| google_gemma_3_27b_it |
87 |
89.6 |
47.1 |
3 |
2.6 |
2.4 |
1 |
| qwen3-14b |
85.4 |
90.2 |
46.3 |
3 |
2.8 |
2.3 |
1.5 |
| google_gemma_3_12b_it |
82.9 |
86 |
44.1 |
4 |
2.9 |
2.7 |
1.1 |
| qwen3-32b |
80.3 |
93.3 |
43 |
3 |
3.1 |
1.9 |
2.5 |
| qwen2.5-coder-32b-instruct |
79.3 |
89.6 |
43.2 |
2 |
3.2 |
1.9 |
2.5 |
| qwen3-4b |
78.8 |
87.8 |
41.6 |
4 |
3.2 |
2.6 |
1.8 |
| qwen3-8b |
78.7 |
90.2 |
42.5 |
3 |
3.2 |
2.3 |
2.2 |
| qwen2.5-coder-14b-instruct |
74 |
90.9 |
39.6 |
3 |
3.4 |
2 |
2.8 |
| google_gemma_2_27b_it |
73.2 |
78.7 |
37.6 |
2 |
3.5 |
2.9 |
1.8 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
71.1 |
84.1 |
36.1 |
3 |
3.5 |
2.5 |
2.5 |
| google_gemma_3_4b_it |
69.8 |
75.6 |
34.8 |
5 |
3.6 |
3.3 |
1.5 |
| google_gemma_2_9b_it |
63.3 |
71.3 |
30.9 |
4 |
3.8 |
3.4 |
1.7 |
| llama-3.1-8B-instruct |
59.8 |
59.8 |
28 |
7 |
3.8 |
3.8 |
0 |
| qwen3-1.7b |
58.8 |
76.2 |
28.9 |
4 |
3.8 |
3 |
2.4 |
| qwen2-math-72b-instruct |
57.9 |
72.6 |
28.8 |
2 |
3.9 |
2.4 |
3 |
| google_codegemma_1.1_7b_it |
54.9 |
75.6 |
25.5 |
5 |
3.9 |
3 |
2.5 |
| qwen1.5-14b-chat |
51.8 |
70.7 |
23.6 |
3 |
3.9 |
2.8 |
2.7 |
| deepseek_r1_distill_qwen_32b |
51.5 |
73.8 |
27.2 |
2 |
3.9 |
1.3 |
3.7 |
| deepseek_r1_distill_qwen_14b |
47.3 |
82.9 |
24.3 |
4 |
3.9 |
1.7 |
3.5 |
| qwen2-72b-instruct |
47 |
65.9 |
23.8 |
2 |
3.9 |
1.9 |
3.4 |
| qwen1.5-32b-chat |
46.7 |
64.6 |
21.7 |
3 |
3.9 |
2.8 |
2.7 |
| deepseek_r1_distill_llama_70b |
45.1 |
65.9 |
24.2 |
2 |
3.9 |
1.6 |
3.6 |
| llama-3.2-3B-instruct |
42.1 |
42.1 |
18.2 |
10 |
3.9 |
3.9 |
0 |
| qwen1.5-72b-chat |
41.8 |
52.4 |
18.3 |
2 |
3.9 |
2.9 |
2.6 |
| google_gemma_3_1b_it |
40.1 |
48.8 |
17.6 |
4 |
3.8 |
3.4 |
1.8 |
| qwen2-7b-instruct |
39.6 |
73.2 |
18.6 |
4 |
3.8 |
1.9 |
3.3 |
| deepseek_v2_lite_chat |
39.2 |
65.9 |
17.9 |
3 |
3.8 |
2 |
3.2 |
| qwen2.5-coder-3b-instruct |
38.6 |
69.5 |
18 |
4 |
3.8 |
2.1 |
3.2 |
| qwen2.5-coder-7b-instruct |
38.6 |
74.4 |
17.9 |
4 |
3.8 |
1.9 |
3.3 |
| mistralai_mistral_7b_instruct_v0.3 |
37.7 |
53.7 |
15.3 |
4 |
3.8 |
3 |
2.3 |
| qwen1.5-7b-chat |
36.4 |
54.9 |
15.2 |
3 |
3.8 |
2.7 |
2.7 |
| mistralai_ministral_8b_instruct_2410 |
35.7 |
67.7 |
15.9 |
4 |
3.7 |
1.9 |
3.2 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
35 |
53.7 |
15.6 |
3 |
3.7 |
2.6 |
2.7 |
| mistralai_mathstral_7b_v0.1 |
30.6 |
59.1 |
13.1 |
4 |
3.6 |
2.1 |
3 |
| qwen2.5-coder-1.5b-instruct |
28.8 |
54.9 |
12 |
4 |
3.5 |
2.1 |
2.8 |
| deepseek_r1_distill_llama_8b |
27.4 |
59.8 |
13 |
4 |
3.5 |
1.6 |
3.1 |
| qwen2-math-7b-instruct |
25 |
39.6 |
11.2 |
2 |
3.4 |
1.6 |
3 |
| google_gemma_7b_it |
24.4 |
37.2 |
9.48 |
4 |
3.4 |
2.7 |
2 |
| qwen2.5-coder-0.5b-instruct |
22.9 |
50 |
9.36 |
5 |
3.3 |
1.9 |
2.7 |
| deepseek_r1_distill_qwen_7b |
22 |
51.2 |
9.93 |
4 |
3.2 |
1.4 |
2.9 |
| llama-3.2-1B-instruct |
22 |
22 |
8.34 |
13 |
3.2 |
3.2 |
0 |
| mistralai_mistral_7b_instruct_v0.1 |
20.1 |
43.3 |
7.54 |
4 |
3.1 |
1.7 |
2.6 |
| qwen3-0.6b |
18.8 |
42.7 |
6.99 |
5 |
3 |
1.9 |
2.4 |
| google_gemma_2b_it |
17.7 |
28.7 |
5.79 |
4 |
3 |
2.4 |
1.7 |
| mistralai_mistral_7b_instruct_v0.2 |
11.7 |
29.9 |
4.32 |
4 |
2.5 |
1.2 |
2.2 |
| qwen2-1.5b-instruct |
8.38 |
28 |
3.32 |
4 |
2.2 |
0.44 |
2.1 |
| qwen1.5-1.8b-chat |
4.47 |
9.15 |
1.61 |
3 |
1.6 |
0.93 |
1.3 |
| qwen2-0.5b-instruct |
3.78 |
9.76 |
0.958 |
5 |
1.5 |
0.81 |
1.2 |
| qwen2-math-1.5b-instruct |
2.24 |
6.1 |
0.891 |
3 |
1.2 |
0.31 |
1.1 |
| qwen1.5-0.5b-chat |
1.83 |
4.88 |
0.367 |
5 |
1 |
0.62 |
0.84 |
| deepseek_r1_distill_qwen_1.5b |
1.37 |
5.49 |
0.484 |
4 |
0.91 |
0 |
0.91 |