| qwen2.5-coder-32b-instruct |
76.1 |
92.8 |
44.6 |
10 |
1.5 |
1.2 |
0.97 |
| google_gemma_3_27b_it |
69 |
87 |
38.7 |
9 |
1.6 |
1.3 |
1 |
| qwen2.5-coder-14b-instruct |
66.1 |
91 |
37 |
12 |
1.7 |
1.2 |
1.1 |
| google_gemma_3_12b_it |
62.5 |
85.6 |
33.7 |
11 |
1.7 |
1.3 |
1.1 |
| llama-3.1-70B-instruct |
61.4 |
61.4 |
32.9 |
13 |
1.7 |
1.7 |
0 |
| google_gemma_2_27b_it |
58 |
85 |
30.6 |
10 |
1.7 |
1.3 |
1.1 |
| qwen2-72b-instruct |
56.9 |
84.2 |
29.8 |
10 |
1.8 |
1.3 |
1.2 |
| qwen2-math-72b-instruct |
56.6 |
84.9 |
29.8 |
10 |
1.8 |
1.3 |
1.2 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
56.1 |
86.8 |
29.6 |
11 |
1.8 |
1.2 |
1.3 |
| qwen2.5-coder-7b-instruct |
54.9 |
85.4 |
28.8 |
11 |
1.8 |
1.3 |
1.2 |
| google_gemma_2_9b_it |
47.9 |
77 |
23.4 |
12 |
1.8 |
1.4 |
1.1 |
| deepseek_r1_distill_qwen_14b |
47 |
78.2 |
23.8 |
11 |
1.8 |
1.3 |
1.2 |
| qwen1.5-72b-chat |
47 |
79.5 |
23.3 |
10 |
1.8 |
1.3 |
1.2 |
| deepseek_r1_distill_llama_70b |
46.8 |
79.1 |
23.6 |
10 |
1.8 |
1.3 |
1.2 |
| google_codegemma_1.1_7b_it |
44.7 |
82.6 |
22.2 |
13 |
1.8 |
1.2 |
1.3 |
| mistralai_mathstral_7b_v0.1 |
44 |
78.2 |
21.2 |
11 |
1.8 |
1.2 |
1.2 |
| google_gemma_3_4b_it |
43.7 |
79.8 |
21.6 |
13 |
1.8 |
1.3 |
1.2 |
| mistralai_ministral_8b_instruct_2410 |
43.3 |
77.9 |
20.8 |
11 |
1.8 |
1.2 |
1.2 |
| qwen2.5-coder-3b-instruct |
43.3 |
82.9 |
21.7 |
12 |
1.8 |
1.1 |
1.3 |
| llama-3.1-8B-instruct |
41.9 |
42 |
20.5 |
15 |
1.7 |
1.7 |
0.052 |
| qwen1.5-32b-chat |
41.4 |
77.2 |
19.8 |
11 |
1.7 |
1.2 |
1.2 |
| qwen2-7b-instruct |
40.4 |
76.9 |
19 |
11 |
1.7 |
1.2 |
1.2 |
| qwen1.5-14b-chat |
39.6 |
73.5 |
18.7 |
12 |
1.7 |
1.2 |
1.2 |
| qwen3-1.7b |
38.6 |
72.1 |
18.4 |
12 |
1.7 |
1.2 |
1.2 |
| qwen3-4b |
37.9 |
64.8 |
18.1 |
12 |
1.7 |
1.3 |
1.1 |
| deepseek_r1_distill_llama_8b |
36 |
71.5 |
16.7 |
12 |
1.7 |
1.2 |
1.2 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
34.5 |
75.2 |
16.1 |
12 |
1.7 |
1.1 |
1.3 |
| qwen2.5-coder-1.5b-instruct |
34.3 |
78 |
16.9 |
12 |
1.7 |
1 |
1.3 |
| qwen3-14b |
32.3 |
51.6 |
14.9 |
12 |
1.7 |
1.4 |
0.89 |
| llama-3.2-3B-instruct |
32.1 |
32.1 |
15.4 |
18 |
1.7 |
1.7 |
0 |
| qwen3-32b |
31.9 |
56.8 |
14.9 |
11 |
1.6 |
1.3 |
0.98 |
| mistralai_mistral_7b_instruct_v0.3 |
31.7 |
65.6 |
14 |
11 |
1.6 |
1.2 |
1.1 |
| qwen2-math-7b-instruct |
31.1 |
65 |
14.8 |
12 |
1.6 |
1.1 |
1.2 |
| google_gemma_7b_it |
29.7 |
63.4 |
14.6 |
12 |
1.6 |
1.1 |
1.2 |
| qwen2.5-coder-0.5b-instruct |
28.2 |
72.8 |
14.7 |
13 |
1.6 |
0.91 |
1.3 |
| qwen1.5-7b-chat |
27.2 |
65.5 |
12 |
12 |
1.6 |
1.1 |
1.2 |
| deepseek_v2_lite_chat |
26.5 |
65.6 |
12 |
11 |
1.6 |
1 |
1.2 |
| mistralai_mistral_7b_instruct_v0.1 |
26.3 |
63.1 |
12 |
11 |
1.6 |
1 |
1.2 |
| mistralai_mistral_7b_instruct_v0.2 |
24.7 |
60.2 |
10.7 |
11 |
1.5 |
0.98 |
1.2 |
| qwen3-0.6b |
22.7 |
59.9 |
10.6 |
13 |
1.5 |
0.9 |
1.2 |
| qwen3-8b |
21.2 |
47.5 |
9.66 |
12 |
1.4 |
0.99 |
1.1 |
| google_gemma_2b_it |
18.7 |
52.1 |
9.76 |
13 |
1.4 |
0.85 |
1.1 |
| deepseek_r1_distill_qwen_7b |
16.9 |
52.5 |
7.15 |
11 |
1.3 |
0.74 |
1.1 |
| qwen2-math-1.5b-instruct |
16.9 |
46.4 |
7.28 |
12 |
1.3 |
0.83 |
1 |
| qwen2-1.5b-instruct |
15.1 |
60.1 |
7.04 |
12 |
1.3 |
0.58 |
1.1 |
| llama-3.2-1B-instruct |
8.88 |
8.88 |
4.3 |
21 |
1 |
1 |
0 |
| deepseek_r1_distill_qwen_1.5b |
6.12 |
27.3 |
2.09 |
12 |
0.85 |
0.42 |
0.74 |
| qwen2-0.5b-instruct |
4.86 |
29.1 |
2.18 |
13 |
0.76 |
0.27 |
0.71 |
| qwen1.5-1.8b-chat |
3.06 |
24.4 |
1.42 |
12 |
0.61 |
0.15 |
0.59 |
| qwen1.5-0.5b-chat |
1.73 |
16.6 |
0.867 |
13 |
0.46 |
0.11 |
0.45 |
| deepseek_r1_distill_qwen_32b |
1.56 |
10.8 |
0.564 |
10 |
0.44 |
0.13 |
0.42 |
| google_gemma_3_1b_it |
0.0865 |
0.5 |
0.0354 |
13 |
0.1 |
0.055 |
0.088 |