| qwen3-14b |
77.2 |
84.1 |
44.4 |
3 |
3.3 |
2.8 |
1.7 |
| google_gemma_3_27b_it |
75 |
78.7 |
41.8 |
3 |
3.4 |
3.2 |
1.2 |
| qwen2.5-coder-32b-instruct |
74.1 |
82.9 |
42.6 |
2 |
3.4 |
2.5 |
2.3 |
| qwen3-32b |
73.4 |
83.5 |
41.7 |
3 |
3.5 |
2.6 |
2.3 |
| google_gemma_3_12b_it |
72.9 |
76.8 |
40.2 |
4 |
3.5 |
3.3 |
1.2 |
| qwen3-4b |
69.4 |
78.7 |
38.1 |
4 |
3.6 |
3.1 |
1.8 |
| qwen3-8b |
68.9 |
81.7 |
38.7 |
3 |
3.6 |
2.8 |
2.3 |
| qwen2.5-coder-14b-instruct |
68.1 |
85.4 |
38.7 |
3 |
3.6 |
2.3 |
2.9 |
| google_gemma_2_27b_it |
66.8 |
72 |
35.9 |
2 |
3.7 |
3.2 |
1.8 |
| google_gemma_3_4b_it |
60.9 |
67.1 |
32.1 |
5 |
3.8 |
3.5 |
1.5 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
60 |
76.2 |
31.4 |
3 |
3.8 |
2.7 |
2.7 |
| google_gemma_2_9b_it |
56.1 |
65.2 |
29 |
4 |
3.9 |
3.5 |
1.7 |
| llama-3.1-8B-instruct |
50.6 |
50.6 |
24.8 |
7 |
3.9 |
3.9 |
0 |
| qwen3-1.7b |
50.5 |
67.1 |
25.6 |
4 |
3.9 |
3.2 |
2.2 |
| deepseek_r1_distill_qwen_32b |
47 |
67.7 |
25.4 |
2 |
3.9 |
1.6 |
3.6 |
| qwen2-math-72b-instruct |
45.7 |
61.6 |
24.4 |
2 |
3.9 |
2.3 |
3.1 |
| google_codegemma_1.1_7b_it |
44.9 |
64 |
21.4 |
5 |
3.9 |
3.1 |
2.4 |
| qwen2-72b-instruct |
43.3 |
62.8 |
23.2 |
2 |
3.9 |
1.8 |
3.4 |
| deepseek_r1_distill_qwen_14b |
43.1 |
76.2 |
23.8 |
4 |
3.9 |
1.8 |
3.4 |
| deepseek_r1_distill_llama_70b |
43 |
61 |
24.1 |
2 |
3.9 |
2 |
3.3 |
| qwen1.5-14b-chat |
42.3 |
59.8 |
19.9 |
3 |
3.9 |
2.9 |
2.5 |
| qwen1.5-32b-chat |
41.5 |
57.9 |
20.7 |
3 |
3.8 |
2.8 |
2.6 |
| deepseek_v2_lite_chat |
36.2 |
54.3 |
17 |
3 |
3.8 |
2.6 |
2.7 |
| qwen2-7b-instruct |
35.5 |
67.1 |
17.9 |
4 |
3.7 |
1.9 |
3.2 |
| google_gemma_3_1b_it |
35.5 |
39 |
16.4 |
4 |
3.7 |
3.5 |
1.3 |
| qwen2.5-coder-7b-instruct |
35.4 |
66.5 |
17.5 |
4 |
3.7 |
2.1 |
3.1 |
| qwen1.5-72b-chat |
34.1 |
46.3 |
16.1 |
2 |
3.7 |
2.5 |
2.7 |
| qwen2.5-coder-3b-instruct |
33.7 |
67.1 |
17.4 |
4 |
3.7 |
1.8 |
3.2 |
| llama-3.2-3B-instruct |
33.5 |
33.5 |
15.1 |
10 |
3.7 |
3.7 |
0 |
| mistralai_ministral_8b_instruct_2410 |
32 |
63.4 |
15.7 |
4 |
3.6 |
1.9 |
3.1 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
30.3 |
45.1 |
14.2 |
3 |
3.6 |
2.7 |
2.4 |
| mistralai_mistral_7b_instruct_v0.3 |
30.2 |
52.4 |
13.2 |
4 |
3.6 |
2.6 |
2.5 |
| qwen1.5-7b-chat |
29.7 |
45.7 |
13.3 |
3 |
3.6 |
2.5 |
2.5 |
| deepseek_r1_distill_llama_8b |
24.4 |
55.5 |
12.2 |
4 |
3.4 |
1.6 |
2.9 |
| mistralai_mathstral_7b_v0.1 |
23.8 |
49.4 |
10.4 |
4 |
3.3 |
1.8 |
2.8 |
| qwen2-math-7b-instruct |
23.5 |
34.1 |
10.9 |
2 |
3.3 |
2.1 |
2.6 |
| qwen2.5-coder-1.5b-instruct |
22.4 |
50.6 |
10.3 |
4 |
3.3 |
1.6 |
2.8 |
| deepseek_r1_distill_qwen_7b |
20.7 |
48.8 |
10.2 |
4 |
3.2 |
1.5 |
2.8 |
| google_gemma_7b_it |
20.4 |
32.3 |
8.83 |
4 |
3.1 |
2.5 |
1.9 |
| llama-3.2-1B-instruct |
20.1 |
20.1 |
8.17 |
13 |
3.1 |
3.1 |
0 |
| qwen2.5-coder-0.5b-instruct |
18.4 |
45.7 |
8.18 |
5 |
3 |
1.4 |
2.7 |
| qwen3-0.6b |
17.1 |
39.6 |
7.15 |
5 |
2.9 |
1.9 |
2.3 |
| mistralai_mistral_7b_instruct_v0.1 |
13.6 |
29.9 |
5.29 |
4 |
2.7 |
1.5 |
2.2 |
| google_gemma_2b_it |
13.3 |
20.7 |
4.63 |
4 |
2.6 |
2.2 |
1.5 |
| mistralai_mistral_7b_instruct_v0.2 |
7.93 |
20.1 |
2.95 |
4 |
2.1 |
1.1 |
1.8 |
| qwen2-1.5b-instruct |
5.79 |
18.9 |
2.42 |
4 |
1.8 |
0.54 |
1.7 |
| qwen1.5-1.8b-chat |
3.66 |
7.93 |
1.27 |
3 |
1.5 |
0.73 |
1.3 |
| qwen2-0.5b-instruct |
2.68 |
8.54 |
0.851 |
5 |
1.3 |
0.57 |
1.1 |
| qwen2-math-1.5b-instruct |
1.63 |
3.05 |
0.621 |
3 |
0.99 |
0.69 |
0.7 |
| qwen1.5-0.5b-chat |
1.22 |
3.66 |
0.356 |
5 |
0.86 |
0.42 |
0.75 |
| deepseek_r1_distill_qwen_1.5b |
0.457 |
1.83 |
0.162 |
4 |
0.53 |
0 |
0.53 |