| google_gemma_3_27b_it |
86.5 |
90.1 |
50.3 |
2 |
0.48 |
0.4 |
0.27 |
| qwen3-14b |
82.4 |
87.7 |
47 |
2 |
0.54 |
0.43 |
0.33 |
| google_gemma_3_12b_it |
80.2 |
87.7 |
45.2 |
3 |
0.56 |
0.46 |
0.33 |
| qwen3-4b |
78.1 |
86.8 |
43.6 |
3 |
0.58 |
0.47 |
0.35 |
| qwen3-8b |
77.8 |
84.9 |
43.4 |
2 |
0.59 |
0.45 |
0.38 |
| qwen3-32b |
75.2 |
86.1 |
42.2 |
2 |
0.61 |
0.39 |
0.47 |
| google_gemma_3_4b_it |
71.5 |
82.6 |
38.7 |
4 |
0.64 |
0.53 |
0.36 |
| deepseek_r1_distill_llama_70b |
70.9 |
70.9 |
40.7 |
1 |
0.64 |
NaN |
NaN |
| deepseek_r1_distill_qwen_7b |
68.4 |
88.7 |
39.1 |
3 |
0.66 |
0.35 |
0.56 |
| deepseek_r1_distill_llama_8b |
65.6 |
87 |
37 |
3 |
0.67 |
0.37 |
0.56 |
| qwen3-1.7b |
63 |
76.9 |
32.8 |
3 |
0.68 |
0.52 |
0.44 |
| deepseek_r1_distill_qwen_14b |
59.9 |
83.7 |
34.1 |
3 |
0.69 |
0.38 |
0.58 |
| deepseek_r1_distill_qwen_1.5b |
59 |
82.5 |
32 |
3 |
0.7 |
0.38 |
0.58 |
| llama-3.1-70B-instruct |
58.5 |
58.8 |
29.8 |
3 |
0.7 |
0.69 |
0.077 |
| deepseek_r1_distill_qwen_32b |
57.8 |
57.8 |
32.6 |
1 |
0.7 |
NaN |
NaN |
| qwen2.5-coder-32b-instruct |
54.4 |
54.4 |
27.8 |
1 |
0.7 |
NaN |
NaN |
| qwen2-72b-instruct |
54.1 |
54.1 |
26.7 |
1 |
0.7 |
NaN |
NaN |
| google_gemma_2_9b_it |
44 |
56.8 |
20 |
3 |
0.7 |
0.57 |
0.41 |
| qwen1.5-72b-chat |
41.9 |
41.9 |
19.2 |
1 |
0.7 |
NaN |
NaN |
| qwen2.5-coder-14b-instruct |
41.4 |
55.7 |
19.4 |
2 |
0.7 |
0.45 |
0.53 |
| qwen1.5-32b-chat |
39.6 |
50.8 |
17.8 |
2 |
0.69 |
0.5 |
0.47 |
| qwen2.5-coder-7b-instruct |
35.3 |
57.6 |
16 |
3 |
0.68 |
0.41 |
0.54 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
33.1 |
45.1 |
14.4 |
2 |
0.67 |
0.45 |
0.49 |
| qwen2-7b-instruct |
32.8 |
53.3 |
14.8 |
3 |
0.66 |
0.42 |
0.51 |
| mistralai_mathstral_7b_v0.1 |
32.7 |
52.4 |
14.2 |
3 |
0.66 |
0.44 |
0.5 |
| qwen3-0.6b |
32.4 |
53.3 |
14 |
4 |
0.66 |
0.47 |
0.46 |
| google_gemma_3_1b_it |
32.1 |
45.5 |
13.9 |
3 |
0.66 |
0.51 |
0.42 |
| llama-3.2-3B-instruct |
30.9 |
31.1 |
13.2 |
10 |
0.65 |
0.65 |
0.055 |
| qwen2.5-coder-3b-instruct |
29.9 |
50.8 |
13.1 |
3 |
0.65 |
0.39 |
0.52 |
| llama-3.1-8B-instruct |
28.7 |
28.9 |
12.2 |
7 |
0.64 |
0.64 |
0.057 |
| qwen1.5-14b-chat |
28.5 |
39 |
11.9 |
2 |
0.64 |
0.45 |
0.46 |
| mistralai_ministral_8b_instruct_2410 |
28.5 |
47.7 |
12 |
3 |
0.64 |
0.41 |
0.49 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
22.7 |
32.7 |
9.09 |
2 |
0.59 |
0.39 |
0.45 |
| deepseek_v2_lite_chat |
22 |
32.1 |
8.79 |
2 |
0.59 |
0.38 |
0.45 |
| qwen2.5-coder-1.5b-instruct |
19.9 |
37.6 |
8.05 |
3 |
0.56 |
0.32 |
0.47 |
| google_codegemma_1.1_7b_it |
18.1 |
36.3 |
7.03 |
4 |
0.55 |
0.36 |
0.41 |
| qwen1.5-7b-chat |
17.6 |
33 |
6.8 |
3 |
0.54 |
0.32 |
0.43 |
| llama-3.2-1B-instruct |
12.4 |
12.5 |
4.6 |
12 |
0.47 |
0.46 |
0.042 |
| google_gemma_7b_it |
11.3 |
19.6 |
4.25 |
3 |
0.45 |
0.32 |
0.32 |
| mistralai_mistral_7b_instruct_v0.3 |
11.1 |
22.3 |
4.05 |
3 |
0.44 |
0.26 |
0.36 |
| mistralai_mistral_7b_instruct_v0.2 |
9.4 |
18.1 |
3.36 |
3 |
0.41 |
0.26 |
0.32 |
| qwen2-1.5b-instruct |
8.98 |
20 |
3.4 |
3 |
0.4 |
0.19 |
0.35 |
| google_gemma_2b_it |
6.05 |
12 |
2.29 |
3 |
0.34 |
0.21 |
0.26 |
| qwen2.5-coder-0.5b-instruct |
5.22 |
15.1 |
1.95 |
4 |
0.31 |
0.14 |
0.28 |
| mistralai_mistral_7b_instruct_v0.1 |
4.87 |
11.3 |
1.73 |
3 |
0.3 |
0.15 |
0.27 |
| qwen2-0.5b-instruct |
3.92 |
11.9 |
1.39 |
4 |
0.27 |
0.11 |
0.25 |
| qwen1.5-1.8b-chat |
3.29 |
8.08 |
1.15 |
3 |
0.25 |
0.11 |
0.23 |
| qwen1.5-0.5b-chat |
0.435 |
1.58 |
0.145 |
4 |
0.093 |
0.024 |
0.09 |