Benchmark Almanac

SuperCLUE-VLM

Gemini 4 Argon 89.0 leads since September 2026
Not in model cards

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
In and out
Text, Images → Text
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
15
Entries on its own leaderboard, 14 models we track

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.

  1. 1 Gemini 4 Argon API 89.0
  2. 2 Claude Opus 5.5 API 86.0
  3. 3 GPT-6.1 Sol API 82.7
  4. 4 Kimi K3.1 Pro API 79.9
  5. 5 Doubao-Seed-2.1-Pro-260915 API 79.5
  6. 6 Qwen3.8 Max (0902) API 76.6
  7. 7 Muse Spark 1.3 API 73.5
  8. 8 MiniMax-M3.1-Flash API 72.6
  9. 9 Grok 4.7 API 72.1
  10. 10 GLM-5.3-Flash API 70.4
  11. 11 DeepSeek V4.1 Flash 1017 API 69.9
  12. 12 MiMo-V2.6 Pro API 69.0
  13. 13 Tencent Hy4 API 67.1
  14. 14 Step 5 Preview API 66.2
  15. 15 MiniCPM-V-4.7-35B-A3B API 58.5

Source: Official SuperCLUE-VLM leaderboard

#EntryScoreSettingDateSource
1 Gemini 4 Argon 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 Qwen3.8 Max (0902) 76.6 API Sep 2026 Official leaderboard
7 Muse Spark 1.3 73.5 API Sep 2026 Official leaderboard
8 MiniMax-M3.1-Flash 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 DeepSeek V4.1 Flash 1017 69.9 API Oct 2026 Official leaderboard
12 MiMo-V2.6 Pro 69.0 API Sep 2026 Official leaderboard
13 Tencent Hy4 67.1 API Nov 2026 Official leaderboard
14 Step 5 Preview 66.2 API Sep 2026 Official leaderboard
15 MiniCPM-V-4.7-35B-A3B 58.5 API Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 4 Argon 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 Qwen3.8 Max (0902) 76.6 API Sep 2026 Official leaderboard
6 Muse Spark 1.3 73.5 API Sep 2026 Official leaderboard
7 MiniMax-M3.1-Flash 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 DeepSeek V4.1 Flash 1017 69.9 API Oct 2026 Official leaderboard
11 MiMo-V2.6 Pro 69.0 API Sep 2026 Official leaderboard
12 Tencent Hy4 67.1 API Nov 2026 Official leaderboard
13 Step 5 Preview 66.2 API Sep 2026 Official leaderboard
14 MiniCPM-V-4.7-35B-A3B 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. 1 Gemini 4 Argon 91.2
  2. 2 Claude Opus 5.5 89.6
  3. 3 Kimi K3.1 Pro ↑1 87.0
  4. 4 Qwen3.8 Max (0902) ↑1 84.0
  5. 5 GPT-6.1 Sol ↓2 83.3
  6. 6 Muse Spark 1.3 80.3
  7. 7 MiniMax-M3.1-Flash 76.5
  8. 8 GLM-5.3-Flash ↑1 75.6
  9. 9 DeepSeek V4.1 Flash 1017 ↑1 70.2
  10. 10 Grok 4.7 ↓2 69.3

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.

Z.ai Qwen Anthropic Google DeepMind
Own leaderboard 4 leaders

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.

Plot with other benchmarks
On the benchmark’s own leaderboard
65.0 70.0 75.0 80.0 85.0 90.0 2027 65.0 70.0 75.0 80.0 85.0 90.0 2027

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

All 636 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.

How we check