| qwen2.5-coder-32b-instruct |
81.5 |
87 |
48.5 |
2 |
1.4 |
1.1 |
0.83 |
| qwen2.5-coder-14b-instruct |
76.2 |
85.6 |
43.9 |
3 |
1.5 |
1.2 |
0.92 |
| qwen3-14b |
76.2 |
86.1 |
44 |
3 |
1.5 |
1.2 |
0.92 |
| google_gemma_3_27b_it |
75.9 |
83.9 |
43.6 |
3 |
1.5 |
1.3 |
0.82 |
| google_gemma_3_12b_it |
69.4 |
81.6 |
38.6 |
4 |
1.6 |
1.3 |
0.92 |
| qwen3-32b |
66.9 |
74.6 |
37.1 |
2 |
1.7 |
1.3 |
0.98 |
| llama-3.1-70B-instruct |
65.4 |
65.4 |
35.4 |
4 |
1.7 |
1.7 |
0 |
| qwen2-72b-instruct |
60.4 |
72.8 |
32.1 |
2 |
1.7 |
1.2 |
1.2 |
| google_gemma_2_27b_it |
59.9 |
68.9 |
31.6 |
2 |
1.7 |
1.4 |
1.1 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
57.2 |
67.5 |
29.5 |
2 |
1.7 |
1.3 |
1.1 |
| qwen3-4b |
56.9 |
72.8 |
29.6 |
4 |
1.8 |
1.4 |
1.1 |
| deepseek_r1_distill_llama_70b |
55.4 |
67.2 |
29 |
2 |
1.8 |
1.3 |
1.2 |
| google_gemma_3_4b_it |
54.9 |
71.6 |
28 |
5 |
1.8 |
1.4 |
1 |
| qwen2.5-coder-7b-instruct |
50.9 |
69.5 |
25.4 |
4 |
1.8 |
1.4 |
1.1 |
| google_gemma_2_9b_it |
46.9 |
59.5 |
22.5 |
3 |
1.8 |
1.4 |
1 |
| deepseek_r1_distill_qwen_14b |
45.9 |
74 |
24.1 |
4 |
1.8 |
1 |
1.5 |
| qwen1.5-72b-chat |
45.9 |
58 |
22.3 |
2 |
1.8 |
1.3 |
1.2 |
| qwen1.5-32b-chat |
44.9 |
56.5 |
21.5 |
2 |
1.8 |
1.3 |
1.2 |
| qwen2.5-coder-3b-instruct |
44.5 |
65.8 |
21.3 |
4 |
1.8 |
1.3 |
1.2 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
41.4 |
59.8 |
19.6 |
3 |
1.7 |
1.2 |
1.2 |
| deepseek_r1_distill_llama_8b |
39.3 |
62.4 |
18.9 |
4 |
1.7 |
1.2 |
1.3 |
| mistralai_ministral_8b_instruct_2410 |
39.2 |
60.5 |
17.8 |
4 |
1.7 |
1.2 |
1.2 |
| google_codegemma_1.1_7b_it |
36.2 |
58 |
16.5 |
5 |
1.7 |
1.3 |
1.1 |
| llama-3.1-8B-instruct |
34.6 |
34.6 |
16 |
7 |
1.7 |
1.7 |
0 |
| mistralai_mathstral_7b_v0.1 |
34.4 |
56.6 |
15.4 |
4 |
1.7 |
1.2 |
1.2 |
| qwen1.5-14b-chat |
33.7 |
50.5 |
14.9 |
3 |
1.7 |
1.2 |
1.2 |
| qwen2-math-72b-instruct |
33.2 |
48.6 |
16.2 |
2 |
1.7 |
0.92 |
1.4 |
| qwen2-7b-instruct |
32.4 |
55.5 |
14.4 |
4 |
1.7 |
1.1 |
1.2 |
| qwen3-1.7b |
31.5 |
60.5 |
15.6 |
4 |
1.6 |
0.88 |
1.4 |
| mistralai_mistral_7b_instruct_v0.3 |
31.3 |
52.1 |
13.7 |
4 |
1.6 |
1.2 |
1.2 |
| deepseek_r1_distill_qwen_32b |
27.7 |
42.9 |
13.4 |
2 |
1.6 |
0.78 |
1.4 |
| google_gemma_3_1b_it |
26.8 |
43.9 |
12 |
4 |
1.6 |
1.2 |
1.1 |
| qwen3-8b |
25.9 |
43.9 |
11.6 |
3 |
1.5 |
0.99 |
1.2 |
| qwen3-0.6b |
25 |
51.4 |
11.2 |
5 |
1.5 |
0.92 |
1.2 |
| qwen1.5-7b-chat |
24.8 |
40.5 |
10.6 |
3 |
1.5 |
1 |
1.1 |
| google_gemma_7b_it |
24.7 |
39.1 |
10.8 |
4 |
1.5 |
1.1 |
1 |
| deepseek_v2_lite_chat |
24.4 |
41.5 |
10.5 |
3 |
1.5 |
0.97 |
1.2 |
| llama-3.2-3B-instruct |
20.6 |
20.6 |
8.53 |
10 |
1.4 |
1.4 |
0 |
| qwen2.5-coder-1.5b-instruct |
19.9 |
43.5 |
8.58 |
4 |
1.4 |
0.75 |
1.2 |
| mistralai_mistral_7b_instruct_v0.1 |
17.9 |
38.5 |
7.62 |
4 |
1.4 |
0.78 |
1.1 |
| qwen2.5-coder-0.5b-instruct |
16.8 |
40.2 |
7.28 |
5 |
1.3 |
0.75 |
1.1 |
| mistralai_mistral_7b_instruct_v0.2 |
16.1 |
38.1 |
7.01 |
4 |
1.3 |
0.63 |
1.1 |
| deepseek_r1_distill_qwen_7b |
12.2 |
33.5 |
5.32 |
4 |
1.2 |
0.45 |
1.1 |
| google_gemma_2b_it |
9.59 |
23.1 |
4.29 |
4 |
1 |
0.57 |
0.87 |
| qwen2-math-1.5b-instruct |
8.41 |
23.8 |
3.45 |
4 |
0.98 |
0.39 |
0.9 |
| llama-3.2-1B-instruct |
7.62 |
7.62 |
3.05 |
13 |
0.94 |
0.94 |
0 |
| qwen2-1.5b-instruct |
5.75 |
16.4 |
2.29 |
4 |
0.82 |
0.35 |
0.74 |
| deepseek_r1_distill_qwen_1.5b |
5.59 |
18.2 |
2.26 |
4 |
0.81 |
0.22 |
0.78 |
| qwen2-math-7b-instruct |
5.5 |
18.2 |
2.34 |
4 |
0.81 |
0.21 |
0.78 |
| qwen1.5-0.5b-chat |
1.73 |
7.12 |
0.798 |
5 |
0.46 |
0.13 |
0.44 |
| qwen2-0.5b-instruct |
0.525 |
2.62 |
0.264 |
5 |
0.26 |
0 |
0.26 |
| qwen1.5-1.8b-chat |
0.375 |
1 |
0.171 |
3 |
0.22 |
0.071 |
0.2 |