| qwen2.5-coder-32b-instruct |
74.2 |
82.1 |
48.8 |
2 |
1.5 |
1.2 |
1 |
| google_gemma_3_27b_it |
68.9 |
81.1 |
44.1 |
3 |
1.6 |
1.3 |
1 |
| qwen2.5-coder-14b-instruct |
62.7 |
81.8 |
39.7 |
3 |
1.7 |
1.1 |
1.3 |
| google_gemma_3_12b_it |
61.3 |
78.2 |
37.7 |
4 |
1.7 |
1.3 |
1.1 |
| qwen2-72b-instruct |
53.8 |
66.9 |
32.2 |
2 |
1.8 |
1.2 |
1.3 |
| llama-3.1-70B-instruct |
53.1 |
53.1 |
32.1 |
4 |
1.8 |
1.8 |
0 |
| google_gemma_2_27b_it |
52.8 |
65 |
31.4 |
2 |
1.8 |
1.3 |
1.2 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
48.5 |
70 |
28.7 |
3 |
1.8 |
1.2 |
1.3 |
| qwen2.5-coder-7b-instruct |
46.7 |
70 |
27.6 |
4 |
1.8 |
1.2 |
1.3 |
| google_gemma_3_4b_it |
43.8 |
69.5 |
25.4 |
5 |
1.8 |
1.2 |
1.2 |
| qwen1.5-72b-chat |
43.6 |
58.4 |
25.2 |
2 |
1.8 |
1.1 |
1.4 |
| google_gemma_2_9b_it |
42.7 |
60.4 |
24.1 |
3 |
1.7 |
1.3 |
1.2 |
| google_codegemma_1.1_7b_it |
40.5 |
70 |
23.3 |
5 |
1.7 |
1.1 |
1.3 |
| qwen3-4b |
39 |
59 |
22.2 |
4 |
1.7 |
1.3 |
1.1 |
| qwen2.5-coder-3b-instruct |
38.9 |
66.6 |
22.3 |
4 |
1.7 |
1 |
1.4 |
| qwen1.5-32b-chat |
37.5 |
57.2 |
20.6 |
3 |
1.7 |
1.2 |
1.3 |
| qwen3-1.7b |
37.2 |
59.4 |
21 |
4 |
1.7 |
1.2 |
1.2 |
| qwen2-math-72b-instruct |
35.8 |
51.2 |
20.4 |
2 |
1.7 |
0.97 |
1.4 |
| qwen1.5-14b-chat |
35.4 |
54 |
19.4 |
3 |
1.7 |
1.2 |
1.2 |
| deepseek_r1_distill_llama_70b |
34.1 |
45.4 |
18.7 |
2 |
1.7 |
1.2 |
1.2 |
| deepseek_r1_distill_qwen_14b |
34.1 |
58.5 |
18.9 |
4 |
1.7 |
1.1 |
1.3 |
| mistralai_ministral_8b_instruct_2410 |
32.2 |
57.5 |
17.2 |
4 |
1.7 |
1.1 |
1.3 |
| mistralai_mathstral_7b_v0.1 |
32.2 |
56 |
17.2 |
4 |
1.7 |
1.1 |
1.2 |
| qwen3-32b |
31.3 |
46.2 |
17.1 |
3 |
1.6 |
1.2 |
1.1 |
| qwen2-7b-instruct |
31 |
56.5 |
16.6 |
4 |
1.6 |
1 |
1.3 |
| qwen3-14b |
29.7 |
40.1 |
15.9 |
3 |
1.6 |
1.3 |
0.91 |
| llama-3.1-8B-instruct |
27.6 |
27.6 |
14.9 |
7 |
1.6 |
1.6 |
0 |
| google_gemma_7b_it |
27.6 |
53.2 |
15.9 |
4 |
1.6 |
0.91 |
1.3 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
26.1 |
45.8 |
13.8 |
3 |
1.6 |
0.96 |
1.2 |
| mistralai_mistral_7b_instruct_v0.3 |
25.6 |
46.6 |
13 |
4 |
1.5 |
1 |
1.1 |
| qwen2.5-coder-1.5b-instruct |
24 |
52 |
13.1 |
4 |
1.5 |
0.79 |
1.3 |
| deepseek_r1_distill_llama_8b |
23.7 |
43.4 |
12 |
4 |
1.5 |
1 |
1.1 |
| qwen1.5-7b-chat |
22.7 |
39 |
11.9 |
3 |
1.5 |
0.96 |
1.1 |
| llama-3.2-3B-instruct |
21.2 |
21.2 |
11.6 |
10 |
1.4 |
1.4 |
0 |
| deepseek_v2_lite_chat |
21.2 |
40.2 |
11 |
3 |
1.4 |
0.82 |
1.2 |
| qwen3-8b |
18.6 |
33.2 |
10 |
3 |
1.4 |
0.87 |
1.1 |
| qwen2.5-coder-0.5b-instruct |
18 |
48.5 |
10.4 |
5 |
1.4 |
0.62 |
1.2 |
| mistralai_mistral_7b_instruct_v0.2 |
17.3 |
39.5 |
8.83 |
4 |
1.3 |
0.7 |
1.1 |
| qwen3-0.6b |
15.4 |
40.8 |
8.46 |
5 |
1.3 |
0.65 |
1.1 |
| google_gemma_2b_it |
15.3 |
36.6 |
9.39 |
4 |
1.3 |
0.67 |
1.1 |
| mistralai_mistral_7b_instruct_v0.1 |
13.6 |
33.4 |
6.84 |
4 |
1.2 |
0.6 |
1.1 |
| deepseek_r1_distill_qwen_7b |
12 |
28.9 |
5.92 |
4 |
1.1 |
0.58 |
0.99 |
| qwen2-math-7b-instruct |
7.44 |
22.1 |
3.89 |
4 |
0.93 |
0.38 |
0.85 |
| qwen2-1.5b-instruct |
6.72 |
21.1 |
3.64 |
4 |
0.89 |
0.28 |
0.84 |
| llama-3.2-1B-instruct |
3.62 |
3.62 |
2.07 |
13 |
0.66 |
0.66 |
0 |
| deepseek_r1_distill_qwen_32b |
3.5 |
6.62 |
1.66 |
2 |
0.65 |
0.18 |
0.62 |
| qwen2-0.5b-instruct |
1.95 |
9 |
1.03 |
5 |
0.49 |
0.068 |
0.48 |
| qwen2-math-1.5b-instruct |
1.84 |
6.75 |
0.915 |
4 |
0.48 |
0.094 |
0.47 |
| deepseek_r1_distill_qwen_1.5b |
1.78 |
6 |
0.722 |
4 |
0.47 |
0.15 |
0.44 |
| qwen1.5-1.8b-chat |
1.04 |
3.12 |
0.616 |
3 |
0.36 |
0 |
0.36 |
| qwen1.5-0.5b-chat |
0.375 |
1.88 |
0.167 |
5 |
0.22 |
0 |
0.22 |
| google_gemma_3_1b_it |
0.0938 |
0.375 |
0.0484 |
4 |
0.11 |
0 |
0.11 |