| qwen3-32b |
92 |
95.7 |
42.1 |
3 |
2.8 |
2.1 |
1.9 |
| qwen3-14b |
90.2 |
95.7 |
40.6 |
3 |
3.1 |
2.2 |
2.2 |
| qwen3-8b |
86.2 |
94.6 |
38.5 |
3 |
3.6 |
2.5 |
2.6 |
| qwen2.5-coder-32b-instruct |
85.9 |
90.2 |
37.7 |
2 |
3.6 |
2.9 |
2.2 |
| google_gemma_3_27b_it |
83.3 |
88 |
35.6 |
3 |
3.9 |
3.5 |
1.8 |
| qwen2-72b-instruct |
82.1 |
90.2 |
36.1 |
2 |
4 |
2.7 |
3 |
| deepseek_r1_distill_qwen_32b |
81.5 |
88 |
36.4 |
2 |
4 |
3 |
2.7 |
| qwen3-4b |
81.2 |
92.4 |
35 |
4 |
4.1 |
3 |
2.8 |
| deepseek_r1_distill_llama_70b |
81 |
84.8 |
35.3 |
2 |
4.1 |
3.6 |
2 |
| google_gemma_3_12b_it |
78.8 |
89.1 |
33.4 |
4 |
4.3 |
3.4 |
2.5 |
| deepseek_r1_distill_qwen_14b |
78.5 |
87 |
34 |
4 |
4.3 |
3.5 |
2.5 |
| google_gemma_2_27b_it |
78.3 |
85.9 |
33.3 |
2 |
4.3 |
3.2 |
2.9 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
77.5 |
91.3 |
33.7 |
3 |
4.4 |
2.7 |
3.4 |
| qwen2.5-coder-14b-instruct |
76.1 |
89.1 |
32 |
3 |
4.4 |
3 |
3.3 |
| google_gemma_2_9b_it |
72.3 |
85.9 |
30.2 |
4 |
4.7 |
3.6 |
3 |
| qwen1.5-72b-chat |
66.8 |
80.4 |
28.2 |
2 |
4.9 |
3.1 |
3.8 |
| qwen1.5-32b-chat |
66.3 |
84.8 |
27.2 |
3 |
4.9 |
3.3 |
3.7 |
| qwen2-math-72b-instruct |
64.7 |
83.7 |
28 |
2 |
5 |
2 |
4.5 |
| google_gemma_3_4b_it |
64.1 |
82.6 |
26.1 |
5 |
5 |
3.7 |
3.4 |
| qwen2.5-coder-7b-instruct |
63 |
91.3 |
26 |
4 |
5 |
3 |
4.1 |
| qwen3-1.7b |
61.7 |
84.8 |
25.2 |
4 |
5.1 |
3.3 |
3.9 |
| deepseek_r1_distill_qwen_7b |
61.7 |
78.3 |
25.7 |
4 |
5.1 |
3.8 |
3.4 |
| deepseek_r1_distill_llama_8b |
59.2 |
79.3 |
23.3 |
4 |
5.1 |
3.6 |
3.6 |
| llama-3.1-8B-instruct |
58.7 |
58.7 |
24.7 |
7 |
5.1 |
5.1 |
0 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
54.7 |
79.3 |
22.6 |
3 |
5.2 |
3.2 |
4.1 |
| qwen2-math-7b-instruct |
54.3 |
70.7 |
22.8 |
2 |
5.2 |
3 |
4.2 |
| qwen1.5-14b-chat |
53.3 |
76.1 |
21.3 |
3 |
5.2 |
3.2 |
4.1 |
| qwen2-7b-instruct |
50.8 |
81.5 |
20 |
4 |
5.2 |
2.9 |
4.3 |
| mistralai_mathstral_7b_v0.1 |
50.5 |
83.7 |
19.7 |
4 |
5.2 |
2.9 |
4.3 |
| mistralai_ministral_8b_instruct_2410 |
50.5 |
76.1 |
19.3 |
4 |
5.2 |
3.3 |
4 |
| mistralai_mistral_7b_instruct_v0.3 |
46.5 |
77.2 |
18 |
4 |
5.2 |
3.1 |
4.2 |
| qwen3-0.6b |
43.3 |
72.8 |
17.2 |
5 |
5.2 |
3.4 |
3.9 |
| qwen2.5-coder-3b-instruct |
39.7 |
76.1 |
15.7 |
4 |
5.1 |
2.4 |
4.5 |
| deepseek_v2_lite_chat |
39.5 |
62 |
15.4 |
3 |
5.1 |
3.1 |
4 |
| mistralai_mistral_7b_instruct_v0.2 |
39.4 |
64.1 |
16 |
4 |
5.1 |
3.3 |
3.9 |
| llama-3.2-3B-instruct |
38 |
38 |
16.2 |
10 |
5.1 |
5.1 |
0 |
| qwen1.5-7b-chat |
38 |
63 |
15.1 |
3 |
5.1 |
2.8 |
4.2 |
| google_gemma_7b_it |
35.9 |
63 |
14.1 |
4 |
5 |
3.2 |
3.9 |
| google_codegemma_1.1_7b_it |
33.7 |
69.6 |
12.7 |
5 |
4.9 |
2.6 |
4.2 |
| google_gemma_2b_it |
32.1 |
40.2 |
11.8 |
4 |
4.9 |
4.3 |
2.3 |
| mistralai_mistral_7b_instruct_v0.1 |
30.7 |
68.5 |
12.5 |
4 |
4.8 |
1.8 |
4.5 |
| google_gemma_3_1b_it |
29.9 |
58.7 |
11.7 |
4 |
4.8 |
2.8 |
3.8 |
| deepseek_r1_distill_qwen_1.5b |
26.4 |
52.2 |
10.2 |
4 |
4.6 |
2.5 |
3.8 |
| qwen2-1.5b-instruct |
26.4 |
59.8 |
10.8 |
4 |
4.6 |
1.9 |
4.2 |
| qwen2.5-coder-1.5b-instruct |
25.5 |
62 |
10.6 |
4 |
4.5 |
1.7 |
4.2 |
| llama-3.2-1B-instruct |
20.7 |
20.7 |
7.9 |
13 |
4.2 |
4.2 |
0 |
| qwen2.5-coder-0.5b-instruct |
12.6 |
47.8 |
5.66 |
5 |
3.5 |
0.53 |
3.4 |
| qwen2-0.5b-instruct |
12.2 |
46.7 |
5.53 |
5 |
3.4 |
0.53 |
3.4 |
| qwen1.5-1.8b-chat |
12 |
31.5 |
5.1 |
3 |
3.4 |
0.15 |
3.4 |
| qwen2-math-1.5b-instruct |
6.52 |
16.3 |
2.87 |
3 |
2.6 |
1.1 |
2.3 |
| qwen1.5-0.5b-chat |
5.65 |
25 |
2.64 |
5 |
2.4 |
0.085 |
2.4 |