| qwen3-32b |
80.1 |
94.5 |
33.7 |
10 |
2 |
1.5 |
1.3 |
| qwen3-14b |
77 |
92.3 |
31.6 |
11 |
2.1 |
1.7 |
1.2 |
| llama-3.1-70B-instruct |
75.2 |
75.2 |
30.2 |
13 |
2.2 |
2.2 |
0 |
| deepseek_r1_distill_llama_70b |
74.9 |
89.6 |
29.9 |
9 |
2.2 |
1.8 |
1.2 |
| qwen2-72b-instruct |
73.6 |
81.1 |
29.4 |
8 |
2.2 |
2 |
0.82 |
| qwen3-8b |
72.2 |
92.6 |
28.9 |
11 |
2.2 |
1.7 |
1.4 |
| deepseek_r1_distill_qwen_32b |
71.3 |
88.3 |
28 |
9 |
2.3 |
1.8 |
1.4 |
| qwen2.5-coder-32b-instruct |
70.4 |
90.6 |
27.3 |
10 |
2.3 |
1.8 |
1.4 |
| qwen3-4b |
70 |
89.8 |
27.9 |
12 |
2.3 |
1.8 |
1.4 |
| qwen1.5-72b-chat |
67.5 |
67.5 |
25.2 |
1 |
2.3 |
NaN |
NaN |
| google_gemma_3_12b_it |
67 |
83.9 |
25.5 |
10 |
2.3 |
2 |
1.3 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
66.8 |
84.1 |
25 |
11 |
2.3 |
2 |
1.2 |
| deepseek_r1_distill_qwen_14b |
66.7 |
87.6 |
25.5 |
11 |
2.3 |
1.8 |
1.5 |
| qwen2-math-72b-instruct |
66.7 |
83.1 |
25.1 |
7 |
2.3 |
1.9 |
1.3 |
| qwen1.5-32b-chat |
66.5 |
66.5 |
24.5 |
1 |
2.4 |
NaN |
NaN |
| qwen2.5-coder-14b-instruct |
63.2 |
86.4 |
22.8 |
11 |
2.4 |
2 |
1.3 |
| qwen2-7b-instruct |
58.3 |
77.2 |
20.6 |
12 |
2.5 |
2.1 |
1.2 |
| qwen1.5-14b-chat |
57.5 |
73.2 |
20 |
11 |
2.5 |
2.2 |
1.1 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
57.4 |
72 |
20 |
11 |
2.5 |
2.3 |
0.99 |
| qwen2.5-coder-7b-instruct |
56.2 |
80.4 |
19.7 |
12 |
2.5 |
2.1 |
1.4 |
| llama-3.1-8B-instruct |
53.6 |
53.6 |
18.2 |
15 |
2.5 |
2.5 |
0 |
| qwen3-1.7b |
51.2 |
79.2 |
18.2 |
12 |
2.5 |
1.9 |
1.6 |
| mistralai_ministral_8b_instruct_2410 |
51 |
87.3 |
17.4 |
12 |
2.5 |
1.8 |
1.7 |
| qwen1.5-7b-chat |
50.5 |
70.7 |
16.8 |
12 |
2.5 |
2.2 |
1.2 |
| mistralai_mathstral_7b_v0.1 |
49.4 |
80.9 |
16.7 |
11 |
2.5 |
1.9 |
1.6 |
| google_gemma_3_4b_it |
48.6 |
76.7 |
17 |
13 |
2.5 |
2 |
1.5 |
| mistralai_mistral_7b_instruct_v0.3 |
48 |
64.8 |
15.2 |
11 |
2.5 |
2.2 |
1.2 |
| mistralai_mistral_7b_instruct_v0.2 |
47.6 |
53.8 |
16.1 |
11 |
2.5 |
2.4 |
0.72 |
| deepseek_v2_lite_chat |
47.5 |
76.4 |
16.4 |
11 |
2.5 |
2 |
1.5 |
| llama-3.2-3B-instruct |
46.9 |
46.9 |
16 |
15 |
2.5 |
2.5 |
0 |
| deepseek_r1_distill_llama_8b |
45.1 |
84.4 |
15.4 |
12 |
2.5 |
1.6 |
1.9 |
| deepseek_r1_distill_qwen_7b |
44.1 |
78.4 |
15.3 |
11 |
2.5 |
1.7 |
1.8 |
| qwen2-math-7b-instruct |
43.8 |
76.4 |
15.3 |
12 |
2.5 |
1.9 |
1.5 |
| qwen2.5-coder-3b-instruct |
40.2 |
89.3 |
14 |
12 |
2.4 |
1.5 |
1.9 |
| mistralai_mistral_7b_instruct_v0.1 |
37.4 |
83.6 |
12.7 |
11 |
2.4 |
1.5 |
1.8 |
| qwen3-0.6b |
37 |
64.5 |
13.7 |
13 |
2.4 |
2 |
1.4 |
| qwen2-1.5b-instruct |
34.6 |
75.4 |
11.7 |
12 |
2.4 |
1.7 |
1.7 |
| qwen1.5-1.8b-chat |
27.6 |
73.4 |
10.3 |
12 |
2.2 |
1.4 |
1.7 |
| qwen2.5-coder-1.5b-instruct |
27.4 |
88.8 |
10.3 |
12 |
2.2 |
1.1 |
2 |
| llama-3.2-1B-instruct |
26.3 |
26.3 |
9.65 |
11 |
2.2 |
2.2 |
0 |
| qwen2-math-1.5b-instruct |
24.3 |
77.2 |
10.5 |
11 |
2.1 |
1.1 |
1.8 |
| deepseek_r1_distill_qwen_1.5b |
24.2 |
74.7 |
9.21 |
12 |
2.1 |
0.98 |
1.9 |
| qwen2-0.5b-instruct |
22.7 |
86.1 |
10 |
13 |
2.1 |
0.84 |
1.9 |
| qwen1.5-0.5b-chat |
21.7 |
86.1 |
9.62 |
13 |
2.1 |
0.7 |
1.9 |
| qwen2.5-coder-0.5b-instruct |
20.5 |
91.3 |
9.33 |
13 |
2 |
0.33 |
2 |