| qwen2.5-coder-32b-instruct |
82.4 |
92.2 |
44.4 |
10 |
1.3 |
1.1 |
0.72 |
| qwen3-14b |
78.7 |
92.4 |
41.3 |
12 |
1.4 |
1.2 |
0.87 |
| qwen2.5-coder-14b-instruct |
76.5 |
89.5 |
39.5 |
12 |
1.5 |
1.3 |
0.79 |
| google_gemma_3_27b_it |
76 |
87 |
38.9 |
9 |
1.5 |
1.3 |
0.77 |
| llama-3.1-70B-instruct |
70.2 |
70.2 |
34.6 |
13 |
1.6 |
1.6 |
0 |
| google_gemma_3_12b_it |
69.7 |
83.6 |
34.3 |
11 |
1.6 |
1.4 |
0.85 |
| qwen3-32b |
69.5 |
84 |
34.4 |
11 |
1.6 |
1.4 |
0.89 |
| deepseek_r1_distill_llama_70b |
66.5 |
87 |
32.3 |
10 |
1.7 |
1.3 |
1.1 |
| qwen2-72b-instruct |
64.1 |
85.5 |
30.5 |
10 |
1.7 |
1.3 |
1.1 |
| google_gemma_2_27b_it |
62.7 |
81.8 |
29.2 |
10 |
1.7 |
1.4 |
0.97 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
62.3 |
83 |
28.8 |
11 |
1.7 |
1.4 |
1 |
| qwen2-math-72b-instruct |
59.5 |
82 |
27.3 |
10 |
1.7 |
1.3 |
1.1 |
| qwen3-4b |
57.4 |
77.5 |
26.1 |
12 |
1.7 |
1.4 |
1 |
| qwen2.5-coder-7b-instruct |
56.2 |
80.6 |
25.1 |
11 |
1.8 |
1.4 |
1.1 |
| google_gemma_3_4b_it |
54.5 |
74.5 |
24 |
13 |
1.8 |
1.5 |
0.96 |
| deepseek_r1_distill_qwen_14b |
54.5 |
88.2 |
26.7 |
11 |
1.8 |
1 |
1.4 |
| deepseek_r1_distill_llama_8b |
52.3 |
78.6 |
22.8 |
12 |
1.8 |
1.3 |
1.2 |
| qwen2.5-coder-3b-instruct |
50.1 |
79.1 |
21.3 |
12 |
1.8 |
1.3 |
1.2 |
| google_gemma_2_9b_it |
48.6 |
69.6 |
19.9 |
12 |
1.8 |
1.5 |
0.98 |
| qwen1.5-32b-chat |
48.3 |
75.5 |
20.1 |
11 |
1.8 |
1.4 |
1.1 |
| qwen1.5-72b-chat |
46.6 |
75.6 |
19.6 |
10 |
1.8 |
1.3 |
1.2 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
45.7 |
73.6 |
18.5 |
11 |
1.8 |
1.3 |
1.1 |
| llama-3.1-8B-instruct |
44.2 |
44.2 |
17.9 |
15 |
1.8 |
1.8 |
0 |
| mistralai_ministral_8b_instruct_2410 |
44.2 |
74.4 |
17.7 |
11 |
1.8 |
1.3 |
1.2 |
| mistralai_mathstral_7b_v0.1 |
40.9 |
72.4 |
15.8 |
11 |
1.7 |
1.3 |
1.1 |
| qwen2-7b-instruct |
39.3 |
69.4 |
15.1 |
11 |
1.7 |
1.3 |
1.1 |
| google_codegemma_1.1_7b_it |
38.2 |
67.6 |
14.8 |
13 |
1.7 |
1.3 |
1.1 |
| qwen1.5-14b-chat |
37.8 |
68.8 |
14.3 |
12 |
1.7 |
1.3 |
1.1 |
| mistralai_mistral_7b_instruct_v0.3 |
34.2 |
62.4 |
12.4 |
11 |
1.7 |
1.3 |
1.1 |
| qwen3-1.7b |
33.9 |
74.4 |
14.8 |
12 |
1.7 |
0.94 |
1.4 |
| qwen3-0.6b |
31.4 |
64.5 |
12 |
13 |
1.6 |
1.1 |
1.2 |
| deepseek_r1_distill_qwen_32b |
30.5 |
75.1 |
13.4 |
10 |
1.6 |
0.83 |
1.4 |
| llama-3.2-3B-instruct |
30.1 |
30.1 |
10.5 |
18 |
1.6 |
1.6 |
0 |
| qwen3-8b |
29.5 |
62.5 |
11.3 |
12 |
1.6 |
1.1 |
1.2 |
| qwen2.5-coder-1.5b-instruct |
29 |
68.2 |
10.7 |
12 |
1.6 |
1 |
1.2 |
| deepseek_v2_lite_chat |
28.1 |
59.6 |
9.99 |
11 |
1.6 |
1.1 |
1.1 |
| google_gemma_3_1b_it |
27.5 |
52.6 |
10.3 |
12 |
1.6 |
1.2 |
1 |
| qwen2-math-7b-instruct |
26.3 |
59.1 |
9.53 |
12 |
1.6 |
1 |
1.2 |
| qwen1.5-7b-chat |
26.2 |
57.5 |
9.23 |
12 |
1.6 |
1.1 |
1.1 |
| google_gemma_7b_it |
25.5 |
47.1 |
9.26 |
12 |
1.5 |
1.2 |
0.95 |
| mistralai_mistral_7b_instruct_v0.1 |
23.6 |
54.1 |
8.26 |
11 |
1.5 |
1 |
1.1 |
| mistralai_mistral_7b_instruct_v0.2 |
22.7 |
59 |
8.24 |
11 |
1.5 |
0.87 |
1.2 |
| qwen2-math-1.5b-instruct |
21.6 |
51.4 |
7.64 |
12 |
1.5 |
1 |
1 |
| qwen2.5-coder-0.5b-instruct |
20.5 |
53.1 |
7.57 |
13 |
1.4 |
0.9 |
1.1 |
| deepseek_r1_distill_qwen_7b |
19.3 |
58.9 |
7.45 |
11 |
1.4 |
0.71 |
1.2 |
| deepseek_r1_distill_qwen_1.5b |
14.1 |
51.6 |
4.94 |
12 |
1.2 |
0.59 |
1.1 |
| google_gemma_2b_it |
12.5 |
37.9 |
4.61 |
13 |
1.2 |
0.73 |
0.92 |
| qwen2-1.5b-instruct |
12.5 |
43.4 |
4.12 |
12 |
1.2 |
0.64 |
0.98 |
| llama-3.2-1B-instruct |
11.4 |
11.4 |
3.77 |
21 |
1.1 |
1.1 |
0 |
| qwen1.5-0.5b-chat |
6.23 |
28.6 |
2.32 |
13 |
0.85 |
0.43 |
0.74 |
| qwen2-0.5b-instruct |
1.84 |
16.2 |
0.666 |
13 |
0.47 |
0.11 |
0.46 |
| qwen1.5-1.8b-chat |
1.17 |
10.4 |
0.378 |
12 |
0.38 |
0.1 |
0.37 |