Neura Intelligence Index
AI Model Benchmarks
MMMU-Pro — AI Model Leaderboard & Results | Neura Market
Neura Market
Marketplace
Directories
Resources
Sell
Search...
⌘
K
Sign In
Get Started
Back to Leaderboard
MMMU-Pro
Harder version of MMMU with augmented candidate options and vision-only input.
multimodal
0-100 percent
Model Rankings (73)
#
Model
Score
Provider
Source
1
GPT-6.1 Sol
🇺🇸
86.0
OpenAI
verified
2
Gemini 3.5 Flash
🇺🇸
83.6
Google
verified
3
GPT-5.5
🇺🇸
83.2
OpenAI
verified
4
GPT-5.6 Sol
🇺🇸
83
OpenAI
verified
5
B
Seed 2.1 Pro
🇨🇳
82.7
ByteDance
verified
6
Q
Qwen3.8 Max
🇨🇳
82.3
Alibaba Cloud / Qwen Team
verified
7
B
Seed 2.1 Turbo
🇨🇳
82.2
ByteDance
verified
8
M
Kimi K3
🇨🇳
81.6
Moonshot AI
verified
9
GPT-5.4
🇺🇸
81.2
OpenAI
verified
10
Gemini 3 Flash
🇺🇸
81.2
Google
verified
11
Gemini 3 Pro
🇺🇸
81
Google
verified
12
GPT-5.6 Terra
🇺🇸
80.7
OpenAI
verified
13
Gemini 3.1 Pro
🇺🇸
80.5
Google
verified
14
M
Muse Spark
🇺🇸
80.4
Meta
verified
15
M
Kimi K2.6
🇨🇳
80.1
Moonshot AI
verified
16
GPT-5.2
🇺🇸
79.5
OpenAI
verified
17
Q
Qwen3.7-Plus
🇨🇳
79
Alibaba Cloud / Qwen Team
verified
18
Q
Qwen3.6 Plus
🇨🇳
78.8
Alibaba Cloud / Qwen Team
verified
19
M
Kimi K2.5
🇨🇳
78.5
Moonshot AI
verified
20
GPT-5
🇺🇸
78.4
OpenAI
verified
21
GPT-5.6 Luna
🇺🇸
78.4
OpenAI
verified
22
MiniMax M3
🇨🇳
78.1
MiniMax
verified
23
X
MiMo-V2.5
🇨🇳
77.9
Xiaomi
verified
24
Claude Opus 4.6
🇺🇸
77.3
Anthropic
verified
25
Gemma 4 31B
🇺🇸
76.9
Google
verified
26
Q
Qwen3.5-122B-A10B
🇨🇳
76.9
Alibaba Cloud / Qwen Team
verified
27
Gemini 3.1 Flash-Lite
🇺🇸
76.8
Google
verified
28
GPT-5.4 mini
🇺🇸
76.6
OpenAI
verified
29
o3
🇺🇸
76.4
OpenAI
verified
30
GPT-5.5 Instant
🇺🇸
76
OpenAI
verified
31
Q
Qwen3.6-27B
🇨🇳
75.8
Alibaba Cloud / Qwen Team
verified
32
Claude Sonnet 4.6
🇺🇸
75.6
Anthropic
verified
33
Q
Qwen3.6-35B-A3B
🇨🇳
75.3
Alibaba Cloud / Qwen Team
verified
34
Q
Qwen3.5-35B-A3B
🇨🇳
75.1
Alibaba Cloud / Qwen Team
verified
35
Q
Qwen3.5-27B
🇨🇳
75
Alibaba Cloud / Qwen Team
verified
36
T
Inkling-Small
🇺🇸
74
Thinking Machines Lab
verified
37
M
Muse Glimmer-30B
🇺🇸
74
Meta
verified
38
Gemma 4 26B-A4B
🇺🇸
73.8
Google
verified
39
T
Inkling
🇺🇸
73.5
Thinking Machines Lab
verified
40
B
Seed 1.8
🇨🇳
73.2
ByteDance
verified
41
B
Seed 2.0 Mini
🇨🇳
71.4
ByteDance
verified
42
Q
Qwen3 VL 235B A22B Thinking
🇨🇳
69.3
Alibaba Cloud / Qwen Team
verified
43
Gemma 4 12B
🇺🇸
69.1
Google
verified
44
L
EXAONE 4.5 33B
🇰🇷
68.6
LG AI Research
verified
45
Q
Qwen3 VL 32B Thinking
🇨🇳
68.1
Alibaba Cloud / Qwen Team
verified
46
Q
Qwen3 VL 235B A22B Instruct
🇨🇳
68.1
Alibaba Cloud / Qwen Team
verified
47
GPT-5.4 nano
🇺🇸
66.1
OpenAI
verified
48
Q
Qwen3 VL 32B Instruct
🇨🇳
65.3
Alibaba Cloud / Qwen Team
verified
49
Nova 2 Pro
🇺🇸
63.5
Amazon
verified
50
Q
Qwen3 VL 30B A3B Thinking
🇨🇳
63
Alibaba Cloud / Qwen Team
verified
51
Command A+
🇨🇦
63
Cohere
verified
52
Nova 2 Lite
🇺🇸
61.8
Amazon
verified
53
Nova 2 Omni
🇺🇸
61.4
Amazon
verified
54
Q
Qwen3 VL 8B Thinking
🇨🇳
60.4
Alibaba Cloud / Qwen Team
verified
55
Q
Qwen3 VL 30B A3B Instruct
🇨🇳
60.4
Alibaba Cloud / Qwen Team
verified
56
Mistral Small 4
🇫🇷
60
Mistral AI
verified
57
GPT-4o
🇺🇸
59.9
OpenAI
verified
58
M
Llama 4 Maverick
🇺🇸
59.6
Meta
verified
59
Q
Qwen3 VL 4B Thinking
🇨🇳
57
Alibaba Cloud / Qwen Team
verified
60
Q
Qwen3 VL 8B Instruct
🇨🇳
55.9
Alibaba Cloud / Qwen Team
verified
61
DiffusionGemma 26B-A4B
🇺🇸
54.3
Google
verified
62
Q
Qwen3 VL 4B Instruct
🇨🇳
53.2
Alibaba Cloud / Qwen Team
verified
63
Gemma 4 E4B
🇺🇸
52.6
Google
verified
64
Q
Qwen2.5 VL 72B Instruct
🇨🇳
51.1
Alibaba Cloud / Qwen Team
verified
65
Q
Qwen2.5 VL 32B Instruct
🇨🇳
49.5
Alibaba Cloud / Qwen Team
verified
66
Q
Qwen2-VL-72B-Instruct
🇨🇳
46.2
Alibaba Cloud / Qwen Team
verified
67
M
Llama 3.2 90B Instruct
🇺🇸
45.2
Meta
verified
68
Gemma 4 E2B
🇺🇸
44.2
Google
verified
69
Phi-4-multimodal-instruct
🇺🇸
38.5
Microsoft
verified
70
Q
Qwen2.5 VL 7B Instruct
🇨🇳
38.3
Alibaba Cloud / Qwen Team
verified
71
Q
Qwen2.5-Omni-7B
🇨🇳
36.6
Alibaba Cloud / Qwen Team
verified
72
M
Llama 3.2 11B Instruct
🇺🇸
33
Meta
verified
73
L
LFM2.5-VL-3B
🇺🇸
30.5
Liquid AI
verified
Nova 2 Pro