Neura Intelligence Index
AI Model Benchmarks
MMMU — AI Model Leaderboard & Results | Neura Market
Neura Market
Marketplace
Directories
Resources
Sell
Search...
⌘
K
Sign In
Get Started
Back to Leaderboard
MMMU
Massive Multi-discipline Multimodal Understanding — college-level multimodal questions.
multimodal
0-100 percent
Paper / Website
Model Rankings (70)
#
Model
Score
Provider
Source
1
Q
Qwen3.6 Plus
🇨🇳
86
Alibaba Cloud / Qwen Team
verified
2
GPT-5.1
🇺🇸
85.4
OpenAI
verified
3
GPT-5.1 Instant
🇺🇸
85.4
OpenAI
verified
4
GPT-5.1 Thinking
🇺🇸
85.4
OpenAI
verified
5
GPT-5
🇺🇸
84.2
OpenAI
verified
6
Q
Qwen3.5-122B-A10B
🇨🇳
83.9
Alibaba Cloud / Qwen Team
verified
7
B
Seed 1.8
🇨🇳
83.4
ByteDance
verified
8
o3
🇺🇸
82.9
OpenAI
verified
9
Q
Qwen3.6-27B
🇨🇳
82.9
Alibaba Cloud / Qwen Team
verified
10
Q
Qwen3.5-27B
🇨🇳
82.3
Alibaba Cloud / Qwen Team
verified
11
Gemini 2.5 Pro Preview 06-05
🇺🇸
82
Google
verified
12
Q
Qwen3.6-35B-A3B
🇨🇳
81.7
Alibaba Cloud / Qwen Team
verified
13
o4-mini
🇺🇸
81.6
OpenAI
verified
14
Q
Qwen3.5-35B-A3B
🇨🇳
81.4
Alibaba Cloud / Qwen Team
verified
15
B
Seed 2.0 Mini
🇨🇳
79.7
ByteDance
verified
16
Gemini 2.5 Flash
🇺🇸
79.7
Google
verified
17
Gemini 2.5 Pro
🇺🇸
79.6
Google
verified
18
L
EXAONE 4.5 33B
🇰🇷
78.7
LG AI Research
verified
19
S
Step3-VL-10B
🇨🇳
78.1
StepFun
verified
20
X
Grok-3
🇺🇸
78
xAI
verified
21
o1
🇺🇸
77.6
OpenAI
verified
22
Gemini 2.0 Flash Thinking
🇺🇸
75.4
Google
verified
23
GPT-4.5
🇺🇸
75.2
OpenAI
verified
24
Command A+
🇨🇦
75.1
Cohere
verified
25
Claude 3.7 Sonnet
🇺🇸
75
Anthropic
verified
26
GPT-4.1
🇺🇸
74.8
OpenAI
verified
27
Claude Sonnet 4
🇺🇸
74.4
Anthropic
verified
28
Claude Opus 4
🇺🇸
74.2
Anthropic
aggregated
29
M
Llama 4 Maverick
🇺🇸
73.4
Meta
verified
30
Gemini 2.5 Flash-Lite
🇺🇸
72.9
Google
verified
31
GPT-4.1 mini
🇺🇸
72.7
OpenAI
verified
32
Claude Sonnet 4
🇺🇸
72.5
Anthropic
aggregated
33
GPT-4o
🇺🇸
72.2
OpenAI
verified
34
Gemini 2.0 Flash
🇺🇸
70.7
Google
verified
35
Q
QvQ-72B-Preview
🇨🇳
70.3
Alibaba Cloud / Qwen Team
verified
36
Q
Qwen2.5 VL 72B Instruct
🇨🇳
70.2
Alibaba Cloud / Qwen Team
verified
37
M
Kimi-k1.5
🇨🇳
70
Moonshot AI
verified
38
Q
Qwen2.5 VL 32B Instruct
🇨🇳
70
Alibaba Cloud / Qwen Team
verified
39
M
Llama 4 Scout
🇺🇸
69.4
Meta
verified
40
GPT-4o
🇺🇸
69.1
OpenAI
aggregated
41
Claude 3.5 Sonnet
🇺🇸
68.3
Anthropic
aggregated
42
Claude 3.5 Sonnet
🇺🇸
68.3
Anthropic
verified
43
Gemini 2.0 Flash-Lite
🇺🇸
68
Google
verified
44
X
Grok-2
🇺🇸
66.1
xAI
verified
45
Gemini 1.5 Pro
🇺🇸
65.9
Google
verified
46
Pixtral Large
🇫🇷
64
Mistral AI
verified
47
X
Grok-2 mini
🇺🇸
63.2
xAI
verified
48
Mistral Small 3.2 24B Instruct
🇫🇷
62.5
Mistral AI
verified
49
Gemini 1.5 Flash
🇺🇸
62.3
Google
verified
50
Nova Pro
🇺🇸
61.7
Amazon
verified
51
M
Llama 3.2 90B Instruct
🇺🇸
60.3
Meta
verified
52
GPT-4o mini
🇺🇸
59.4
OpenAI
verified
53
Mistral Small 3.1 24B Instruct
🇫🇷
59.3
Mistral AI
verified
54
Mistral Small 3.1 24B Base
🇫🇷
59.3
Mistral AI
verified
55
Q
Qwen2.5-Omni-7B
🇨🇳
59.2
Alibaba Cloud / Qwen Team
verified
56
Q
Qwen2.5 VL 7B Instruct
🇨🇳
58.6
Alibaba Cloud / Qwen Team
verified
57
Nova Lite
🇺🇸
56.2
Amazon
verified
58
GPT-4.1 nano
🇺🇸
55.4
OpenAI
verified
59
Phi-4-multimodal-instruct
🇺🇸
55.1
Microsoft
verified
60
Gemini 1.5 Flash 8B
🇺🇸
53.7
Google
verified
61
X
Grok-1.5V
🇺🇸
53.6
xAI
verified
62
X
Grok-1.5
🇺🇸
53.6
xAI
verified
63
Pixtral-12B
🇫🇷
52.5
Mistral AI
verified
64
DeepSeek VL2
🇨🇳
51.1
DeepSeek
verified
65
M
Llama 3.2 11B Instruct
🇺🇸
50.7
Meta
verified
66
DeepSeek VL2 Small
🇨🇳
48
DeepSeek
verified
67
Gemini 1.0 Pro
🇺🇸
47.9
Google
verified
68
Phi-3.5-vision-instruct
🇺🇸
43
Microsoft
verified
69
DeepSeek VL2 Tiny
🇨🇳
40.7
DeepSeek
verified
70
GPT-3.5 Turbo
🇺🇸
0
OpenAI
verified
Nova Pro