Skip to main content

Artificial Analysis MMMU-Pro (AA-MMMU-Pro)

A display-only Artificial Analysis MMMU-Pro score.

Benchmark score on AA-MMMU-Pro — May 21, 2026

BenchLM mirrors the published score view for AA-MMMU-Pro. Gemini 3.5 Flash leads the public snapshot at 84.3% , followed by Gemini 3.1 Pro (82.4%) and Muse Spark (80.5%). BenchLM does not use these results to rank models overall.

69 modelsMultimodal & GroundedCurrentDisplay onlyUpdated May 21, 2026

The published AA-MMMU-Pro snapshot is tightly clustered at the top: Gemini 3.5 Flash sits at 84.3%, while the third row is only 3.8 points behind. The broader top-10 spread is 5.9 points, so many of the published scores sit in a relatively narrow band.

69 models have been evaluated on AA-MMMU-Pro. The benchmark falls in the Multimodal & Grounded category. This category carries a 12% weight in BenchLM.ai's overall scoring system. AA-MMMU-Pro is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About AA-MMMU-Pro

Year

2026

Tasks

Multimodal academic reasoning

Format

Image + text question answering

Difficulty

Frontier multimodal

BenchLM stores the Artificial Analysis MMMU-Pro result separately from the weighted MMMU-Pro lane so AA refreshes remain display-only.

BenchLM freshness & provenance

Version

AA-MMMU-Pro 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Benchmark score table (69 models)

1
84.3%
2
82.4%
3
80.5%
4
80.2%
5
79.9%
6
79.4%
7
78.8%
8
78.6%
9
78.5%
10
78.4%
11
78.1%
12
78.0%
13
77.3%
14
76.4%
15
76.3%
16
75.5%
17
75.5%
18
75.4%
19
75.4%
20
75.4%
21
75.0%
22
75.0%
23
75.0%
24
74.9%
25
74.6%
26
74.3%
27
74.2%
28
74.0%
29
73.4%
30
73.3%
31
72.8%
32
72.7%
33
72.5%
34
72.5%
35
72.5%
36
71.2%
37
70.6%
38
70.1%
39
69.9%
40
69.2%
41
68.8%
42
67.9%
43
65.5%
44
65.4%
45
64.9%
46
64.9%
48
63.2%
49
62.4%
50
62.1%
51
61.8%
52
61.2%
53
58.7%
54
56.8%
55
56.8%
56
55.7%
57
55.0%
59
53.0%
60
52.9%
61
52.7%
62
51.4%
63
48.4%
64
48.0%
65
44.6%
66
44.3%
67
41.5%
68
40.1%
69
30.8%

FAQ

What does AA-MMMU-Pro measure?

A display-only Artificial Analysis MMMU-Pro score.

Which model scores highest on AA-MMMU-Pro?

Gemini 3.5 Flash by Google currently leads with a score of 84.3% on AA-MMMU-Pro.

How many models are evaluated on AA-MMMU-Pro?

69 AI models have been evaluated on AA-MMMU-Pro on BenchLM.

Last updated: May 21, 2026 · BenchLM version AA-MMMU-Pro 2026

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.