| qwen3-32b |
89.4 |
95.6 |
40.6 |
11 |
0.59 |
NaN |
NaN |
| google_gemma_3_27b_it |
89.2 |
94.2 |
40.5 |
10 |
0.59 |
0.52 |
0.28 |
| deepseek_r1_distill_llama_70b |
86.7 |
95.6 |
39 |
11 |
0.65 |
NaN |
NaN |
| google_gemma_3_12b_it |
86.3 |
93.7 |
38.3 |
12 |
0.66 |
NaN |
NaN |
| llama-3.1-70B-instruct |
86.1 |
86.1 |
38.6 |
12 |
0.66 |
0.66 |
0 |
| qwen3-14b |
84.4 |
93.4 |
36.7 |
11 |
0.69 |
0.58 |
0.37 |
| google_gemma_2_27b_it |
83.9 |
92.9 |
36.8 |
10 |
0.7 |
0.58 |
0.39 |
| qwen2-72b-instruct |
80.6 |
91.1 |
34 |
11 |
0.75 |
NaN |
NaN |
| qwen3-8b |
80.5 |
91.6 |
33.9 |
11 |
0.76 |
0.64 |
0.41 |
| deepseek_r1_distill_qwen_32b |
80.3 |
92.1 |
33.9 |
11 |
0.76 |
NaN |
NaN |
| qwen2.5-coder-32b-instruct |
79.4 |
91.1 |
33.2 |
11 |
0.77 |
NaN |
NaN |
| qwen2-math-72b-instruct |
79 |
92.3 |
33.2 |
11 |
0.78 |
NaN |
NaN |
| google_gemma_2_9b_it |
79 |
91.3 |
33.4 |
11 |
0.78 |
0.64 |
0.44 |
| deepseek_r1_distill_qwen_14b |
74.6 |
90 |
30.1 |
13 |
0.83 |
NaN |
NaN |
| qwen3-4b |
74.4 |
87.2 |
29.8 |
12 |
0.83 |
0.72 |
0.42 |
| google_gemma_3_4b_it |
71.8 |
90.1 |
29.1 |
13 |
0.86 |
0.68 |
0.53 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
71.7 |
89.5 |
28.5 |
10 |
0.86 |
NaN |
NaN |
| qwen2.5-coder-14b-instruct |
68.8 |
88 |
26.7 |
11 |
0.88 |
0.69 |
0.56 |
| qwen1.5-72b-chat |
65.3 |
86 |
24.6 |
11 |
0.91 |
NaN |
NaN |
| mistralai_ministral_8b_instruct_2410 |
64.6 |
88 |
24.2 |
12 |
0.91 |
NaN |
NaN |
| llama-3.1-8B-instruct |
64.2 |
64.2 |
25.1 |
15 |
0.91 |
0.91 |
0 |
| deepseek_r1_distill_qwen_7b |
61.7 |
84.1 |
22.6 |
13 |
0.93 |
NaN |
NaN |
| mistralai_mathstral_7b_v0.1 |
60.1 |
89.9 |
22.6 |
13 |
0.93 |
NaN |
NaN |
| qwen1.5-32b-chat |
59.2 |
82.1 |
21.7 |
10 |
0.94 |
NaN |
NaN |
| qwen2.5-coder-7b-instruct |
57.3 |
83 |
20.1 |
13 |
0.94 |
NaN |
NaN |
| qwen2-7b-instruct |
57 |
84.1 |
20.3 |
13 |
0.94 |
NaN |
NaN |
| qwen3-1.7b |
54.6 |
76.5 |
18.9 |
12 |
0.95 |
0.78 |
0.54 |
| llama-3.2-3B-instruct |
51.1 |
51.1 |
18.3 |
18 |
0.95 |
0.95 |
0 |
| qwen2-math-7b-instruct |
50.8 |
77.6 |
17 |
12 |
0.95 |
0.74 |
0.6 |
| qwen1.5-14b-chat |
46.8 |
77.8 |
15.4 |
11 |
0.95 |
0.69 |
0.65 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
45.3 |
77.3 |
15.4 |
10 |
0.95 |
0.67 |
0.67 |
| deepseek_r1_distill_llama_8b |
44.8 |
76.7 |
14.6 |
12 |
0.95 |
0.7 |
0.64 |
| google_codegemma_1.1_7b_it |
41.5 |
76.5 |
13.9 |
13 |
0.94 |
0.68 |
0.65 |
| deepseek_v2_lite_chat |
40.2 |
75.1 |
13 |
9.9 |
0.94 |
NaN |
NaN |
| qwen2.5-coder-3b-instruct |
40.2 |
74.3 |
12.5 |
12 |
0.93 |
0.66 |
0.67 |
| deepseek_r1_distill_qwen_1.5b |
33.4 |
64.7 |
9.7 |
12 |
0.9 |
0.68 |
0.59 |
| qwen1.5-7b-chat |
31.9 |
66.1 |
9.27 |
11 |
0.89 |
0.62 |
0.63 |
| qwen2-math-1.5b-instruct |
31.2 |
56.2 |
8.91 |
12 |
0.88 |
0.71 |
0.53 |
| mistralai_mistral_7b_instruct_v0.3 |
29.1 |
66.5 |
8.63 |
13 |
0.87 |
NaN |
NaN |
| google_gemma_3_1b_it |
26.4 |
58.2 |
7.53 |
12 |
0.84 |
0.62 |
0.56 |
| mistralai_mistral_7b_instruct_v0.2 |
24.6 |
62.9 |
7.34 |
13 |
0.82 |
NaN |
NaN |
| qwen2.5-coder-1.5b-instruct |
23.1 |
57.7 |
6.16 |
12 |
0.8 |
0.53 |
0.6 |
| qwen3-0.6b |
22.8 |
52.3 |
6.32 |
13 |
0.8 |
0.59 |
0.54 |
| llama-3.2-1B-instruct |
19.5 |
19.5 |
5.83 |
8 |
0.76 |
0.76 |
0 |
| google_gemma_7b_it |
18.1 |
45.2 |
5.31 |
12 |
0.73 |
0.54 |
0.5 |
| mistralai_mistral_7b_instruct_v0.1 |
17.7 |
50.6 |
4.72 |
13 |
0.73 |
NaN |
NaN |
| qwen2-1.5b-instruct |
14.6 |
47.1 |
3.68 |
12 |
0.67 |
0.42 |
0.53 |
| google_gemma_2b_it |
5.5 |
22.3 |
1.79 |
12 |
0.43 |
0.25 |
0.35 |
| qwen1.5-1.8b-chat |
5.38 |
26.9 |
1.38 |
11 |
0.43 |
0.2 |
0.38 |
| qwen2-0.5b-instruct |
5.05 |
28.5 |
1.33 |
13 |
0.42 |
0.2 |
0.37 |
| qwen2.5-coder-0.5b-instruct |
4.89 |
24.4 |
1.31 |
13 |
0.41 |
0.21 |
0.35 |
| qwen1.5-0.5b-chat |
2.21 |
17.6 |
0.69 |
13 |
0.28 |
0.093 |
0.26 |