Alibaba | 84.1% |
| 8 | [Ternary Bonsai 2 27B](/models/ternary-bonsai-2-27b) | Prism ML | 80.1% |
| 9 | [LFM2.5-VL-3B](/models/lfm2-5-vl-3b) | LiquidAI | 73.1% |
| 10 | [ZAYA1-VL-8B](/models/zaya1-vl-8b) | Zyphra | 65.0% |
| 11 | [North Micro Vision Instruct](/models/north-micro-vision-instruct) | Cohere | 62.2% |
| 12 | [LFM2.5-VL-450M](/models/lfm2-5-vl-450m) | LiquidAI | 58.4% |

## FAQ

### What does RealWorldQA measure?

A grounded visual QA benchmark focused on answering practical questions about real-world images and scenes.

### Which model scores highest on RealWorldQA?

Qwen3.8-Flash-Next by Alibaba currently leads with a score of 88.5% on RealWorldQA.

### How many models are evaluated on RealWorldQA?

12 AI models have been evaluated on RealWorldQA on BenchLM.

### Does RealWorldQA affect BenchLM's overall score?

Not directly. RealWorldQA is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on RealWorldQA

- [Qwen3.8-Flash-Next vs Qwen3.8 Max](/compare/qwen3-8-flash-next-vs-qwen3-8-max)
- [Qwen3.8 Max vs Qwen3.8-Omni-Flash](/compare/qwen3-8-max-vs-qwen3-8-omni-flash)
- [Qwen3.8-Omni-Flash vs Qwen3.7 Plus](/compare/qwen3-7-plus-vs-qwen3-8-omni-flash)
- [Qwen3.7 Plus vs Qwen3.8-27B](/compare/qwen3-7-plus-vs-qwen3-8-27b)