| google_gemma_3_27b_it |
86.5 |
95.6 |
43.3 |
8 |
1.5 |
1.2 |
0.9 |
| deepseek_r1_distill_qwen_32b |
84.8 |
98.2 |
42.1 |
1.1e+03 |
1.6 |
1.2 |
1.1 |
| qwen3-32b |
82.3 |
98 |
39.9 |
7e+02 |
1.7 |
1.3 |
1.1 |
| qwen3-14b |
82.3 |
97.8 |
39.8 |
1.1e+03 |
1.7 |
1.4 |
1 |
| deepseek_r1_distill_llama_70b |
82.1 |
97.8 |
40.1 |
1.1e+03 |
1.7 |
1.3 |
1.2 |
| qwen2-math-72b-instruct |
81.1 |
94.6 |
38.7 |
35 |
1.7 |
1.5 |
0.98 |
| google_gemma_3_12b_it |
80.2 |
98.4 |
38.3 |
1.1e+03 |
1.8 |
1.5 |
1 |
| qwen3-8b |
79.7 |
98.2 |
37.8 |
1.1e+03 |
1.8 |
1.4 |
1.1 |
| qwen3-4b |
78.2 |
97.8 |
36.8 |
1.1e+03 |
1.8 |
1.5 |
1.1 |
| deepseek_r1_distill_qwen_7b |
78.1 |
98.2 |
37.2 |
1.1e+03 |
1.8 |
1.4 |
1.2 |
| qwen2.5-coder-32b-instruct |
77 |
97.2 |
35.7 |
1.1e+03 |
1.9 |
1.5 |
1.1 |
| qwen2.5-coder-14b-instruct |
72.6 |
98 |
32.7 |
1.1e+03 |
2 |
1.6 |
1.2 |
| deepseek_r1_distill_llama_8b |
70.5 |
95.2 |
32.8 |
71 |
2 |
1.5 |
1.4 |
| deepseek_r1_distill_qwen_1.5b |
68.7 |
98 |
30.7 |
1.1e+03 |
2.1 |
1.5 |
1.4 |
| qwen3-1.7b |
67.9 |
97.6 |
29.9 |
1.1e+03 |
2.1 |
1.6 |
1.3 |
| llama-3.1-70B-instruct |
66.4 |
88.6 |
29.1 |
1e+03 |
2.1 |
1.7 |
1.3 |
| google_gemma_3_4b_it |
65.7 |
97.2 |
29.4 |
1.1e+03 |
2.1 |
1.7 |
1.3 |
| qwen2-72b-instruct |
65.3 |
96.4 |
27.9 |
2.2e+02 |
2.1 |
1.7 |
1.3 |
| qwen2.5-coder-7b-instruct |
62.4 |
96.8 |
26.5 |
1.1e+03 |
2.2 |
1.6 |
1.5 |
| google_gemma_2_27b_it |
53.1 |
93.8 |
20.8 |
1.1e+03 |
2.2 |
1.9 |
1.2 |
| qwen2-7b-instruct |
52.5 |
96.8 |
20.5 |
1.1e+03 |
2.2 |
1.7 |
1.5 |
| mistralai_ministral_8b_instruct_2410 |
49.3 |
97.4 |
19 |
1.1e+03 |
2.2 |
1.6 |
1.5 |
| mistralai_mathstral_7b_v0.1 |
48.5 |
97.8 |
18.6 |
1.1e+03 |
2.2 |
1.6 |
1.5 |
| llama-3.1-8B-instruct |
48.4 |
93.8 |
18.7 |
1.1e+03 |
2.2 |
1.7 |
1.5 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
47.8 |
91.8 |
18.4 |
1e+02 |
2.2 |
1.6 |
1.5 |
| qwen2.5-coder-3b-instruct |
47.4 |
97.2 |
18.7 |
1.1e+03 |
2.2 |
1.5 |
1.7 |
| google_gemma_2_9b_it |
47.4 |
90.6 |
17.6 |
1.1e+03 |
2.2 |
1.9 |
1.2 |
| llama-3.2-3B-instruct |
44.5 |
91.8 |
16.7 |
1.1e+03 |
2.2 |
1.7 |
1.4 |
| qwen1.5-72b-chat |
40.6 |
93.4 |
14.9 |
3.9e+02 |
2.2 |
1.6 |
1.5 |
| qwen1.5-32b-chat |
39.9 |
82.2 |
14.6 |
30 |
2.2 |
1.6 |
1.5 |
| qwen3-0.6b |
33.4 |
95 |
12.1 |
1.1e+03 |
2.1 |
1.4 |
1.5 |
| qwen2.5-coder-1.5b-instruct |
33.1 |
95.6 |
11.7 |
1.1e+03 |
2.1 |
1.4 |
1.6 |
| qwen1.5-14b-chat |
30.9 |
95.2 |
10.4 |
1.1e+03 |
2.1 |
1.5 |
1.5 |
| llama-3.2-1B-instruct |
26.6 |
87.8 |
8.92 |
1.1e+03 |
2 |
1.4 |
1.4 |
| google_codegemma_1.1_7b_it |
21.9 |
91.2 |
7.04 |
1.1e+03 |
1.9 |
1.3 |
1.3 |
| deepseek_v2_lite_chat |
21.4 |
93.8 |
6.98 |
1.1e+03 |
1.8 |
1.1 |
1.4 |
| qwen1.5-7b-chat |
17 |
92.2 |
5.27 |
1.1e+03 |
1.7 |
1.1 |
1.3 |
| google_gemma_3_1b_it |
14.5 |
86.6 |
6.01 |
1.1e+03 |
1.6 |
1 |
1.2 |
| mistralai_mistral_7b_instruct_v0.3 |
13.9 |
91.4 |
4.34 |
1.1e+03 |
1.5 |
0.97 |
1.2 |
| mistralai_mistral_7b_instruct_v0.2 |
10.4 |
86 |
3.22 |
9.2e+02 |
1.4 |
0.79 |
1.1 |
| qwen2.5-coder-0.5b-instruct |
8.66 |
87.4 |
2.77 |
1.1e+03 |
1.3 |
0.68 |
1.1 |
| qwen2-1.5b-instruct |
7.18 |
89.4 |
2.17 |
1.1e+03 |
1.2 |
0.51 |
1 |
| mistralai_mistral_7b_instruct_v0.1 |
6.04 |
83.6 |
1.88 |
1.1e+03 |
1.1 |
0.48 |
0.95 |
| google_gemma_7b_it |
5.78 |
64.8 |
1.72 |
1.1e+03 |
1 |
0.68 |
0.79 |
| qwen2-0.5b-instruct |
3.34 |
83.2 |
1.13 |
1.1e+03 |
0.8 |
0.28 |
0.75 |
| qwen1.5-1.8b-chat |
1.53 |
73.8 |
0.539 |
1.1e+03 |
0.55 |
0.14 |
0.53 |
| qwen1.5-0.5b-chat |
0.92 |
64.8 |
0.386 |
8.9e+02 |
0.43 |
0.089 |
0.42 |
| google_gemma_2b_it |
0.196 |
26.6 |
0.0683 |
1.1e+03 |
0.2 |
0.041 |
0.19 |