Benchmark Almanac

SuperCLUE-V

ChatGPT-4o-latest 77.8 tops its leaderboard GPT-4o May 2024 75.1 leads the models we track
Not in model cards

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
In and out
Text, Images → Text
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
17
Entries on its own leaderboard, 6 models we track

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:

  1. 1 ChatGPT-4o-latest API 77.8
  2. 2 GPT-4o May 2024, API 75.1
  3. 3 Step-1V-8k API 74.0
  4. 4 hunyuan-vision API 73.6
  5. 5 SenseChat-Vision 5.5 API 73.6
  6. 6 Claude 3.5 Sonnet POE 73.3
  7. 7 InternVL2-40B 模型 72.5
  8. 8 Gemini 1.5 Pro Sep 2024, POE 70.7
  9. 9 ERNIE-4-Turbo 网页 69.3
  10. 10 Qwen2-VL-72B API 68.4
  11. 11 GLM-4V-Plus API 67.5
  12. 12 MiniCPM-V-2_6 模型 66.9
  13. 13 GPT-4-Turbo-0409 API 65.9
  14. 14 海螺AI 网页 65.0
  15. 15 Yi-Vision API 64.4
  16. 16 DeekSeek-VL-7b-chat 模型 55.8
  17. 17 Phi-3.5-vision-instruct 模型 45.0

Source: Official SuperCLUE-V leaderboard

#EntryScoreSettingReleasedRun onSource
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 InternVL2-40B 72.5 模型 Jul 2024 Oct 2024 Official leaderboard
8 Gemini 1.5 Pro Sep 2024 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
#ModelScoreSettingReleasedRun onSource
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 InternVL2-40B 72.5 模型 Jul 2024 Oct 2024 Official leaderboard
4 Gemini 1.5 Pro Sep 2024 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. 1 Gemini 1.5 Pro Sep 2024 ↑3 72.0
  2. 2 Claude 3.5 Sonnet 71.7
  3. 3 InternVL2-40B 71.1
  4. 4 GPT-4o May 2024 ↓3 70.8
  5. 5 MiniCPM-V-2_6 66.0
  6. 6 Phi-3.5-vision-instruct 47.1

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Own leaderboard Not tested since Sep 2024
GPT-4o 75.1

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.

Plot with other benchmarks
On the benchmark’s own leaderboard
40.0 50.0 60.0 70.0 80.0 2024 40.0 50.0 60.0 70.0 80.0 2024

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

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

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.

How we check