Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multi-discipline Reasoning on MMMU

69.1Accuracy

GPT-4o

20.53233.14145.7558.359Dec 5, 2024Mar 9, 2025Jun 12, 2025Sep 14, 2025Dec 18, 2025Mar 22, 2026Jun 25, 2026
Updated 29d ago

Evaluation Results

MethodLinks
2026.03
69.1
2026.03
65.6
2026.06
62.79
2026.06
60.12
2026.06
60.04
2026.06
59.92
2026.06
59.85
2026.06
59.47
2026.06
59.33
2026.06
59.18
2026.06
58.8
2026.03
56
2026.01
55.44
2026.06
55.3
2026.06
53.8
2026.01
53.67
2026.06
52.89
2026.06
52.8
2026.06
52.69
2026.06
52.61
2026.03
52.1
2026.03
52
2026.06
51.83
2026.06
51.6
2026.06
51.56
2026.03
51.2
2026.06
50.6
2026.06
50.43
2026.06
50.12
2026.06
49.98
2026.01
49.33
2026.06
48.89
2026.03
48.8
2026.01
48.68
2026.06
48.6
2026.06
46.27
2026.06
46.2
2026.06
46.13
2026.06
46.02
2026.06
45.42
2026.06
45.41
2026.06
45.17
2026.06
43.8
2026.06
43.2
2026.06
41.8
2026.06
41
2026.06
40.67
2026.06
39.58
2026.06
39.5
2026.06
39.27
2026.06
39.27
2026.06
39.11
2026.06
39.08
2026.06
38.92
2026.06
38.2
2026.03
37.2
2026.03
37
2026.02
36.8
2024.12
36.4
2024.12
36.4
2024.12
36.4
2024.12
36.4
2026.03
36.33
2026.03
36.1
2026.03
36.1
2026.03
36.1
2026.02
36.1
2024.12
36.1
2026.03
36
2026.01
35.89
2026.03
35.89
2026.03
35.6
2026.06
35.6
2024.12
35.4
2026.02
35.3
2024.12
35.3
2026.03
35.22
2026.03
34.8
2026.01
34.67
2026.06
31.6
2026.06
30.5
2026.06
27.4
2026.06
22.4