| qwen3-14b |
82.1 |
87.5 |
41.4 |
3 |
0.48 |
0.41 |
0.24 |
| google_gemma_3_12b_it |
81.5 |
89.2 |
41.3 |
3 |
0.48 |
0.39 |
0.29 |
| llama-3.1-70B-instruct |
81.2 |
81.2 |
41.4 |
4 |
0.48 |
0.48 |
0 |
| qwen3-4b |
75 |
82.8 |
36.8 |
4 |
0.54 |
0.47 |
0.26 |
| qwen2.5-coder-32b-instruct |
74.8 |
83.7 |
36.7 |
2 |
0.54 |
0.39 |
0.37 |
| qwen3-32b |
73.3 |
81.9 |
36.2 |
2 |
0.55 |
0.41 |
0.36 |
| qwen3-8b |
72.6 |
80.8 |
35.2 |
3 |
0.55 |
0.47 |
0.29 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
72.3 |
82.2 |
35 |
2 |
0.55 |
0.39 |
0.39 |
| qwen2-72b-instruct |
71.8 |
82.4 |
35.2 |
2 |
0.56 |
0.39 |
0.4 |
| qwen2-math-72b-instruct |
68.6 |
80.8 |
33.2 |
2 |
0.58 |
0.38 |
0.43 |
| qwen1.5-72b-chat |
65.4 |
76.5 |
31.3 |
2 |
0.59 |
0.42 |
0.41 |
| google_gemma_3_4b_it |
64.4 |
81.2 |
31.2 |
5 |
0.59 |
0.47 |
0.36 |
| qwen2.5-coder-14b-instruct |
63.7 |
82.6 |
30.3 |
3 |
0.6 |
0.38 |
0.46 |
| qwen1.5-32b-chat |
60.9 |
73.9 |
28.3 |
2 |
0.6 |
0.41 |
0.45 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
58.3 |
74.6 |
26.9 |
3 |
0.61 |
0.45 |
0.42 |
| llama-3.1-8B-instruct |
54.7 |
54.7 |
25.1 |
7 |
0.62 |
0.62 |
0 |
| mistralai_mathstral_7b_v0.1 |
53 |
76.3 |
24.1 |
3 |
0.62 |
0.38 |
0.49 |
| qwen2-math-7b-instruct |
51.9 |
75 |
23.5 |
4 |
0.62 |
0.43 |
0.44 |
| llama-3.2-3B-instruct |
49.9 |
49.9 |
22.3 |
10 |
0.62 |
0.62 |
0 |
| qwen3-1.7b |
49 |
63.3 |
21.5 |
4 |
0.62 |
0.52 |
0.34 |
| mistralai_ministral_8b_instruct_2410 |
47.2 |
72.4 |
21.1 |
3 |
0.62 |
0.35 |
0.51 |
| qwen2.5-coder-3b-instruct |
46.7 |
75.9 |
20.8 |
4 |
0.62 |
0.37 |
0.49 |
| qwen2.5-coder-7b-instruct |
46.5 |
72 |
20.7 |
3 |
0.62 |
0.35 |
0.51 |
| mistralai_mistral_7b_instruct_v0.3 |
45.1 |
65.4 |
19.5 |
3 |
0.62 |
0.42 |
0.45 |
| deepseek_v2_lite_chat |
41.4 |
55.8 |
18.4 |
2 |
0.61 |
0.39 |
0.47 |
| qwen1.5-14b-chat |
36.8 |
61.1 |
16.1 |
3 |
0.6 |
0.34 |
0.49 |
| mistralai_mistral_7b_instruct_v0.1 |
35.8 |
59.1 |
15.3 |
3 |
0.59 |
0.36 |
0.47 |
| mistralai_mistral_7b_instruct_v0.2 |
35.3 |
53.9 |
14.5 |
3 |
0.59 |
0.41 |
0.43 |
| qwen2-math-1.5b-instruct |
32.7 |
53.2 |
13.9 |
3 |
0.58 |
0.38 |
0.44 |
| qwen3-0.6b |
30.6 |
54.8 |
13.2 |
4 |
0.57 |
0.37 |
0.43 |
| deepseek_r1_distill_llama_70b |
30.4 |
44.5 |
12.9 |
2 |
0.57 |
0.33 |
0.47 |
| qwen2.5-coder-1.5b-instruct |
28.7 |
59.8 |
12.5 |
4 |
0.56 |
0.29 |
0.48 |
| llama-3.2-1B-instruct |
27.5 |
27.5 |
12.2 |
13 |
0.55 |
0.55 |
0 |
| qwen2-7b-instruct |
27.3 |
50.1 |
11.4 |
3 |
0.55 |
0.3 |
0.46 |
| deepseek_r1_distill_qwen_7b |
25.6 |
46.7 |
10.4 |
3 |
0.54 |
0.3 |
0.45 |
| qwen1.5-7b-chat |
22.3 |
44.2 |
9.25 |
3 |
0.52 |
0.26 |
0.45 |
| deepseek_r1_distill_llama_8b |
22.1 |
49.7 |
8.96 |
4 |
0.51 |
0.25 |
0.45 |
| qwen2.5-coder-0.5b-instruct |
21.7 |
50.5 |
9.77 |
4 |
0.51 |
0.24 |
0.45 |
| deepseek_r1_distill_qwen_14b |
19.2 |
37.5 |
7.61 |
3 |
0.49 |
0.26 |
0.41 |
| deepseek_r1_distill_qwen_32b |
17.3 |
28.5 |
6.94 |
2 |
0.47 |
0.22 |
0.41 |
| qwen2-1.5b-instruct |
11.6 |
33.5 |
5.08 |
4 |
0.4 |
0.15 |
0.37 |
| qwen1.5-1.8b-chat |
11.3 |
25.8 |
4.66 |
3 |
0.39 |
0.17 |
0.35 |
| qwen1.5-0.5b-chat |
10.6 |
29.8 |
4.57 |
4 |
0.38 |
0.16 |
0.35 |
| qwen2-0.5b-instruct |
9.41 |
28 |
4.28 |
4 |
0.36 |
0.13 |
0.34 |
| deepseek_r1_distill_qwen_1.5b |
8.6 |
25.5 |
3.56 |
4 |
0.35 |
0.13 |
0.32 |