| qwen2-math-72b-instruct |
78.3 |
92 |
43.7 |
11 |
4.8 |
3.7 |
3 |
| qwen2-72b-instruct |
77.3 |
82.7 |
43.2 |
11 |
4.8 |
4.6 |
1.6 |
| google_gemma_3_27b_it |
74.4 |
89.3 |
42.2 |
12 |
5 |
3.9 |
3.1 |
| qwen3-8b |
72 |
90.7 |
39.2 |
12 |
5.2 |
4.3 |
2.9 |
| qwen3-4b |
71.9 |
89.3 |
39.7 |
12 |
5.2 |
4.1 |
3.2 |
| qwen3-14b |
71.1 |
81.3 |
38.7 |
12 |
5.2 |
4.6 |
2.5 |
| qwen3-32b |
67.9 |
89.3 |
37.6 |
11 |
5.4 |
4.1 |
3.5 |
| qwen2.5-coder-32b-instruct |
62.4 |
86.7 |
33.2 |
11 |
5.6 |
4.3 |
3.6 |
| qwen1.5-72b-chat |
60.1 |
76 |
32.3 |
11 |
5.7 |
5.1 |
2.5 |
| google_gemma_2_27b_it |
59.2 |
85.3 |
32.3 |
10 |
5.7 |
3.6 |
4.4 |
| qwen1.5-32b-chat |
58.4 |
70.7 |
29.9 |
11 |
5.7 |
5.1 |
2.5 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
58.1 |
80 |
29.8 |
11 |
5.7 |
4.5 |
3.5 |
| qwen2.5-coder-14b-instruct |
56.2 |
78.7 |
28.6 |
12 |
5.7 |
4.7 |
3.3 |
| qwen2.5-coder-7b-instruct |
55.2 |
78.7 |
28.5 |
10 |
5.7 |
4.3 |
3.8 |
| google_gemma_3_12b_it |
54.3 |
78.7 |
28.6 |
11 |
5.8 |
4.4 |
3.7 |
| qwen1.5-14b-chat |
52.7 |
77.3 |
26.5 |
12 |
5.8 |
4.6 |
3.5 |
| qwen2-math-7b-instruct |
51.8 |
66.7 |
26.8 |
6 |
5.8 |
4.7 |
3.3 |
| qwen3-1.7b |
48.2 |
77.3 |
24.2 |
12 |
5.8 |
4.3 |
3.8 |
| qwen1.5-7b-chat |
46.3 |
72 |
24.1 |
12 |
5.8 |
4.8 |
3.2 |
| qwen2-7b-instruct |
46.1 |
72 |
23.2 |
11 |
5.8 |
4.6 |
3.5 |
| mistralai_mathstral_7b_v0.1 |
45.6 |
81.3 |
23.3 |
11 |
5.8 |
4.1 |
4 |
| mistralai_mistral_7b_instruct_v0.3 |
41 |
60 |
19.5 |
11 |
5.7 |
4.9 |
2.8 |
| qwen3-0.6b |
39.8 |
68 |
19.9 |
13 |
5.7 |
4.5 |
3.4 |
| deepseek_v2_lite_chat |
39.2 |
74.7 |
19.9 |
11 |
5.6 |
3.7 |
4.3 |
| google_gemma_2_9b_it |
38.8 |
73.3 |
20 |
11 |
5.6 |
3.8 |
4.1 |
| mistralai_ministral_8b_instruct_2410 |
38.3 |
84 |
18.9 |
11 |
5.6 |
3.3 |
4.5 |
| qwen2-math-1.5b-instruct |
37.3 |
60 |
19.6 |
4 |
5.6 |
4 |
3.9 |
| llama-3.2-3B-instruct |
37.3 |
37.3 |
17.5 |
17 |
5.6 |
5.6 |
0 |
| llama-3.1-8B-instruct |
37.3 |
37.3 |
17.9 |
15 |
5.6 |
5.6 |
0 |
| google_gemma_3_4b_it |
37 |
61.3 |
19.2 |
13 |
5.6 |
4.4 |
3.4 |
| qwen2.5-coder-3b-instruct |
35.3 |
86.7 |
17.6 |
12 |
5.5 |
3.2 |
4.5 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
29.8 |
69.3 |
15.2 |
12 |
5.3 |
3.4 |
4 |
| qwen2.5-coder-1.5b-instruct |
25.6 |
92 |
13.8 |
11 |
5 |
1.3 |
4.9 |
| google_gemma_7b_it |
24.4 |
41.3 |
11.3 |
13 |
5 |
4.1 |
2.8 |
| qwen2-1.5b-instruct |
24.3 |
76 |
12.3 |
13 |
5 |
2.9 |
4 |
| mistralai_mistral_7b_instruct_v0.2 |
24 |
46.7 |
10.8 |
10 |
4.9 |
3.6 |
3.4 |
| google_codegemma_1.1_7b_it |
23.4 |
60 |
11.4 |
13 |
4.9 |
3.3 |
3.6 |
| mistralai_mistral_7b_instruct_v0.1 |
20 |
76 |
10.2 |
11 |
4.6 |
2.3 |
4 |
| qwen1.5-0.5b-chat |
19.5 |
82.7 |
11.4 |
13 |
4.6 |
1.2 |
4.4 |
| llama-3.2-1B-instruct |
18.7 |
18.7 |
9.57 |
12 |
4.5 |
4.5 |
0 |
| qwen1.5-1.8b-chat |
18.3 |
77.3 |
9.79 |
11 |
4.5 |
1.5 |
4.2 |
| qwen2.5-coder-0.5b-instruct |
18.3 |
84 |
11.1 |
13 |
4.5 |
1.1 |
4.3 |
| deepseek_r1_distill_llama_70b |
18.2 |
53.3 |
8.64 |
11 |
4.5 |
2.5 |
3.7 |
| qwen2-0.5b-instruct |
18.2 |
80 |
10.6 |
13 |
4.5 |
1.2 |
4.3 |
| google_gemma_3_1b_it |
17.9 |
48 |
11.2 |
13 |
4.4 |
3.2 |
3.1 |
| google_gemma_2b_it |
17.1 |
45.3 |
9.38 |
13 |
4.4 |
3.2 |
2.9 |
| deepseek_r1_distill_qwen_14b |
14.7 |
53.3 |
6.69 |
11 |
4.1 |
1.9 |
3.6 |
| deepseek_r1_distill_qwen_32b |
12.8 |
52 |
5.98 |
11 |
3.9 |
1.6 |
3.5 |
| deepseek_r1_distill_llama_8b |
11.3 |
46.7 |
4.77 |
13 |
3.7 |
1.8 |
3.2 |
| deepseek_r1_distill_qwen_7b |
6.79 |
38.7 |
3.09 |
11 |
2.9 |
0.9 |
2.8 |
| deepseek_r1_distill_qwen_1.5b |
4 |
34.7 |
1.7 |
13 |
2.3 |
0.49 |
2.2 |