| qwen3-32b |
87.5 |
97.6 |
42.9 |
11 |
2.6 |
1.9 |
1.8 |
| google_gemma_3_27b_it |
86.5 |
89.6 |
41.4 |
12 |
2.7 |
2.5 |
0.79 |
| qwen3-14b |
86 |
94.5 |
41.7 |
12 |
2.7 |
2.3 |
1.5 |
| qwen2.5-coder-32b-instruct |
83.3 |
95.7 |
41 |
11 |
2.9 |
1.9 |
2.2 |
| google_gemma_3_12b_it |
82.8 |
87.8 |
38.7 |
11 |
2.9 |
2.7 |
1.1 |
| qwen2.5-coder-14b-instruct |
82.3 |
95.7 |
39.9 |
12 |
3 |
1.9 |
2.3 |
| qwen3-4b |
78.9 |
92.1 |
36.7 |
12 |
3.2 |
2.7 |
1.7 |
| qwen3-8b |
77.6 |
95.1 |
36.6 |
12 |
3.3 |
2.5 |
2.1 |
| google_gemma_2_27b_it |
75.2 |
82.3 |
33.7 |
10 |
3.4 |
3.1 |
1.4 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
74.2 |
90.2 |
33.4 |
11 |
3.4 |
2.6 |
2.2 |
| qwen2-math-72b-instruct |
70.6 |
93.3 |
31.8 |
11 |
3.6 |
2.4 |
2.6 |
| deepseek_r1_distill_qwen_32b |
70.2 |
97.6 |
33.8 |
11 |
3.6 |
1.8 |
3.1 |
| google_gemma_3_4b_it |
69.6 |
77.4 |
30.5 |
13 |
3.6 |
3.3 |
1.4 |
| llama-3.1-8B-instruct |
65.9 |
65.9 |
28 |
15 |
3.7 |
3.7 |
0 |
| google_gemma_2_9b_it |
63.1 |
71.3 |
26.6 |
11 |
3.8 |
3.5 |
1.4 |
| deepseek_r1_distill_qwen_14b |
58.6 |
94.5 |
27.7 |
11 |
3.8 |
2 |
3.3 |
| qwen2-7b-instruct |
57.7 |
92.7 |
24.7 |
11 |
3.9 |
2.3 |
3.1 |
| qwen3-1.7b |
57.1 |
81.7 |
23.9 |
12 |
3.9 |
3.2 |
2.1 |
| google_codegemma_1.1_7b_it |
56.4 |
78.7 |
22.3 |
13 |
3.9 |
3.1 |
2.3 |
| qwen2-72b-instruct |
55 |
95.1 |
25.6 |
11 |
3.9 |
2 |
3.3 |
| deepseek_r1_distill_llama_70b |
54.4 |
93.3 |
25.1 |
11 |
3.9 |
2 |
3.3 |
| qwen2.5-coder-7b-instruct |
54 |
92.7 |
23.5 |
10 |
3.9 |
2.1 |
3.3 |
| qwen1.5-14b-chat |
52.1 |
79.9 |
20.3 |
12 |
3.9 |
3.1 |
2.4 |
| qwen2.5-coder-3b-instruct |
50 |
91.5 |
21.3 |
12 |
3.9 |
2.2 |
3.2 |
| deepseek_v2_lite_chat |
48.8 |
81.7 |
19.2 |
11 |
3.9 |
2.7 |
2.8 |
| qwen1.5-32b-chat |
48.2 |
73.8 |
19.1 |
11 |
3.9 |
3.2 |
2.3 |
| mistralai_ministral_8b_instruct_2410 |
46.1 |
87.8 |
19.2 |
11 |
3.9 |
2.3 |
3.1 |
| llama-3.2-3B-instruct |
45.7 |
45.7 |
16.9 |
17 |
3.9 |
3.9 |
0 |
| mistralai_mathstral_7b_v0.1 |
44 |
82.3 |
17.1 |
11 |
3.9 |
2.3 |
3.1 |
| qwen2.5-coder-1.5b-instruct |
43.1 |
84.8 |
16.6 |
11 |
3.9 |
2.3 |
3.1 |
| deepseek_r1_distill_llama_8b |
42.6 |
88.4 |
18.1 |
13 |
3.9 |
2.2 |
3.2 |
| qwen1.5-72b-chat |
42.6 |
70.1 |
16.6 |
11 |
3.9 |
3 |
2.5 |
| mistralai_mistral_7b_instruct_v0.3 |
41.6 |
67.7 |
14.8 |
11 |
3.8 |
3.1 |
2.2 |
| google_gemma_3_1b_it |
41.3 |
50 |
15.4 |
13 |
3.8 |
3.6 |
1.4 |
| qwen1.5-7b-chat |
39.8 |
69.5 |
14.4 |
12 |
3.8 |
2.9 |
2.4 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
38.7 |
67.1 |
14.9 |
12 |
3.8 |
2.8 |
2.6 |
| qwen2.5-coder-0.5b-instruct |
36.4 |
77.4 |
13.6 |
13 |
3.8 |
2.3 |
3 |
| qwen2-math-7b-instruct |
32.2 |
65.9 |
12.4 |
6 |
3.6 |
2.4 |
2.8 |
| deepseek_r1_distill_qwen_7b |
31.8 |
75.6 |
13 |
11 |
3.6 |
2 |
3 |
| llama-3.2-1B-instruct |
30.5 |
30.5 |
10.6 |
12 |
3.6 |
3.6 |
0 |
| mistralai_mistral_7b_instruct_v0.1 |
28.3 |
63.4 |
9.4 |
11 |
3.5 |
2.4 |
2.6 |
| google_gemma_7b_it |
26.3 |
45.7 |
8.58 |
13 |
3.4 |
2.9 |
1.9 |
| qwen3-0.6b |
25.1 |
56.1 |
8.03 |
13 |
3.4 |
2.5 |
2.3 |
| google_gemma_2b_it |
17 |
31.7 |
4.73 |
13 |
2.9 |
2.4 |
1.6 |
| qwen2-1.5b-instruct |
16.4 |
65.2 |
6.09 |
13 |
2.9 |
1.2 |
2.6 |
| qwen2-0.5b-instruct |
10.3 |
35.4 |
2.82 |
13 |
2.4 |
1.4 |
1.9 |
| mistralai_mistral_7b_instruct_v0.2 |
9.15 |
33.5 |
2.69 |
10 |
2.3 |
1.2 |
1.9 |
| qwen1.5-1.8b-chat |
7.43 |
28 |
2.09 |
11 |
2 |
1.1 |
1.7 |
| qwen2-math-1.5b-instruct |
3.96 |
9.76 |
1.45 |
4 |
1.5 |
0.98 |
1.2 |
| qwen1.5-0.5b-chat |
2.91 |
12.8 |
0.517 |
13 |
1.3 |
0.75 |
1.1 |
| deepseek_r1_distill_qwen_1.5b |
2.67 |
19.5 |
0.804 |
13 |
1.3 |
0.39 |
1.2 |