| 1 |
Meta-llama/Llama-4-Maverick:free |
95.6 ± 3.3% |
58 |
60 |
1 |
1 |
| 2 |
Meta-llama/Llama-4-Maverick |
92.1 ± 5.1% |
54 |
58 |
2 |
2 |
| 3 |
Meta-llama/Llama-3.3-70b-Instruct |
84.1 ± 8.4% |
40 |
47 |
5 |
2 |
| 4 |
Meta-llama/Llama-3.3-70b-Instruct:free |
78.9 ± 11.0% |
28 |
35 |
3 |
4 |
| 5 |
Meta-llama/Llama-3.2-90b-Vision-Instruct |
74.7 ± 13.0% |
22 |
29 |
4 |
3 |
| 6 |
Meta-llama/Llama-4-Scout |
70.9 ± 14.8% |
18 |
25 |
1 |
6 |
| 7 |
Meta-llama/Llama-3-70b-Instruct |
63.6 ± 19.1% |
11 |
17 |
5 |
1 |
| 8 |
Meta-llama/Llama-4-Scout:free |
60.3 ± 19.4% |
11 |
18 |
3 |
4 |
| 9 |
Meta-llama/Llama-3.1-405b-Instruct |
56.5 ± 22.2% |
8 |
14 |
3 |
3 |
| 9 |
Meta-llama/Llama-3.1-70b-Instruct |
56.5 ± 22.2% |
8 |
14 |
4 |
2 |
| 10 |
Meta-llama/Llama-3.2-3b-Instruct |
41.2 ± 28.0% |
4 |
10 |
5 |
1 |
| 11 |
Meta-llama/Llama-3.3-8b-Instruct:free |
39.3 ± 30.8% |
3 |
8 |
1 |
4 |
| 12 |
Meta-llama/Llama-3-8b-Instruct |
32.1 ± 33.0% |
2 |
7 |
4 |
1 |
| 13 |
Meta-llama/Llama-3.1-405b |
29.3 ± 54.9% |
0 |
1 |
1 |
0 |
| 14 |
Meta-llama/Llama-3.1-8b-Instruct |
26.4 ± 37.7% |
1 |
5 |
3 |
1 |
| 15 |
Meta-llama/Llama-3.2-11b-Vision-Instruct |
12.9 ± 39.2% |
0 |
4 |
1 |
3 |
| 15 |
Meta-llama/Llama-3.2-3b-Instruct:free |
12.9 ± 39.2% |
0 |
4 |
3 |
1 |