| google_gemma_3_27b_it |
94.2 |
96.5 |
28 |
11 |
0.65 |
0.59 |
0.27 |
| qwen3-32b |
93.9 |
97.7 |
28 |
11 |
0.66 |
0.54 |
0.38 |
| llama-3.1-70B-instruct |
93.8 |
93.8 |
28 |
11 |
0.66 |
0.66 |
0 |
| qwen3-14b |
93.5 |
96.5 |
27.7 |
11 |
0.68 |
0.6 |
0.32 |
| deepseek_r1_distill_llama_70b |
92.6 |
97.6 |
27.6 |
10 |
0.72 |
0.53 |
0.48 |
| qwen2-math-72b-instruct |
92.5 |
98.4 |
27.3 |
9 |
0.73 |
0.49 |
0.53 |
| qwen3-8b |
92.2 |
96.1 |
26.8 |
11 |
0.74 |
0.64 |
0.38 |
| qwen2.5-coder-32b-instruct |
92.1 |
97.5 |
27 |
9 |
0.74 |
0.56 |
0.48 |
| google_gemma_3_12b_it |
92.1 |
96.2 |
26.9 |
12 |
0.74 |
0.65 |
0.36 |
| qwen2-72b-instruct |
91.6 |
98.1 |
26.8 |
10 |
0.76 |
0.55 |
0.53 |
| google_gemma_2_27b_it |
90.2 |
95.8 |
25.6 |
9 |
0.82 |
0.69 |
0.45 |
| qwen3-4b |
89.2 |
93.4 |
25.3 |
11 |
0.85 |
0.78 |
0.35 |
| google_gemma_2_9b_it |
87.6 |
95.1 |
24.3 |
11 |
0.91 |
0.74 |
0.52 |
| qwen2.5-coder-14b-instruct |
86.4 |
98 |
24 |
11 |
0.94 |
0.63 |
0.7 |
| deepseek_r1_distill_qwen_7b |
86.4 |
97.3 |
24.2 |
11 |
0.94 |
0.65 |
0.68 |
| deepseek_r1_distill_qwen_32b |
85.9 |
98 |
25.1 |
10 |
0.96 |
0.57 |
0.77 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
84.8 |
98.1 |
23.3 |
11 |
0.99 |
0.67 |
0.73 |
| deepseek_r1_distill_qwen_14b |
84.7 |
96 |
24.1 |
11 |
0.99 |
0.7 |
0.7 |
| qwen1.5-72b-chat |
84.2 |
96.7 |
23 |
10 |
1 |
0.73 |
0.69 |
| google_gemma_3_4b_it |
83.4 |
93.4 |
22.5 |
13 |
1 |
0.86 |
0.56 |
| qwen1.5-32b-chat |
83.2 |
96.9 |
22.6 |
11 |
1 |
0.71 |
0.74 |
| qwen2-math-7b-instruct |
83 |
96.1 |
22.2 |
11 |
1 |
0.76 |
0.7 |
| llama-3.1-8B-instruct |
81 |
81 |
21.3 |
15 |
1.1 |
1.1 |
0.035 |
| qwen2-math-1.5b-instruct |
80.4 |
95.1 |
21.1 |
11 |
1.1 |
0.81 |
0.73 |
| mistralai_ministral_8b_instruct_2410 |
79.8 |
96.1 |
20.8 |
12 |
1.1 |
0.78 |
0.79 |
| deepseek_r1_distill_llama_8b |
79.7 |
96.4 |
21.4 |
12 |
1.1 |
0.72 |
0.84 |
| qwen2-7b-instruct |
78 |
96.8 |
20.4 |
12 |
1.1 |
0.74 |
0.87 |
| qwen2.5-coder-7b-instruct |
77.1 |
96.7 |
20 |
12 |
1.2 |
0.77 |
0.87 |
| mistralai_mathstral_7b_v0.1 |
74.9 |
95.9 |
18.9 |
11 |
1.2 |
0.78 |
0.9 |
| llama-3.2-3B-instruct |
73.4 |
73.4 |
18 |
17 |
1.2 |
1.2 |
0 |
| qwen3-1.7b |
73.4 |
87.3 |
18.1 |
11 |
1.2 |
1 |
0.64 |
| qwen1.5-14b-chat |
72.8 |
92.8 |
17.9 |
10 |
1.2 |
0.9 |
0.83 |
| deepseek_r1_distill_qwen_1.5b |
68.6 |
94.2 |
17.3 |
12 |
1.3 |
0.79 |
1 |
| deepseek_v2_lite_chat |
67.7 |
92.3 |
16 |
11 |
1.3 |
0.92 |
0.9 |
| qwen2.5-coder-3b-instruct |
66.2 |
92.5 |
15.5 |
11 |
1.3 |
0.89 |
0.95 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
65.7 |
93.9 |
15.7 |
11 |
1.3 |
0.87 |
0.98 |
| qwen1.5-7b-chat |
59.1 |
88.9 |
13.2 |
12 |
1.4 |
0.93 |
0.99 |
| google_codegemma_1.1_7b_it |
54.8 |
87.5 |
11.8 |
13 |
1.4 |
0.97 |
0.97 |
| qwen2.5-coder-1.5b-instruct |
49.9 |
84.8 |
10.3 |
11 |
1.4 |
0.93 |
1 |
| mistralai_mistral_7b_instruct_v0.3 |
48.3 |
84.8 |
10 |
11 |
1.4 |
0.93 |
1 |
| google_gemma_3_1b_it |
44.7 |
70.7 |
8.82 |
12 |
1.4 |
1.1 |
0.79 |
| qwen3-0.6b |
41.6 |
74.2 |
7.92 |
13 |
1.4 |
1 |
0.91 |
| mistralai_mistral_7b_instruct_v0.2 |
40 |
75.7 |
7.87 |
11 |
1.3 |
0.94 |
0.97 |
| llama-3.2-1B-instruct |
38 |
38 |
7.06 |
12 |
1.3 |
1.3 |
0 |
| qwen2-1.5b-instruct |
37.9 |
81.2 |
7.42 |
11 |
1.3 |
0.78 |
1.1 |
| mistralai_mistral_7b_instruct_v0.1 |
34.3 |
74.8 |
6.37 |
11 |
1.3 |
0.84 |
1 |
| google_gemma_7b_it |
28.9 |
60 |
5.11 |
12 |
1.2 |
0.92 |
0.85 |
| qwen2-0.5b-instruct |
19.5 |
62.7 |
3.12 |
13 |
1.1 |
0.62 |
0.9 |
| qwen1.5-1.8b-chat |
15.8 |
57.1 |
2.53 |
12 |
1 |
0.5 |
0.87 |
| qwen2.5-coder-0.5b-instruct |
14 |
51.4 |
2.04 |
13 |
0.95 |
0.55 |
0.78 |
| google_gemma_2b_it |
9.9 |
30.6 |
1.46 |
12 |
0.82 |
0.58 |
0.58 |
| qwen1.5-0.5b-chat |
6.86 |
34.7 |
1.02 |
13 |
0.7 |
0.34 |
0.61 |