1 | gemini-2.5-pro-exp-03-25 | 2025-03-31 | | 89.67 | 86 | 90 | 90 | 79.67 | 95 | 89.11 | 100 | 96.67 | 93.33 | 70 |
2 | gemini-2.5-flash-preview-04-17 | 2025-04-30 | | 89.53 | 85.83 | 100 | 85 | 70.67 | 85 | 92.67 | 98.67 | 95.67 | 96.67 | 90 |
3 | gemini-2.5-pro-preview-05-06 | 2025-05-09 | | 88.98 | 84.67 | 90 | 90 | 77.67 | 95 | 89.33 | 100 | 96.67 | 91.33 | 70 |
4 | o3-2025-04-16 | 2025-04-17 | | 88.29 | 84.83 | 80 | 90 | 78 | 95 | 96.22 | 90 | 94 | 86.67 | 80 |
5 | o1-2024-12-17 | 2025-03-31 | | 88.25 | 83.33 | 100 | 100 | 86.67 | 95 | 92.67 | 90 | 86.67 | 83.33 | 80 |
6 | o4-mini-2025-04-16 | 2025-04-17 | | 87.85 | 84.33 | 90 | 70 | 82 | 95 | 84 | 100 | 95.33 | 90 | 80 |
7 | gemini-2.5-flash-preview-05-20 | 2025-05-21 | | 86.76 | 78 | 90 | 90 | 73.33 | 85 | 92 | 100 | 96.67 | 88 | 80 |
8 | gpt-4.1-mini-2025-04-14 | 2025-04-17 | | 85.82 | 82.5 | 90 | 60 | 79 | 90 | 89.56 | 93.33 | 85 | 90 | 90 |
9 | gpt-4.1-2025-04-14 | 2025-04-17 | | 85.71 | 88.33 | 90 | 85 | 83.33 | 95 | 91.56 | 78 | 88.67 | 73.33 | 80 |
10 | chatgpt-4o-latest (2025-01-29) | 2025-02-14 | | 85.35 | 80.67 | 90 | 80 | 80 | 95 | 90.44 | 86.67 | 88.67 | 83.33 | 80 |
11 | gpt-4.5-preview-2025-02-27 | 2025-02-28 | | 85.31 | 85.5 | 80 | 80 | 76.67 | 95 | 93.56 | 90.67 | 93.33 | 70 | 70 |
12 | gpt-4o-2024-11-20 | 2024-12-05 | | 81.96 | 78.33 | 90 | 85 | 80 | 91.5 | 85.56 | 86.67 | 82.33 | 74.67 | 70 |
13 | claude-3-5-sonnet-20241022 | 2024-12-05 | | 80.47 | 81.83 | 90 | 80 | 66 | 76.5 | 88.89 | 78 | 73.67 | 88.67 | 80 |
14 | | 2025-02-05 | 73.4 | 80.11 | 81.83 | 90 | 45 | 63.67 | 95 | 85.33 | 83.33 | 84 | 76.67 | 80 |
15 | | 2025-04-11 | 108.6 | 79.93 | 84.33 | 70 | 40 | 61.67 | 88.5 | 83.56 | 82.67 | 85.33 | 83.33 | 90 |
16 | gemini-2.0-flash-001 | 2025-02-12 | | 79.09 | 73.5 | 80 | 70 | 65.33 | 93.5 | 72.67 | 90 | 96.67 | 88 | 50 |
17 | gemini-2.0-flash-exp | 2024-12-12 | | 78.87 | 73.83 | 80 | 70 | 56.67 | 90 | 82.67 | 93.33 | 90 | 84.67 | 50 |
18 | gpt-4o-2024-08-06 | 2024-12-05 | | 77.6 | 77.5 | 80 | 90 | 64.67 | 80 | 87.56 | 77 | 82 | 68 | 70 |
19 | gemini-2.0-pro-exp-02-05 | 2025-02-12 | | 77.6 | 80 | 80 | 90 | 58 | 85 | 87.11 | 86 | 78.67 | 68 | 50 |
20 | gemini-1.5-pro-002 | 2024-12-05 | | 77.24 | 71.33 | 90 | 60 | 69.33 | 62.5 | 83.33 | 94.67 | 80 | 84.67 | 60 |
21 | | 2025-04-22 | 401.6 | 76.95 | 79.17 | 70 | 20 | 74.33 | 78 | 76.44 | 86 | 80 | 83.33 | 80 |
22 | gemini-2.0-flash-lite-001 | 2025-03-28 | | 76.07 | 71 | 90 | 70 | 54.67 | 88 | 79.11 | 90 | 90 | 66.67 | 70 |
23 | | 2024-12-05 | 73.4 | 74.76 | 86.67 | 80 | 45 | 62.67 | 75 | 83.11 | 64 | 84.33 | 61.33 | 70 |
24 | | 2025-03-25 | 33.5 | 74.44 | 77 | 65 | 60 | 65.67 | 70 | 82.44 | 70.33 | 80.33 | 71.33 | 86 |
25 | gemini-1.5-flash-002 | 2024-12-05 | | 73.45 | 72.83 | 90 | 50 | 68 | 72.5 | 78.22 | 89.33 | 83.33 | 61.33 | 40 |
26 | | 2025-04-15 | 78.4 | 70.25 | 81.5 | 70 | 35 | 58 | 80 | 82.67 | 58.67 | 65.67 | 59.67 | 80 |
27 | | 2025-02-12 | 8.9 | 69.53 | 77.83 | 65 | 30 | 70.67 | 70 | 76.22 | 53.67 | 74 | 64 | 80 |
28 | | 2025-04-25 | 38.4 | 68.98 | 75.5 | 55 | 30 | 70.67 | 70 | 82.44 | 71.67 | 55 | 56.67 | 86 |
29 | | 2025-04-25 | 15.1 | 68.47 | 77.83 | 65 | 25 | 69.33 | 70 | 77.78 | 60.33 | 53.67 | 73.33 | 66 |
30 | gpt-4o-mini-2024-07-18 | 2024-12-05 | | 68.29 | 71.33 | 80 | 35 | 66.33 | 100 | 77.78 | 63 | 47.67 | 61.33 | 70 |
31 | | 2024-12-09 | 88.6 | 67.93 | 75 | 75 | 40 | 62.67 | 80 | 76 | 56 | 55 | 68 | 76 |
32 | | 2025-02-04 | 8.3 | 67.75 | 78.33 | 50 | 25 | 55.33 | 85 | 71.56 | 74.67 | 61.67 | 58.67 | 75 |
33 | | 2025-03-13 | 27.4 | 67.56 | 66.33 | 90 | 40 | 68 | 85 | 83.78 | 47.33 | 55.67 | 73.33 | 50 |
34 | | 2024-12-09 | 78.4 | 67.16 | 71.33 | 75 | 25 | 66.67 | 70 | 78.89 | 60.67 | 51 | 68 | 85 |
35 | | 2025-03-31 | 8.9 | 66.29 | 65.33 | 70 | 25 | 64.67 | 90 | 72.22 | 72.67 | 61 | 55.33 | 70 |
36 | | 2024-12-05 | 15.2 | 65.96 | 76.67 | 45 | 10 | 58 | 85 | 70.67 | 48.33 | 74 | 63.33 | 80 |
37 | | 2025-03-13 | 12.2 | 65.93 | 67.67 | 85 | 10 | 64.67 | 67.5 | 84.44 | 57.33 | 52.33 | 71.33 | 60 |
38 | gpt-4.1-nano-2025-04-14 | 2025-04-17 | | 65.53 | 71.5 | 80 | 20 | 61 | 60 | 76.89 | 71 | 45.67 | 68 | 70 |
39 | gemini-2.0-flash-lite-preview-02-05 | 2025-02-12 | | 65.24 | 59.83 | 75 | 60 | 43.67 | 68 | 72.67 | 80.33 | 71.67 | 63.33 | 60 |
40 | gpt-4-turbo-2024-04-09 | 2024-12-05 | | 65.2 | 76.67 | 90 | 60 | 76.33 | 30 | 80 | 47.33 | 39.33 | 64.67 | 80 |
41 | claude-3-7-sonnet-20250219 | 2025-02-25 | | 64.87 | 69.5 | 50 | 40 | 59 | 25 | 86.89 | 64.67 | 73 | 72 | 30 |
42 | | 2025-02-12 | 34.9 | 64.33 | 81 | 80 | 35 | 77 | 45 | 80.89 | 37.67 | 40 | 60 | 70 |
43 | | 2024-12-05 | 8.3 | 63.16 | 73.17 | 50 | 40 | 56 | 70 | 74.89 | 64.33 | 50 | 53.33 | 60 |
44 | gemini-1.5-flash-8b-001 | 2024-12-05 | | 61.85 | 68.67 | 50 | 15 | 46.67 | 35 | 82.44 | 91.33 | 51.33 | 53.33 | 55 |
45 | | 2024-12-05 | 11.1 | 61.13 | 78 | 65 | 5 | 51.67 | 63 | 77.33 | 53 | 45 | 50 | 70 |
46 | | 2024-12-16 | 38.4 | 60.25 | 64.5 | 35 | 15 | 57.67 | 45 | 69.33 | 56.33 | 58.67 | 71.33 | 86 |
47 | | 2025-04-24 | 3.7 | 59.6 | 73.83 | 50 | 20 | 68.67 | 75 | 67.56 | 56.33 | 35.33 | 37 | 80 |
48 | claude-3-opus-20240229 | 2024-12-13 | | 58.91 | 65.67 | 80 | 25 | 67.67 | 75 | 82.67 | 45 | 31.67 | 40 | 46 |
49 | | 2025-04-14 | 9.1 | 57.02 | 64.5 | 35 | 0 | 50.33 | 77.5 | 62.22 | 67 | 50 | 54.67 | 45 |
50 | | 2025-04-14 | 7.9 | 55.82 | 58.5 | 25 | 20 | 62.33 | 70 | 66.44 | 47.33 | 40.33 | 65.33 | 54 |
51 | | 2024-12-09 | 73.2 | 54.15 | 77.83 | 65 | 5 | 71 | 5 | 79.33 | 23 | 18.33 | 54 | 86 |
52 | | 2025-03-12 | 33.1 | 52.07 | 68.83 | 100 | 35 | 70 | 10 | 76.89 | 24.33 | 16.33 | 38.67 | 70 |
53 | | 2024-12-09 | 76.3 | 51.89 | 72.67 | 90 | 15 | 60 | 5 | 77.11 | 20.33 | 14 | 56.67 | 76 |
54 | | 2025-04-16 | 16.4 | 51.27 | 64.33 | 50 | 5 | 55.67 | 65 | 56 | 41.33 | 33.33 | 48.67 | 50 |
55 | claude-3-haiku-20240307 | 2024-12-05 | | 50.47 | 59.83 | 70 | 0 | 57.33 | 50 | 73.56 | 26.67 | 25.33 | 46.67 | 60 |
56 | | 2024-12-05 | 10.7 | 50.36 | 55.5 | 80 | 25 | 62 | 62.5 | 58.67 | 36 | 24.67 | 46.67 | 50 |
57 | | 2025-02-04 | 3.8 | 49.56 | 54.33 | 40 | 10 | 32.33 | 85 | 55.11 | 53.67 | 48.33 | 42 | 40 |
58 | | 2025-04-11 | 24 | 49.2 | 60.33 | 55 | 15 | 62.67 | 15 | 62.44 | 29 | 38.33 | 46.67 | 80 |
59 | | 2025-03-13 | 4.3 | 49.2 | 68.83 | 75 | 5 | 45.67 | 30 | 78.44 | 23 | 18 | 48.67 | 41 |
60 | | 2024-12-16 | 25.5 | 44.95 | 57.5 | 25 | 10 | 34 | 55 | 60.67 | 32 | 39.67 | 40 | 36 |
61 | | 2024-12-05 | 12.7 | 44.62 | 61.67 | 65 | 10 | 45.67 | 10 | 65.11 | 17.67 | 23.67 | 56 | 40 |
62 | | 2025-03-12 | 8.6 | 44.44 | 70.67 | 75 | 25 | 48.33 | 5 | 72.67 | 27.67 | 9.67 | 14.67 | 60 |
63 | | 2024-12-09 | 8.1 | 44.18 | 56.33 | 25 | 5 | 40.67 | 30 | 57.33 | 44 | 21.33 | 56.67 | 41 |
64 | | 2024-12-11 | 25.3 | 44.15 | 66.5 | 55 | 0 | 50.67 | 5 | 79.33 | 17.33 | 9 | 37.33 | 50 |
65 | | 2024-12-11 | 2.2 | 43.75 | 61 | 55 | 20 | 37.33 | 35 | 48.22 | 54 | 19.33 | 33.33 | 43 |
66 | | 2025-04-25 | 2.1 | 43.67 | 47.17 | 5 | 15 | 34.33 | 71.5 | 52.67 | 47 | 27.33 | 50.67 | 40 |
67 | | 2024-12-05 | 8 | 40.98 | 60.33 | 35 | 15 | 54.33 | 5 | 63.33 | 21.67 | 6.67 | 30.67 | 80 |
68 | | 2024-12-16 | 5.2 | 40.18 | 47.83 | 35 | 0 | 43.33 | 35 | 51.56 | 36.67 | 23 | 50.67 | 20 |
69 | | 2024-12-05 | 10.2 | 38.98 | 73.17 | 55 | 0 | 33 | 10 | 45.11 | 15 | 17 | 31.33 | 66 |
70 | | 2024-12-09 | 73.3 | 36.58 | 45.5 | 25 | 5 | 47.67 | 0 | 54.44 | 18.33 | 20.67 | 42.67 | 70 |
71 | | 2025-04-25 | 0.9 | 33.75 | 28.83 | 20 | 0 | 26 | 50 | 44 | 46 | 20 | 38.67 | 45 |
72 | | 2024-12-05 | 8.1 | 32.69 | 56 | 35 | 0 | 33.67 | 5 | 59.78 | 20.67 | 5.33 | 16.67 | 20 |
73 | | 2024-12-05 | 8.1 | 32.04 | 49.67 | 20 | 0 | 36 | 5 | 36.22 | 24.67 | 16.33 | 31 | 66 |
74 | | 2024-12-16 | 4.1 | 31.89 | 41.17 | 0 | 5 | 39.33 | 10 | 39.78 | 21.67 | 19.33 | 40 | 65 |
75 | claude-3-sonnet-20240229 | 2024-12-13 | | 31.85 | 28.5 | 20 | 0 | 32 | 27.5 | 30.22 | 38 | 49.33 | 42 | 10 |
76 | | 2024-12-05 | 8 | 30.25 | 52.5 | 20 | 0 | 32 | 5 | 47.78 | 12 | 9.33 | 27.33 | 30 |
77 | | 2025-04-01 | 5.6 | 30.18 | 42.17 | 10 | 0 | 23.67 | 11.5 | 39.56 | 25.67 | 24 | 40 | 26 |
78 | | 2024-12-05 | 28.9 | 30.18 | 43.33 | 50 | 0 | 11 | 5 | 43.56 | 29 | 11.33 | 46.67 | 20 |
79 | | 2024-12-16 | 8 | 25.96 | 36.33 | 60 | 0 | 17.33 | 5 | 33.11 | 24.33 | 5.33 | 42 | 10 |
80 | | 2024-12-11 | 2.2 | 21.31 | 14 | 0 | 5 | 36.33 | 5 | 31.33 | 21 | 8.67 | 36.67 | 38 |
81 | | 2024-12-11 | 8.5 | 18.51 | 26.67 | 0 | 0 | 23.33 | 0 | 20 | 21 | 5.33 | 33.33 | 10 |
82 | | 2024-12-05 | 11.1 | 8.33 | 14 | 20 | 0 | 3.33 | 5 | 10.89 | 6.67 | 0 | 5.33 | 20 |