| qwen3-32b |
92.5 |
97.7 |
31.9 |
11 |
0.99 |
0.81 |
0.56 |
| qwen3-14b |
90.3 |
95.6 |
30.3 |
11 |
1.1 |
0.96 |
0.56 |
| qwen2-72b-instruct |
89 |
95.6 |
29.6 |
9 |
1.2 |
0.96 |
0.68 |
| llama-3.1-70B-instruct |
88.7 |
88.7 |
30 |
11 |
1.2 |
1.2 |
0 |
| google_gemma_3_27b_it |
88.6 |
94.1 |
29.4 |
10 |
1.2 |
1 |
0.62 |
| deepseek_r1_distill_llama_70b |
88.6 |
95.9 |
29.8 |
9 |
1.2 |
0.95 |
0.72 |
| deepseek_r1_distill_qwen_32b |
87.2 |
96.5 |
28.9 |
9 |
1.3 |
0.96 |
0.8 |
| qwen3-8b |
86.8 |
95.8 |
28.3 |
11 |
1.3 |
1 |
0.72 |
| qwen2.5-coder-32b-instruct |
86.4 |
95.5 |
27.9 |
9 |
1.3 |
1 |
0.77 |
| deepseek_r1_distill_qwen_14b |
85.3 |
95.5 |
27.6 |
12 |
1.3 |
1 |
0.83 |
| google_gemma_3_12b_it |
85.2 |
93.1 |
27.2 |
11 |
1.3 |
1.1 |
0.7 |
| qwen3-4b |
83.3 |
92.3 |
26.7 |
11 |
1.4 |
1.2 |
0.72 |
| google_gemma_2_27b_it |
83.1 |
93 |
26.1 |
10 |
1.4 |
1.2 |
0.76 |
| qwen1.5-72b-chat |
81.5 |
93.8 |
25.4 |
9 |
1.5 |
1.1 |
0.91 |
| google_gemma_2_9b_it |
80.9 |
92.4 |
25 |
12 |
1.5 |
1.2 |
0.81 |
| qwen2-math-72b-instruct |
80.5 |
94.8 |
25.3 |
9 |
1.5 |
1.1 |
0.99 |
| qwen2.5-coder-14b-instruct |
80.5 |
94.1 |
24.8 |
11 |
1.5 |
1.2 |
0.94 |
| qwen1.5-32b-chat |
79.1 |
94.1 |
24.3 |
11 |
1.5 |
1.2 |
0.97 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
76.8 |
94.4 |
24.9 |
11 |
1.6 |
1.1 |
1.2 |
| llama-3.1-8B-instruct |
73.4 |
73.4 |
21.8 |
15 |
1.7 |
1.7 |
0 |
| qwen2-7b-instruct |
72.6 |
93.7 |
21.4 |
12 |
1.7 |
1.2 |
1.1 |
| qwen1.5-14b-chat |
71.8 |
89 |
20.7 |
11 |
1.7 |
1.4 |
0.98 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
71 |
92.4 |
20.9 |
11 |
1.7 |
1.3 |
1.1 |
| qwen2.5-coder-7b-instruct |
70.9 |
94.7 |
20.7 |
12 |
1.7 |
1.2 |
1.2 |
| qwen3-1.7b |
70.8 |
87.6 |
20.9 |
11 |
1.7 |
1.4 |
0.99 |
| mistralai_ministral_8b_instruct_2410 |
69.2 |
95.8 |
20.1 |
12 |
1.7 |
1.2 |
1.3 |
| google_gemma_3_4b_it |
68.5 |
86.5 |
19.7 |
13 |
1.7 |
1.5 |
0.96 |
| deepseek_r1_distill_llama_8b |
63.2 |
92.5 |
18.2 |
12 |
1.8 |
1.2 |
1.4 |
| qwen2-math-7b-instruct |
61.9 |
92.7 |
18.6 |
11 |
1.8 |
1.2 |
1.3 |
| qwen1.5-7b-chat |
61.5 |
90 |
17.1 |
12 |
1.8 |
1.4 |
1.2 |
| llama-3.2-3B-instruct |
60.3 |
60.3 |
16.4 |
18 |
1.8 |
1.8 |
0 |
| mistralai_mistral_7b_instruct_v0.3 |
59.7 |
86.9 |
16.5 |
12 |
1.8 |
1.4 |
1.2 |
| mistralai_mathstral_7b_v0.1 |
57.6 |
92.3 |
15.9 |
12 |
1.9 |
1.2 |
1.4 |
| deepseek_v2_lite_chat |
57.2 |
90.3 |
15.8 |
11 |
1.9 |
1.3 |
1.3 |
| qwen2.5-coder-3b-instruct |
55.3 |
93 |
15.2 |
11 |
1.9 |
1.2 |
1.4 |
| deepseek_r1_distill_qwen_7b |
54.4 |
88.6 |
15.5 |
12 |
1.9 |
1.2 |
1.4 |
| google_codegemma_1.1_7b_it |
52.9 |
83.4 |
14.2 |
13 |
1.9 |
1.4 |
1.2 |
| mistralai_mistral_7b_instruct_v0.2 |
52.3 |
80.7 |
14.2 |
12 |
1.9 |
1.4 |
1.3 |
| mistralai_mistral_7b_instruct_v0.1 |
49 |
88.9 |
13.1 |
12 |
1.9 |
1.2 |
1.4 |
| google_gemma_7b_it |
48.1 |
77.4 |
13.1 |
12 |
1.9 |
1.4 |
1.2 |
| qwen3-0.6b |
47.2 |
82.3 |
12.9 |
12 |
1.9 |
1.4 |
1.3 |
| qwen2-1.5b-instruct |
39.2 |
84.1 |
10.4 |
11 |
1.8 |
1.2 |
1.4 |
| google_gemma_3_1b_it |
35.4 |
71.3 |
9.39 |
12 |
1.8 |
1.3 |
1.2 |
| qwen2-math-1.5b-instruct |
34.3 |
85.7 |
10.7 |
11 |
1.8 |
0.95 |
1.5 |
| qwen2.5-coder-1.5b-instruct |
33.9 |
88.6 |
9.75 |
11 |
1.8 |
0.81 |
1.6 |
| google_gemma_2b_it |
32.6 |
50.9 |
9.28 |
12 |
1.8 |
1.5 |
0.88 |
| llama-3.2-1B-instruct |
31.9 |
31.9 |
8.67 |
21 |
1.7 |
1.7 |
0 |
| qwen1.5-1.8b-chat |
30.5 |
79.5 |
8.29 |
12 |
1.7 |
0.98 |
1.4 |
| deepseek_r1_distill_qwen_1.5b |
26.5 |
77.6 |
7.34 |
12 |
1.7 |
0.81 |
1.4 |
| qwen2-0.5b-instruct |
22.3 |
78.1 |
7.08 |
13 |
1.6 |
0.79 |
1.3 |
| qwen2.5-coder-0.5b-instruct |
19.7 |
85.9 |
6.82 |
12 |
1.5 |
0.39 |
1.4 |
| qwen1.5-0.5b-chat |
19.7 |
73.4 |
6.23 |
12 |
1.5 |
0.68 |
1.3 |