CRPE
Qwen2.5-VL-72B 79.2% leads since Feb 2025 Dropped Models answer single-choice questions about objects and their relations in images, covering subject, predicate and object. Each question is asked again with options rotated (CircularEval).
Has four splits, one for object existence and three for relation parts. Some images show rare relations generated with DALL-E 3. Labs usually report the relation split.
- Level
- Everyday Most adults, without training
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Multiple choice
Qwen2.5-VL-72B leads with 79.2% among models released by Oct 2025
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 Oct 2025, 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 Qwen2.5-VL-72B 79.2%
- 2
InternVL3.5-241B-A28B 78% - 3 Qwen2.5-Omni-7B 76.5%
- 4
Nemotron Nano 12B v2 VL 64.3%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Qwen2.5-VL-72B | 79.2% | Feb 2025 | Model card | |
| 2 | InternVL3.5-241B-A28B | 78% | Aug 2025 | Model card | |
| 3 | Qwen2.5-Omni-7B | 76.5% | Mar 2025 | Model card | |
| 4 | Nemotron Nano 12B v2 VL | 64.3% | Nov 2025 | Model card |
Number one over time
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.
No launch post has listed it since Mar 2025
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 |
|---|---|---|---|
| 27 Mar 2025 | Qwen2.5-Omni-7B | 76.5 | CRPErelation |
4 system cards report it, from 3 labs
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 6 Nov 2025 | Nemotron Nano 12B v2 VL technical report | 64.3 | CRPE (Relation), reasoning on (Table 3). Reasoning off 71.3 | Capabilities |
| 25 Aug 2025 | InternVL3.5-241B-A28B technical report | 78 | CRPE (relation) (Table 6) | Hallucination |
| 26 Mar 2025 | Qwen2.5-Omni-7B technical report | 76.5 | CRPE relation (Table 5) | Hallucination |
| 19 Feb 2025 | Qwen2.5-VL-72B technical report | 79.2 | CRPE relation (Table 3) | Capabilities |
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%