| 1 |
Mistralai/Mistral-Medium-3.1 |
92.0 ± 5.1% |
53 |
57 |
3 |
1 |
| 2 |
Mistralai/Mistral-Medium-3 |
88.8 ± 6.3% |
52 |
58 |
4 |
2 |
| 3 |
Mistralai/Mistral-Large |
85.1 ± 7.9% |
43 |
50 |
7 |
0 |
| 4 |
Mistralai/Mistral-Large-2411 |
84.5 ± 8.2% |
41 |
48 |
4 |
3 |
| 5 |
Mistralai/Devstral-Medium |
80.5 ± 10.2% |
31 |
38 |
4 |
3 |
| 6 |
Mistralai/Mistral-Small-3.2-24b-Instruct |
74.7 ± 13.0% |
22 |
29 |
6 |
1 |
| 7 |
Mistralai/Magistral-Medium-2506:thinking |
74.7 ± 13.8% |
19 |
25 |
2 |
4 |
| 8 |
Mistralai/Mistral-Saba |
72.9 ± 13.8% |
20 |
27 |
7 |
0 |
| 9 |
Mistralai/Mistral-Large-2407 |
70.9 ± 14.8% |
18 |
25 |
6 |
1 |
| 10 |
Mistralai/Devstral-Small-2505 |
69.7 ± 15.3% |
17 |
24 |
4 |
3 |
| 11 |
Mistralai/Devstral-Small |
68.5 ± 15.9% |
16 |
23 |
6 |
1 |
| 11 |
Mistralai/Pixtral-Large-2411 |
68.5 ± 15.9% |
16 |
23 |
7 |
0 |
| 12 |
Mistralai/Codestral-2508 |
65.5 ± 18.2% |
12 |
18 |
6 |
0 |
| 13 |
Mistralai/Mistral-Small-3.1-24b-Instruct:free |
61.5 ± 20.0% |
10 |
16 |
6 |
0 |
| 14 |
Mistralai/Codestral-2501 |
60.3 ± 19.4% |
11 |
18 |
6 |
1 |
| 14 |
Mistralai/Mistral-7b-Instruct-V0.3 |
60.3 ± 19.4% |
11 |
18 |
7 |
0 |
| 14 |
Mistralai/Mistral-Small-3.1-24b-Instruct |
60.3 ± 19.4% |
11 |
18 |
4 |
3 |
| 15 |
Mistralai/Magistral-Small-2506 |
59.2 ± 21.1% |
9 |
15 |
0 |
6 |
| 16 |
Mistralai/Mistral-7b-Instruct:free |
58.2 ± 20.3% |
10 |
17 |
7 |
0 |
| 17 |
Mistralai/Magistral-Medium-2506 |
53.5 ± 23.5% |
7 |
13 |
3 |
3 |
| 17 |
Mistralai/Mistral-Small |
53.5 ± 23.5% |
7 |
13 |
5 |
1 |
| 17 |
Mistralai/Pixtral-12b |
53.5 ± 23.5% |
7 |
13 |
4 |
2 |
| 18 |
Mistralai/Mistral-7b-Instruct |
50.0 ± 24.9% |
6 |
12 |
6 |
0 |
| 19 |
Mistralai/Ministral-8b |
46.0 ± 26.4% |
5 |
11 |
3 |
3 |
| 20 |
Mistralai/Ministral-3b |
39.3 ± 30.8% |
3 |
8 |
4 |
1 |
| 20 |
Mistralai/Mistral-Small-24b-Instruct-2501 |
39.3 ± 30.8% |
3 |
8 |
3 |
2 |
| 21 |
Mistralai/Mistral-Tiny |
35.5 ± 29.7% |
3 |
9 |
3 |
3 |
| 22 |
Mistralai/Mistral-Nemo |
32.1 ± 33.0% |
2 |
7 |
3 |
2 |
| 22 |
Mistralai/Mixtral-8x22b-Instruct |
32.1 ± 33.0% |
2 |
7 |
2 |
3 |
| 23 |
Mistralai/Mistral-7b-Instruct-V0.1 |
12.9 ± 39.2% |
0 |
4 |
2 |
2 |
| 23 |
Mistralai/Mistral-7b-Instruct-V0.2 |
12.9 ± 39.2% |
0 |
4 |
0 |
4 |
| 23 |
Mistralai/Mixtral-8x7b-Instruct |
12.9 ± 39.2% |
0 |
4 |
3 |
1 |