| qwen3-14b |
77.6 |
91.5 |
38 |
1.1e+03 |
3.3 |
2.9 |
1.4 |
| qwen3-32b |
77.3 |
93.3 |
37.7 |
1.1e+03 |
3.3 |
2.7 |
1.8 |
| google_gemma_3_27b_it |
75.7 |
78.7 |
36.2 |
7 |
3.3 |
3.2 |
0.93 |
| qwen2.5-coder-32b-instruct |
75 |
90.9 |
36.8 |
1.1e+03 |
3.4 |
2.7 |
2.1 |
| qwen2.5-coder-14b-instruct |
74.8 |
93.3 |
36.6 |
1.1e+03 |
3.4 |
2.6 |
2.1 |
| google_gemma_3_12b_it |
72.9 |
85.4 |
34 |
1.1e+03 |
3.5 |
3.3 |
1.1 |
| llama-3.1-70B-instruct |
70.7 |
88.4 |
33 |
1.1e+03 |
3.6 |
2.9 |
2 |
| qwen3-8b |
70.7 |
92.1 |
34.1 |
1.1e+03 |
3.6 |
2.9 |
2.1 |
| qwen3-4b |
69.7 |
89.6 |
32.3 |
1.1e+03 |
3.6 |
3.2 |
1.7 |
| google_gemma_2_27b_it |
66.4 |
86.6 |
29.8 |
1.1e+03 |
3.7 |
3.4 |
1.5 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
65.9 |
92.7 |
29.8 |
8.9e+02 |
3.7 |
2.9 |
2.3 |
| deepseek_r1_distill_qwen_32b |
62.7 |
92.7 |
30.5 |
1.1e+03 |
3.8 |
2.3 |
3 |
| qwen2-math-72b-instruct |
61.7 |
89 |
27.8 |
1.4e+02 |
3.8 |
2.8 |
2.5 |
| google_gemma_3_4b_it |
61 |
77.4 |
27.1 |
1.1e+03 |
3.8 |
3.6 |
1.4 |
| google_gemma_2_9b_it |
55.2 |
79.3 |
23.4 |
1.1e+03 |
3.9 |
3.6 |
1.5 |
| llama-3.1-8B-instruct |
54.8 |
90.2 |
22.9 |
1.1e+03 |
3.9 |
3.1 |
2.4 |
| deepseek_r1_distill_qwen_14b |
51.9 |
92.1 |
24.7 |
1.1e+03 |
3.9 |
2.3 |
3.1 |
| qwen2-7b-instruct |
50.1 |
92.7 |
21.6 |
1.1e+03 |
3.9 |
2.5 |
3 |
| deepseek_r1_distill_llama_70b |
49.9 |
93.9 |
23.6 |
1.1e+03 |
3.9 |
2.3 |
3.2 |
| qwen3-1.7b |
49.8 |
86.6 |
21.2 |
1.1e+03 |
3.9 |
3.3 |
2.1 |
| qwen2-72b-instruct |
48.4 |
93.3 |
22.1 |
1.1e+03 |
3.9 |
2.4 |
3.1 |
| google_codegemma_1.1_7b_it |
47.4 |
84.8 |
18.7 |
1.1e+03 |
3.9 |
3.2 |
2.3 |
| qwen2.5-coder-7b-instruct |
47.4 |
93.9 |
20.8 |
1.1e+03 |
3.9 |
2.3 |
3.2 |
| qwen1.5-14b-chat |
44.7 |
89.6 |
17.7 |
1.1e+03 |
3.9 |
3 |
2.4 |
| qwen2.5-coder-3b-instruct |
44.3 |
92.1 |
19.2 |
1.1e+03 |
3.9 |
2.3 |
3.1 |
| llama-3.2-3B-instruct |
44.2 |
87.2 |
17.4 |
1.1e+03 |
3.9 |
2.9 |
2.5 |
| deepseek_v2_lite_chat |
42.2 |
90.2 |
16.8 |
1.1e+03 |
3.9 |
2.8 |
2.7 |
| qwen1.5-32b-chat |
41.6 |
83.5 |
16.6 |
1.1e+03 |
3.8 |
3.2 |
2.2 |
| mistralai_ministral_8b_instruct_2410 |
40.1 |
92.1 |
16.5 |
1.1e+03 |
3.8 |
2.4 |
3 |
| deepseek_r1_distill_llama_8b |
37.9 |
91.5 |
16.1 |
1.1e+03 |
3.8 |
2.3 |
3 |
| qwen1.5-72b-chat |
36.9 |
84.8 |
14.4 |
1.1e+03 |
3.8 |
3 |
2.3 |
| mistralai_mathstral_7b_v0.1 |
36.3 |
92.1 |
14 |
1.1e+03 |
3.8 |
2.4 |
2.9 |
| google_gemma_3_1b_it |
36.1 |
56.1 |
13.8 |
1.1e+03 |
3.8 |
3.5 |
1.3 |
| qwen2.5-coder-1.5b-instruct |
35.3 |
92.1 |
13.8 |
1.1e+03 |
3.7 |
2.3 |
3 |
| qwen1.5-7b-chat |
33.2 |
84.1 |
12.2 |
1.1e+03 |
3.7 |
2.8 |
2.4 |
| mistralai_mistral_7b_instruct_v0.3 |
31.7 |
87.2 |
11 |
1.1e+03 |
3.6 |
2.8 |
2.3 |
| qwen2.5-coder-0.5b-instruct |
30.7 |
88.4 |
11.8 |
1.1e+03 |
3.6 |
2.2 |
2.8 |
| deepseek_r1_distill_qwen_7b |
28.3 |
92.1 |
11.7 |
1.1e+03 |
3.5 |
2 |
2.9 |
| llama-3.2-1B-instruct |
25.9 |
76.8 |
8.72 |
1.1e+03 |
3.4 |
2.5 |
2.3 |
| mistralai_mistral_7b_instruct_v0.1 |
22.4 |
84.1 |
7.24 |
1.1e+03 |
3.3 |
2.3 |
2.3 |
| qwen3-0.6b |
21.2 |
82.3 |
6.99 |
1.1e+03 |
3.2 |
2.3 |
2.2 |
| google_gemma_7b_it |
20.4 |
65.9 |
6.5 |
1.1e+03 |
3.1 |
2.6 |
1.8 |
| qwen2-1.5b-instruct |
14 |
85.4 |
5.2 |
1.1e+03 |
2.7 |
1.2 |
2.4 |
| google_gemma_2b_it |
13.7 |
45.7 |
3.6 |
1.1e+03 |
2.7 |
2.3 |
1.4 |
| mistralai_mistral_7b_instruct_v0.2 |
7.76 |
69.5 |
2.45 |
1.1e+03 |
2.1 |
1.2 |
1.7 |
| qwen2-0.5b-instruct |
7.41 |
67.7 |
2.12 |
1.1e+03 |
2 |
1.1 |
1.7 |
| qwen1.5-1.8b-chat |
5.42 |
62.2 |
1.52 |
1.1e+03 |
1.8 |
0.93 |
1.5 |
| deepseek_r1_distill_qwen_1.5b |
2.32 |
71.3 |
0.722 |
1.1e+03 |
1.2 |
0.38 |
1.1 |
| qwen1.5-0.5b-chat |
1.79 |
23.8 |
0.302 |
1e+03 |
1 |
0.64 |
0.81 |