Multimodal · Benchmark profile
A grounded visual QA benchmark focused on answering practical questions about real-world images and scenes.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on RealWorldQA
Qwen3.7-Plus leads at 86.9%, followed by Qwen3.6-35B-A3B (85.3%) and Qwen3.6 27B (84.1%).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
4 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| Qwen3.7-Plus | #1 | Alibaba Cloud | 86.9% |
| Qwen3.6-35B-A3B | #2 | Alibaba Cloud | 85.3% |
| Qwen3.6 27B | #3 | Alibaba Cloud | 84.1% |
| LFM2.5-VL-450M | #4 | LiquidAI | 58.4% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | Qwen3.7-Plus qwen3.7-plus | Alibaba Cloud | — | Reference only | 86.9% |
| #2 | Qwen3.6-35B-A3B qwen3-6-35b-a3b | Alibaba Cloud | open | Estimated reference | 85.3% |
| #3 | Qwen3.6 27B qwen3.6-27b | Alibaba Cloud | open | Estimated reference | 84.1% |
| #4 | LFM2.5-VL-450M lfm2-5-vl-450m | LiquidAI | open | Estimated reference | 58.4% |
The top of this snapshot is led by Qwen3.7-Plus at 86.9%; third place is 2.8 points behind. The top-4 spread is 28.5 points.
About RealWorldQA
A grounded visual QA benchmark focused on answering practical questions about real-world images and scenes. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
A grounded visual QA benchmark focused on answering practical questions about real-world images and scenes.
Qwen3.7-Plus by Alibaba Cloud currently leads with 86.9%.
4 models in the LuminaBench cohort have a qualifying score on this benchmark.
No. This benchmark is display-only and does not enter the overall Lumina composite.
Related
