SuperCLUE-VLR
Models solve problems that require visual reasoning.
SuperCLUE reports scores in a public workbook.
- Made by
- SuperCLUE
- Kind
- General visual questions
- Level
- University
- Scored
- Checked automatically
- Answers
- Short answer
- Measures
- Capability
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- A host
- In views
- Vision
- Strongest model tested
- o3 #84 on the capability index
- Last model added
- May 2025
- Scores refreshed
- November 20th, 2026
Gemini 2.5 Pro leads with 72.1 among models released by May 2025 Gemini 2.5 Pro leads with 72.1 among models released by May 2025
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in May 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1
Gemini 2.5 Pro May 2025, API 72.1
- 2 Doubao-1.5-Thinking-Vision-Pro API 65.3
- 3 QVQ-Max API 56.6
- 4 Hunyuan-T1-Vision API 56.0
- 5 K1.5 长思考 官网 53.7
- 6 Claude 3.7 Sonnet API 52.2
- 7 Step-R1-V-Mini API 50.7
- 8 o3 官网 47.2
- 9
InternVL3-78B 模型 39.6
- 10 GLM-4V-Plus-0111 API 39.4
Source: Official SuperCLUE-VLR leaderboard
- 1
Gemini 2.5 Pro May 2025, API 72.1
- 2 Claude 3.7 Sonnet API 52.2
- 3 o3 官网 47.2
- 4
InternVL3-78B 模型 39.6
Source: Official SuperCLUE-VLR leaderboard
| # | Entry | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | | 72.1 | API | May 2025 | May 2025 | Official leaderboard |
| 2 | Doubao-1.5-Thinking-Vision-Pro | 65.3 | API | May 2025 | Official leaderboard | |
| 3 | QVQ-Max | 56.6 | API | May 2025 | Official leaderboard | |
| 4 | Hunyuan-T1-Vision | 56.0 | API | May 2025 | Official leaderboard | |
| 5 | K1.5 长思考 | 53.7 | 官网 | May 2025 | Official leaderboard | |
| 6 | Claude 3.7 Sonnet | 52.2 | API | Feb 2025 | May 2025 | Official leaderboard |
| 7 | Step-R1-V-Mini | 50.7 | API | May 2025 | Official leaderboard | |
| 8 | o3 | 47.2 | 官网 | Apr 2025 | May 2025 | Official leaderboard |
| 9 | | 39.6 | 模型 | Apr 2025 | May 2025 | Official leaderboard |
| 10 | GLM-4V-Plus-0111 | 39.4 | API | May 2025 | Official leaderboard |
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | | 72.1 | API | May 2025 | May 2025 | Official leaderboard |
| 2 | Claude 3.7 Sonnet | 52.2 | API | Feb 2025 | May 2025 | Official leaderboard |
| 3 | o3 | 47.2 | 官网 | Apr 2025 | May 2025 | Official leaderboard |
| 4 | | 39.6 | 模型 | Apr 2025 | May 2025 | Official leaderboard |
Rankings by part
We read 6 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as 数学推理, 科学推理 and 代码推理. Gemini 2.5 Pro leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.
数学推理
4 models we track have a score here.
- 1
Gemini 2.5 Pro May 2025 87.2
- 2 Claude 3.7 Sonnet 78.9
- 3 o3 53.8
- 4
InternVL3-78B 39.8
科学推理
4 models we track have a score here.
- 1
Gemini 2.5 Pro May 2025 65.6
- 2 o3 ↑1 56.3
- 3 Claude 3.7 Sonnet ↓1 46.9
- 4
InternVL3-78B 28.1
代码推理
4 models we track have a score here.
- 1
Gemini 2.5 Pro May 2025 100.0
- 2 Claude 3.7 Sonnet 90.0
- 3 o3 88.8
- 4
InternVL3-78B 68.8
逻辑推理
4 models we track have a score here.
- 1
Gemini 2.5 Pro May 2025 47.2
- 2 Claude 3.7 Sonnet 31.7
- 3
InternVL3-78B ↑1 16.1
- 4 o3 ↓1 11.1
空间推理
4 models we track have a score here.
- 1
Gemini 2.5 Pro May 2025 39.8
- 2
InternVL3-78B ↑2 28.6
- 3 Claude 3.7 Sonnet ↓1 21.6
- 4 o3 ↓1 14.1
时间推理
4 models we track have a score here.
- 1
Gemini 2.5 Pro May 2025 92.9
- 2 o3 ↑1 59.1
- 3
InternVL3-78B ↑1 56.5
- 4 Claude 3.7 Sonnet ↓2 44.2
2 models have held number one on the official leaderboard since 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official SuperCLUE-VLR leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official SuperCLUE-VLR leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy.
Qwen 3.6 Plus 86%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy.
Seed2.1 Pro 90.7%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy.
Qwen 3.8 Max 97.7%
- MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy.
Qwen 3.8 Max 85.9%
Data audit
7 of 9 checks pass, 2 warnings. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark
Catalog record 1 warning 1 pass
- Warning Task access We don’t know whether the tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (10 entries).
- Pass Models scored 4 models we track, plus 6 other entries on its leaderboard.
- Warning Newest score The newest came 18 months ago, in May 2025, for Gemini 2.5 Pro.
- Note Frontier models None of the top 10 has a score. The strongest tested is o3 (#84).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on superclueai.com: 4 rows for models we track and 6 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.