Multimodal · Benchmark profile
A grounded visual reasoning benchmark focused on evidence-based question answering over real images.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on ERQA
Qwen3.7-Plus leads at 69.8%, followed by Gemini 3.1 Pro (69.4%) and GPT-5.4 (65.4%).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
7 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| Qwen3.7-Plus | #1 | Alibaba Cloud | 69.8% |
| Gemini 3.1 Pro | #2 | 69.4% | |
| GPT-5.4 | #3 | OpenAI | 65.4% |
| Muse Spark | #4 | Meta | 64.7% |
| Qwen3.6 27B | #5 | Alibaba Cloud | 62.5% |
| Grok 4.20 | #6 | xAI | 54.1% |
| Claude Opus 4.6 | #7 | Anthropic | 51.6% |
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 | 69.8% |
| #2 | Gemini 3.1 Pro gemini-3-1-pro | closed | Estimated reference | 69.4% | |
| #3 | GPT-5.4 gpt-5.4 | OpenAI | closed | Reference only | 65.4% |
| #4 | Muse Spark muse-spark | Meta | closed | Reference only | 64.7% |
| #5 | Qwen3.6 27B qwen3.6-27b | Alibaba Cloud | open | Estimated reference | 62.5% |
| #6 | Grok 4.20 grok-4.20 | xAI | closed | Estimated reference | 54.1% |
| #7 | Claude Opus 4.6 claude-opus-4-6 | Anthropic | closed | Reference only | 51.6% |
The top of this snapshot is led by Qwen3.7-Plus at 69.8%; third place is 4.4 points behind. The top-7 spread is 18.2 points.
About ERQA
A grounded visual reasoning benchmark focused on evidence-based question answering over real images. 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 reasoning benchmark focused on evidence-based question answering over real images.
Qwen3.7-Plus by Alibaba Cloud currently leads with 69.8%.
7 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
