Qwen3-VL-235B-A22B
Qwen Team (Alibaba Cloud)
Parameters
—
Architecture
—
Released
—
License
—
About
No detailed description available for this model.
Benchmark Scores
| Benchmark | Score | Date | Standing |
|---|---|---|---|
|
MMMU-Pro
vision_language
|
74.35%
|
01.02.2026 |
#24/35
better than 29%
|
|
MMMU
vision_language
|
90.39%
|
01.02.2026 |
#8/19
better than 56%
|
|
MathVision
vision_language
|
55.21%
|
01.02.2026 |
#16/27
better than 35%
|
|
DynaMath
vision_language
|
44.94%
|
01.02.2026 |
#7/14
better than 38%
|
|
ZEROBench_sub
vision_language
|
23.53%
|
01.02.2026 |
#5/11
better than 50%
|
|
VlmsAreBlind
vision_language
|
17.45%
|
01.02.2026 |
#9/11
better than 10%
|
|
RealWorldQA
vision_language
|
83.26%
|
01.02.2026 |
#10/23
better than 55%
|
|
MMStar
vision_language
|
81.87%
|
01.02.2026 |
#7/16
better than 53%
|
|
HallusionBench
vision_language
|
55.74%
|
01.02.2026 |
#7/13
better than 42%
|
|
OmniDocBench 1.5
document_understanding
|
92.23%
|
01.02.2026 |
#16/26
better than 36%
|
|
CharXiv (RQ)
document_understanding
|
0.40%
|
01.02.2026 |
#31/34
better than 6%
|
|
MMLongBench-Doc
document_understanding
|
59.60%
|
01.02.2026 |
#4/7
better than 33%
|
|
CountBench
spatial_intelligence
|
47.44%
|
01.02.2026 |
#9/13
better than 25%
|
|
ODInW13
spatial_intelligence
|
21.65%
|
01.02.2026 |
#3/6
better than 40%
|
|
RefSpatialBench
spatial_intelligence
|
99.85%
|
01.02.2026 |
#2/12
better than 82%
|
|
LingoQA
spatial_intelligence
|
78.03%
|
01.02.2026 |
#5/8
better than 29%
|
|
Hypersim
spatial_intelligence
|
11.00
|
01.02.2026 |
#5/6
better than 0%
|
|
SUNRGBD
spatial_intelligence
|
53.57%
|
01.02.2026 |
#3/5
better than 25%
|
|
Nuscene
spatial_intelligence
|
72.73%
|
01.02.2026 |
#4/6
better than 20%
|
|
ScreenSpot Pro
general_agent
|
64.66%
|
01.02.2026 |
#7/11
better than 30%
|
|
OSWorld-Verified
general_agent
|
5.08%
|
01.02.2026 |
#23/25
better than 4%
|
|
AndroidWorld
general_agent
|
19.69%
|
01.02.2026 |
#9/13
better than 25%
|
|
TIR-Bench
vision_language
|
14.77%
|
01.02.2026 |
#5/8
better than 29%
|
|
V-Star
vision_language
|
68.59%
|
01.02.2026 |
#13/20
better than 32%
|
|
SLAKE
vision_language
|
54.70
|
01.02.2026 |
#7/8
better than 0%
|
|
PMC-VQA
vision_language
|
18.15%
|
01.02.2026 |
#6/8
better than 14%
|
|
MedXpertQA-MM
vision_language
|
55.02%
|
01.02.2026 |
#8/13
better than 33%
|
|
AI2D_TEST
document_understanding
|
86.38%
|
01.02.2026 |
#6/15
better than 57%
|
|
CC-OCR
document_understanding
|
96.40%
|
01.02.2026 |
#4/14
better than 69%
|
|
ZEROBench
vision_language
|
2.08%
|
01.02.2026 |
#10/14
better than 15%
|
|
LVBench
video_understanding
|
63.28%
|
01.02.2026 |
#9/12
better than 18%
|
|
RefCOCO (avg)
spatial_intelligence
|
92.61%
|
01.02.2026 |
#5/11
better than 50%
|
|
MMBench EN-DEV v1.1
vision_language
|
83.79%
|
01.02.2026 |
#7/15
better than 50%
|
|
MMVU
video_understanding
|
62.33%
|
01.02.2026 |
#5/10
better than 44%
|
|
VideoMME (w sub.)
video_understanding
|
70.48%
|
01.02.2026 |
#11/17
better than 31%
|
|
SimpleVQA
vision_language
|
67.02%
|
01.02.2026 |
#5/16
better than 67%
|
|
MLVU
video_understanding
|
78.12%
|
01.02.2026 |
#7/13
better than 42%
|
|
ERQA
spatial_intelligence
|
41.42%
|
01.02.2026 |
#13/21
better than 35%
|
|
OCRBench
document_understanding
|
1.49%
|
01.02.2026 |
#7/12
better than 45%
|
|
VideoMMMU
video_understanding
|
79.37%
|
01.02.2026 |
#14/19
better than 22%
|
|
MathVista (mini)
vision_language
|
92.09%
|
01.02.2026 |
#6/14
better than 54%
|
|
VideoMME (w/o sub.)
video_understanding
|
81.30%
|
01.02.2026 |
#5/11
better than 50%
|
|
EmbSpatialBench
spatial_intelligence
|
97.86%
|
01.02.2026 |
#3/12
better than 64%
|
|
MVBench
video_understanding
|
87.74%
|
01.02.2026 |
#4/12
better than 64%
|
|
BabyVision
vision_language
|
11.78%
|
01.02.2026 |
#18/24
better than 22%
|
What is a good MMMU-Pro score? What is a good MMMU score? What is a good MathVision score?
No comments yet
Be the first to share your thoughts!