SuperCLUE-V
Models answer Chinese questions about visual inputs.
SuperCLUE reports scores in a public workbook.
- Made by
- SuperCLUE
- Kind
- General visual questions
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Measures
- Capability
- Language
- Chinese
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- A host
- In views
- Vision
- Strongest model tested
-
Gemini 1.5 Pro Sep 2024 #157 on the capability index
- Last model added
- September 2024
- Scores refreshed
- November 20th, 2026
ChatGPT-4o-latest tops the leaderboard with 77.8 GPT-4o leads with 75.1 among models released by September 2024
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. The best model we track is GPT-4o, at 75.1. This view shows only models we track, each at its best.
The newest model with a score here came out in September 2024, 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
- 77.8 ChatGPT-4o-latest
- 75.1 GPT-4o
- 74.0 Step-1V-8k
- 73.6 hunyuan-vision
- 73.6 SenseChat-Vision 5.5
- 73.3 Claude 3.5 Sonnet
- 72.5
InternVL2-40B
- 70.7
Gemini 1.5 Pro
- 69.3 ERNIE-4-Turbo
- 68.4 Qwen2-VL-72B
- 67.5 GLM-4V-Plus
- 66.9 MiniCPM-V-2_6
- 65.9 GPT-4-Turbo-0409
- 65.0 海螺AI
- 64.4 Yi-Vision
- 55.8 DeekSeek-VL-7b-chat
- 45.0 Phi-3.5-vision-instruct
- 1 ChatGPT-4o-latest API 77.8
- 2 GPT-4o May 2024, API 75.1
- 3 Step-1V-8k API 74.0
- 4 hunyuan-vision API 73.6
- 5 SenseChat-Vision 5.5 API 73.6
- 6 Claude 3.5 Sonnet POE 73.3
- 7
InternVL2-40B 模型 72.5
- 8
Gemini 1.5 Pro Sep 2024, POE 70.7
- 9 ERNIE-4-Turbo 网页 69.3
- 10 Qwen2-VL-72B API 68.4
- 11 GLM-4V-Plus API 67.5
- 12 MiniCPM-V-2_6 模型 66.9
- 13 GPT-4-Turbo-0409 API 65.9
- 14 海螺AI 网页 65.0
- 15 Yi-Vision API 64.4
- 16 DeekSeek-VL-7b-chat 模型 55.8
- 17 Phi-3.5-vision-instruct 模型 45.0
Source: Official SuperCLUE-V leaderboard
- 1 GPT-4o May 2024, API 75.1
- 2 Claude 3.5 Sonnet POE 73.3
- 3
InternVL2-40B 模型 72.5
- 4
Gemini 1.5 Pro Sep 2024, POE 70.7
- 5 MiniCPM-V-2_6 模型 66.9
- 6 Phi-3.5-vision-instruct 模型 45.0
Source: Official SuperCLUE-V leaderboard
| # | Entry | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | ChatGPT-4o-latest | 77.8 | API | Oct 2024 | Official leaderboard | |
| 2 | GPT-4o May 2024 | 75.1 | API | May 2024 | Oct 2024 | Official leaderboard |
| 3 | Step-1V-8k | 74.0 | API | Oct 2024 | Official leaderboard | |
| 4 | hunyuan-vision | 73.6 | API | Oct 2024 | Official leaderboard | |
| 5 | SenseChat-Vision 5.5 | 73.6 | API | Oct 2024 | Official leaderboard | |
| 6 | Claude 3.5 Sonnet | 73.3 | POE | Jun 2024 | Oct 2024 | Official leaderboard |
| 7 | | 72.5 | 模型 | Jul 2024 | Oct 2024 | Official leaderboard |
| 8 | | 70.7 | POE | Sep 2024 | Oct 2024 | Official leaderboard |
| 9 | ERNIE-4-Turbo | 69.3 | 网页 | Oct 2024 | Official leaderboard | |
| 10 | Qwen2-VL-72B | 68.4 | API | Oct 2024 | Official leaderboard | |
| 11 | GLM-4V-Plus | 67.5 | API | Oct 2024 | Official leaderboard | |
| 12 | MiniCPM-V-2_6 | 66.9 | 模型 | Aug 2024 | Oct 2024 | Official leaderboard |
| 13 | GPT-4-Turbo-0409 | 65.9 | API | Oct 2024 | Official leaderboard | |
| 14 | 海螺AI | 65.0 | 网页 | Oct 2024 | Official leaderboard | |
| 15 | Yi-Vision | 64.4 | API | Oct 2024 | Official leaderboard | |
| 16 | DeekSeek-VL-7b-chat | 55.8 | 模型 | Oct 2024 | Official leaderboard | |
| 17 | Phi-3.5-vision-instruct | 45.0 | 模型 | Aug 2024 | Oct 2024 | Official leaderboard |
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | GPT-4o May 2024 | 75.1 | API | May 2024 | Oct 2024 | Official leaderboard |
| 2 | Claude 3.5 Sonnet | 73.3 | POE | Jun 2024 | Oct 2024 | Official leaderboard |
| 3 | | 72.5 | 模型 | Jul 2024 | Oct 2024 | Official leaderboard |
| 4 | | 70.7 | POE | Sep 2024 | Oct 2024 | Official leaderboard |
| 5 | MiniCPM-V-2_6 | 66.9 | 模型 | Aug 2024 | Oct 2024 | Official leaderboard |
| 6 | Phi-3.5-vision-instruct | 45.0 | 模型 | Aug 2024 | Oct 2024 | Official leaderboard |
Rankings by part
We read 12 parts from the benchmark’s own leaderboard in 2 groups: 基础认知能力 and 应用能力. Each ranks models on one part of the test. GPT-4o leads 7 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
基础认知能力
6 models we track have a score here.
- 1
Gemini 1.5 Pro Sep 2024 ↑3 72.0
- 2 Claude 3.5 Sonnet 71.7
- 3
InternVL2-40B 71.1
- 4 GPT-4o May 2024 ↓3 70.8
- 5 MiniCPM-V-2_6 66.0
- 6 Phi-3.5-vision-instruct 47.1
应用能力
6 models we track have a score here.
- 1 GPT-4o May 2024 77.9
- 2 Claude 3.5 Sonnet 73.9
- 3
InternVL2-40B 73.9
- 4
Gemini 1.5 Pro Sep 2024 69.1
- 5 MiniCPM-V-2_6 66.8
- 6 Phi-3.5-vision-instruct 42.3
分数
6 models we track have a score here.
- 1
Gemini 1.5 Pro Sep 2024 ↑3 72.0
- 2 Claude 3.5 Sonnet 71.7
- 3
InternVL2-40B 71.1
- 4 GPT-4o May 2024 ↓3 70.8
- 5 MiniCPM-V-2_6 66.0
- 6 Phi-3.5-vision-instruct 47.1
粗粒度视觉认知
6 models we track have a score here.
- 1 GPT-4o May 2024 73.8
- 2
Gemini 1.5 Pro Sep 2024 ↑2 73.3
- 3 Claude 3.5 Sonnet ↓1 73.2
- 4 MiniCPM-V-2_6 ↑1 71.0
- 5
InternVL2-40B ↓2 70.8
- 6 Phi-3.5-vision-instruct 52.5
细粒度视觉认知
6 models we track have a score here.
- 1 Claude 3.5 Sonnet ↑1 67.2
- 2 GPT-4o May 2024 ↓1 66.0
- 3
InternVL2-40B 65.9
- 4
Gemini 1.5 Pro Sep 2024 64.8
- 5 MiniCPM-V-2_6 56.4
- 6 Phi-3.5-vision-instruct 44.5
数理逻辑分析
6 models we track have a score here.
- 1
Gemini 1.5 Pro Sep 2024 ↑3 75.2
- 2 Claude 3.5 Sonnet 73.8
- 3
InternVL2-40B 72.9
- 4 GPT-4o May 2024 ↓3 72.5
- 5 MiniCPM-V-2_6 65.8
- 6 Phi-3.5-vision-instruct 42.0
多模态多轮问答
6 models we track have a score here.
- 1
Gemini 1.5 Pro Sep 2024 ↑3 74.9
- 2
InternVL2-40B ↑1 74.7
- 3 Claude 3.5 Sonnet ↓1 72.8
- 4 MiniCPM-V-2_6 ↑1 71.0
- 5 GPT-4o May 2024 ↓4 71.0
- 6 Phi-3.5-vision-instruct 49.7
分数
6 models we track have a score here.
- 1 GPT-4o May 2024 77.9
- 2 Claude 3.5 Sonnet 73.9
- 3
InternVL2-40B 73.9
- 4
Gemini 1.5 Pro Sep 2024 69.1
- 5 MiniCPM-V-2_6 66.8
- 6 Phi-3.5-vision-instruct 42.3
通用场景
6 models we track have a score here.
- 1 GPT-4o May 2024 74.8
- 2 Claude 3.5 Sonnet 72.1
- 3
InternVL2-40B 69.1
- 4
Gemini 1.5 Pro Sep 2024 68.7
- 5 MiniCPM-V-2_6 64.0
- 6 Phi-3.5-vision-instruct 48.3
常识问答
6 models we track have a score here.
- 1 GPT-4o May 2024 80.3
- 2
InternVL2-40B ↑1 79.8
- 3 Claude 3.5 Sonnet ↓1 78.5
- 4
Gemini 1.5 Pro Sep 2024 74.0
- 5 MiniCPM-V-2_6 69.5
- 6 Phi-3.5-vision-instruct 37.7
图像OCR识别与理解
6 models we track have a score here.
- 1 GPT-4o May 2024 85.3
- 2
InternVL2-40B ↑1 76.9
- 3 Claude 3.5 Sonnet ↓1 76.0
- 4 MiniCPM-V-2_6 ↑1 73.3
- 5
Gemini 1.5 Pro Sep 2024 ↓1 67.4
- 6 Phi-3.5-vision-instruct 42.6
中文元素理解和推理
6 models we track have a score here.
- 1 GPT-4o May 2024 71.4
- 2
InternVL2-40B ↑1 69.7
- 3 Claude 3.5 Sonnet ↓1 68.8
- 4
Gemini 1.5 Pro Sep 2024 66.4
- 5 MiniCPM-V-2_6 60.6
- 6 Phi-3.5-vision-instruct 40.4
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official SuperCLUE-V 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-V 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 (17 entries).
- Pass Models scored 6 models we track, plus 11 other entries on its leaderboard.
- Warning Newest score The newest came 2 years ago, in September 2024, for Gemini 1.5 Pro.
- Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 1.5 Pro (#157).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on superclueai.com: 6 rows for models we track and 11 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.