SuperCLUE-VLM
Vision language models interpret images and answer questions in Chinese.
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
- Claude Opus 5.5 #5 on the capability index
- Last model added
- November 2026
- Scores refreshed
- November 20th, 2026
Gemini 4 Argon leads with 89.0 Gemini 4 Argon leads with 89.0
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.
- 89.0
Gemini 4 Argon
- 86.0 Claude Opus 5.5
- 82.7 GPT-6.1 Sol
- 79.9 Kimi K3.1 Pro
- 79.5 Doubao-Seed-2.1-Pro-260915
- 76.6
Qwen3.8 Max (0902)
- 73.5
Muse Spark 1.3
- 72.6
MiniMax-M3.1-Flash
- 72.1 Grok 4.7
- 70.4 GLM-5.3-Flash
- 69.9
DeepSeek V4.1 Flash 1017
- 69.0 MiMo-V2.6 Pro
- 67.1
Tencent Hy4
- 66.2
Step 5 Preview
- 58.5
MiniCPM-V-4.7-35B-A3B
- 1
Gemini 4 Argon API 89.0
- 2 Claude Opus 5.5 API 86.0
- 3 GPT-6.1 Sol API 82.7
- 4 Kimi K3.1 Pro API 79.9
- 5 Doubao-Seed-2.1-Pro-260915 API 79.5
- 6
Qwen3.8 Max (0902) API 76.6
- 7
Muse Spark 1.3 API 73.5
- 8
MiniMax-M3.1-Flash API 72.6
- 9 Grok 4.7 API 72.1
- 10 GLM-5.3-Flash API 70.4
- 11
DeepSeek V4.1 Flash 1017 API 69.9
- 12 MiMo-V2.6 Pro API 69.0
- 13
Tencent Hy4 API 67.1
- 14
Step 5 Preview API 66.2
- 15
MiniCPM-V-4.7-35B-A3B API 58.5
Source: Official SuperCLUE-VLM leaderboard
- 1
Gemini 4 Argon API 89.0
- 2 Claude Opus 5.5 API 86.0
- 3 GPT-6.1 Sol API 82.7
- 4 Kimi K3.1 Pro API 79.9
- 5
Qwen3.8 Max (0902) API 76.6
- 6
Muse Spark 1.3 API 73.5
- 7
MiniMax-M3.1-Flash API 72.6
- 8 Grok 4.7 API 72.1
- 9 GLM-5.3-Flash API 70.4
- 10
DeepSeek V4.1 Flash 1017 API 69.9
- 11 MiMo-V2.6 Pro API 69.0
- 12
Tencent Hy4 API 67.1
- 13
Step 5 Preview API 66.2
- 14
MiniCPM-V-4.7-35B-A3B API 58.5
Source: Official SuperCLUE-VLM leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 89.0 | API | Sep 2026 | Official leaderboard |
| 2 | Claude Opus 5.5 | 86.0 | API | Sep 2026 | Official leaderboard |
| 3 | GPT-6.1 Sol | 82.7 | API | Sep 2026 | Official leaderboard |
| 4 | Kimi K3.1 Pro | 79.9 | API | Oct 2026 | Official leaderboard |
| 5 | Doubao-Seed-2.1-Pro-260915 | 79.5 | API | Official leaderboard | |
| 6 | | 76.6 | API | Sep 2026 | Official leaderboard |
| 7 | | 73.5 | API | Sep 2026 | Official leaderboard |
| 8 | | 72.6 | API | Oct 2026 | Official leaderboard |
| 9 | Grok 4.7 | 72.1 | API | Sep 2026 | Official leaderboard |
| 10 | GLM-5.3-Flash | 70.4 | API | Aug 2026 | Official leaderboard |
| 11 | | 69.9 | API | Oct 2026 | Official leaderboard |
| 12 | MiMo-V2.6 Pro | 69.0 | API | Sep 2026 | Official leaderboard |
| 13 | | 67.1 | API | Nov 2026 | Official leaderboard |
| 14 | | 66.2 | API | Sep 2026 | Official leaderboard |
| 15 | | 58.5 | API | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 89.0 | API | Sep 2026 | Official leaderboard |
| 2 | Claude Opus 5.5 | 86.0 | API | Sep 2026 | Official leaderboard |
| 3 | GPT-6.1 Sol | 82.7 | API | Sep 2026 | Official leaderboard |
| 4 | Kimi K3.1 Pro | 79.9 | API | Oct 2026 | Official leaderboard |
| 5 | | 76.6 | API | Sep 2026 | Official leaderboard |
| 6 | | 73.5 | API | Sep 2026 | Official leaderboard |
| 7 | | 72.6 | API | Oct 2026 | Official leaderboard |
| 8 | Grok 4.7 | 72.1 | API | Sep 2026 | Official leaderboard |
| 9 | GLM-5.3-Flash | 70.4 | API | Aug 2026 | Official leaderboard |
| 10 | | 69.9 | API | Oct 2026 | Official leaderboard |
| 11 | MiMo-V2.6 Pro | 69.0 | API | Sep 2026 | Official leaderboard |
| 12 | | 67.1 | API | Nov 2026 | Official leaderboard |
| 13 | | 66.2 | API | Sep 2026 | Official leaderboard |
| 14 | | 58.5 | API | Official leaderboard |
Rankings by part
We read 13 parts from the benchmark’s own leaderboard in 3 groups: 基础认知能力, 视觉推理能力 and 视觉应用能力. Each ranks models on one part of the test. Gemini 4 Argon leads 8 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
14 models we track have a score here.
- 1
Gemini 4 Argon 91.2
- 2 Claude Opus 5.5 89.6
- 3 Kimi K3.1 Pro ↑1 87.0
- 4
Qwen3.8 Max (0902) ↑1 84.0
- 5 GPT-6.1 Sol ↓2 83.3
- 6
Muse Spark 1.3 80.3
- 7
MiniMax-M3.1-Flash 76.5
- 8 GLM-5.3-Flash ↑1 75.6
- 9
DeepSeek V4.1 Flash 1017 ↑1 70.2
- 10 Grok 4.7 ↓2 69.3
视觉推理能力
14 models we track have a score here.
- 1
Gemini 4 Argon 90.3
- 2 GPT-6.1 Sol ↑1 89.7
- 3 Claude Opus 5.5 ↓1 83.4
- 4 Kimi K3.1 Pro 80.7
- 5 Grok 4.7 ↑3 80.3
- 6
Muse Spark 1.3 78.8
- 7
MiniMax-M3.1-Flash 78.0
- 8
Qwen3.8 Max (0902) ↓3 77.3
- 9
DeepSeek V4.1 Flash 1017 ↑1 77.2
- 10 MiMo-V2.6 Pro ↑1 76.4
视觉应用能力
14 models we track have a score here.
- 1
Gemini 4 Argon 85.6
- 2 Claude Opus 5.5 85.1
- 3 GPT-6.1 Sol 75.1
- 4 Kimi K3.1 Pro 72.0
- 5
Qwen3.8 Max (0902) 68.6
- 6 Grok 4.7 ↑2 66.6
- 7 MiMo-V2.6 Pro ↑4 64.0
- 8
MiniMax-M3.1-Flash ↓1 63.4
- 9
DeepSeek V4.1 Flash 1017 ↑1 62.3
- 10
Muse Spark 1.3 ↓4 61.4
分数
14 models we track have a score here.
- 1
Gemini 4 Argon 91.2
- 2 Claude Opus 5.5 89.6
- 3 Kimi K3.1 Pro ↑1 87.0
- 4
Qwen3.8 Max (0902) ↑1 84.0
- 5 GPT-6.1 Sol ↓2 83.3
- 6
Muse Spark 1.3 80.3
- 7
MiniMax-M3.1-Flash 76.5
- 8 GLM-5.3-Flash ↑1 75.6
- 9
DeepSeek V4.1 Flash 1017 ↑1 70.2
- 10 Grok 4.7 ↓2 69.3
信息解析
14 models we track have a score here.
- 1
Gemini 4 Argon 99.0
- 2 Kimi K3.1 Pro ↑2 99.0
- 3 Claude Opus 5.5 ↓1 95.8
- 4
Qwen3.8 Max (0902) ↑1 93.0
- 5 GPT-6.1 Sol ↓2 91.7
- 6
Muse Spark 1.3 85.6
- 7 GLM-5.3-Flash ↑2 84.5
- 8
MiniMax-M3.1-Flash ↓1 78.0
- 9
DeepSeek V4.1 Flash 1017 ↑1 73.8
- 10 Grok 4.7 ↓2 71.9
通用识别
14 models we track have a score here.
- 1 Claude Opus 5.5 ↑1 83.3
- 2
Gemini 4 Argon ↓1 83.3
- 3
Qwen3.8 Max (0902) ↑2 75.0
- 4
Muse Spark 1.3 ↑2 75.0
- 5 GPT-6.1 Sol ↓2 75.0
- 6
MiniMax-M3.1-Flash ↑1 75.0
- 7 Kimi K3.1 Pro ↓3 75.0
- 8
Tencent Hy4 ↑4 75.0
- 9 GLM-5.3-Flash 66.7
- 10
Step 5 Preview ↑3 66.7
分数
14 models we track have a score here.
- 1
Gemini 4 Argon 90.3
- 2 GPT-6.1 Sol ↑1 89.7
- 3 Claude Opus 5.5 ↓1 83.4
- 4 Kimi K3.1 Pro 80.7
- 5 Grok 4.7 ↑3 80.3
- 6
Muse Spark 1.3 78.8
- 7
MiniMax-M3.1-Flash 78.0
- 8
Qwen3.8 Max (0902) ↓3 77.3
- 9
DeepSeek V4.1 Flash 1017 ↑1 77.2
- 10 MiMo-V2.6 Pro ↑1 76.4
学科推理
14 models we track have a score here.
- 1 Claude Opus 5.5 ↑1 100.0
- 2
Gemini 4 Argon ↓1 100.0
- 3 GLM-5.3-Flash ↑6 95.8
- 4
Qwen3.8 Max (0902) ↑1 95.8
- 5
Muse Spark 1.3 ↑1 95.8
- 6 Grok 4.7 ↑2 95.8
- 7 MiMo-V2.6 Pro ↑4 95.8
- 8 GPT-6.1 Sol ↓5 95.8
- 9
DeepSeek V4.1 Flash 1017 ↑1 95.8
- 10 Kimi K3.1 Pro ↓6 95.8
应用推理
14 models we track have a score here.
- 1 GPT-6.1 Sol ↑2 83.5
- 2
Gemini 4 Argon ↓1 80.7
- 3 Claude Opus 5.5 ↓1 66.8
- 4 Kimi K3.1 Pro 65.5
- 5 Grok 4.7 ↑3 64.7
- 6
MiniMax-M3.1-Flash ↑1 64.4
- 7
Muse Spark 1.3 ↓1 61.8
- 8
Qwen3.8 Max (0902) ↓3 58.8
- 9
DeepSeek V4.1 Flash 1017 ↑1 58.6
- 10 MiMo-V2.6 Pro ↑1 57.0
分数
14 models we track have a score here.
- 1
Gemini 4 Argon 85.6
- 2 Claude Opus 5.5 85.1
- 3 GPT-6.1 Sol 75.1
- 4 Kimi K3.1 Pro 72.0
- 5
Qwen3.8 Max (0902) 68.6
- 6 Grok 4.7 ↑2 66.6
- 7 MiMo-V2.6 Pro ↑4 64.0
- 8
MiniMax-M3.1-Flash ↓1 63.4
- 9
DeepSeek V4.1 Flash 1017 ↑1 62.3
- 10
Muse Spark 1.3 ↓4 61.4
安全风控
14 models we track have a score here.
- 1 Claude Opus 5.5 ↑1 100.0
- 2
Gemini 4 Argon ↓1 100.0
- 3 Grok 4.7 ↑5 83.3
- 4 MiMo-V2.6 Pro ↑7 83.3
- 5
MiniMax-M3.1-Flash ↑2 83.3
- 6 GPT-6.1 Sol ↓3 75.0
- 7
DeepSeek V4.1 Flash 1017 ↑3 75.0
- 8
Muse Spark 1.3 ↓2 70.8
- 9
Step 5 Preview ↑4 70.8
- 10 GLM-5.3-Flash ↓1 66.7
智能交互
14 models we track have a score here.
- 1 Claude Opus 5.5 ↑1 83.3
- 2 GPT-6.1 Sol ↑1 83.3
- 3
Gemini 4 Argon ↓2 83.3
- 4 Kimi K3.1 Pro 83.3
- 5
Qwen3.8 Max (0902) 77.8
- 6 Grok 4.7 ↑2 66.7
- 7
Tencent Hy4 ↑5 66.7
- 8
MiniMax-M3.1-Flash ↓1 61.1
- 9
Muse Spark 1.3 ↓3 55.6
- 10
DeepSeek V4.1 Flash 1017 55.6
行业应用
14 models we track have a score here.
- 1
Gemini 4 Argon 73.3
- 2 Claude Opus 5.5 71.8
- 3
Qwen3.8 Max (0902) ↑2 69.6
- 4 GLM-5.3-Flash ↑5 66.8
- 5 GPT-6.1 Sol ↓2 66.8
- 6 Kimi K3.1 Pro ↓2 65.9
- 7
MiniCPM-V-4.7-35B-A3B ↑7 59.0
- 8 MiMo-V2.6 Pro ↑3 58.5
- 9
Muse Spark 1.3 ↓3 57.8
- 10
Step 5 Preview ↑3 56.3
4 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-VLM 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-VLM 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
9 of 10 checks pass, 1 warning. 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 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (15 entries).
- Pass Models scored 14 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from November 2026, for Tencent Hy4.
- Pass Frontier models 3 of the top 10 have a score, led by Claude Opus 5.5 (#5).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on superclueai.com: 14 rows for models we track and 1 other entry 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.