| qwen3-32b |
92 |
94.2 |
33.7 |
2 |
1 |
0.85 |
0.56 |
| qwen3-14b |
89.7 |
92.8 |
32.1 |
3 |
1.1 |
0.98 |
0.57 |
| google_gemma_3_27b_it |
88.7 |
92.5 |
31.6 |
3 |
1.2 |
0.99 |
0.65 |
| qwen2-72b-instruct |
88.7 |
92 |
31.6 |
2 |
1.2 |
0.97 |
0.67 |
| llama-3.1-70B-instruct |
87.8 |
87.8 |
31.2 |
4 |
1.2 |
1.2 |
0 |
| deepseek_r1_distill_llama_70b |
87.4 |
91.8 |
31 |
2 |
1.2 |
0.96 |
0.79 |
| qwen3-8b |
87.1 |
93 |
30.5 |
3 |
1.3 |
1 |
0.75 |
| qwen2.5-coder-32b-instruct |
85.8 |
90.4 |
29.6 |
2 |
1.3 |
1 |
0.81 |
| google_gemma_3_12b_it |
85 |
89.3 |
29 |
3 |
1.3 |
1.2 |
0.64 |
| google_gemma_2_27b_it |
83.9 |
88.5 |
28.7 |
2 |
1.4 |
1.1 |
0.8 |
| qwen3-4b |
83.4 |
90.3 |
28.8 |
4 |
1.4 |
1.2 |
0.74 |
| deepseek_r1_distill_qwen_32b |
82.8 |
88.6 |
28.6 |
2 |
1.4 |
1.1 |
0.9 |
| deepseek_r1_distill_qwen_14b |
82.4 |
91.8 |
27.9 |
4 |
1.4 |
1.1 |
0.9 |
| qwen1.5-72b-chat |
81.9 |
88.7 |
27.5 |
2 |
1.4 |
1.1 |
0.98 |
| google_gemma_2_9b_it |
80.1 |
87.1 |
26.4 |
3 |
1.5 |
1.2 |
0.84 |
| qwen2.5-coder-14b-instruct |
79.1 |
91 |
26.2 |
3 |
1.5 |
1.1 |
1.1 |
| qwen1.5-32b-chat |
79 |
85.7 |
26 |
2 |
1.5 |
1.2 |
0.96 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
77.4 |
87.1 |
27 |
2 |
1.6 |
1.1 |
1.2 |
| qwen2-math-72b-instruct |
75.1 |
86.8 |
25.2 |
2 |
1.6 |
0.99 |
1.3 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
72.1 |
84.7 |
23 |
3 |
1.7 |
1.3 |
1.1 |
| qwen3-1.7b |
71.4 |
83.8 |
23 |
4 |
1.7 |
1.4 |
0.99 |
| qwen1.5-14b-chat |
69.9 |
80.3 |
21.7 |
3 |
1.7 |
1.4 |
1 |
| llama-3.1-8B-instruct |
69.1 |
69.1 |
21.2 |
7 |
1.7 |
1.7 |
0 |
| qwen2-7b-instruct |
68.6 |
88.6 |
21.5 |
4 |
1.7 |
1.2 |
1.3 |
| google_gemma_3_4b_it |
68.3 |
83.3 |
21.4 |
5 |
1.7 |
1.4 |
1 |
| qwen2.5-coder-7b-instruct |
67 |
87.5 |
21 |
4 |
1.8 |
1.2 |
1.3 |
| mistralai_ministral_8b_instruct_2410 |
66.5 |
85.1 |
20.6 |
3 |
1.8 |
1.1 |
1.4 |
| deepseek_r1_distill_llama_8b |
60.7 |
85.1 |
19 |
4 |
1.8 |
1.1 |
1.5 |
| mistralai_mistral_7b_instruct_v0.3 |
59.9 |
79 |
18.1 |
4 |
1.8 |
1.3 |
1.3 |
| qwen1.5-7b-chat |
59.8 |
76.7 |
17.8 |
3 |
1.8 |
1.4 |
1.2 |
| qwen2-math-7b-instruct |
58.7 |
85 |
18.9 |
4 |
1.8 |
1.2 |
1.4 |
| llama-3.2-3B-instruct |
58.5 |
58.5 |
17.6 |
10 |
1.8 |
1.8 |
0 |
| deepseek_v2_lite_chat |
54.6 |
66.9 |
16.3 |
2 |
1.9 |
1.3 |
1.3 |
| mistralai_mathstral_7b_v0.1 |
52.9 |
81.9 |
15.9 |
4 |
1.9 |
1.1 |
1.5 |
| google_codegemma_1.1_7b_it |
52.3 |
76.2 |
15.5 |
5 |
1.9 |
1.4 |
1.3 |
| mistralai_mistral_7b_instruct_v0.2 |
52.2 |
74 |
15.4 |
4 |
1.9 |
1.3 |
1.3 |
| qwen2.5-coder-3b-instruct |
51.8 |
82.1 |
15.9 |
4 |
1.9 |
1.1 |
1.5 |
| deepseek_r1_distill_qwen_7b |
49.4 |
76.4 |
14.8 |
4 |
1.9 |
1.2 |
1.5 |
| google_gemma_7b_it |
47.9 |
67.7 |
14.4 |
4 |
1.9 |
1.4 |
1.3 |
| qwen3-0.6b |
47.2 |
76.8 |
14.4 |
5 |
1.9 |
1.3 |
1.4 |
| mistralai_mistral_7b_instruct_v0.1 |
41.7 |
72 |
12 |
4 |
1.8 |
1.1 |
1.5 |
| google_gemma_3_1b_it |
34.8 |
58.9 |
10.1 |
4 |
1.8 |
1.2 |
1.3 |
| google_gemma_2b_it |
32.2 |
45.4 |
9.9 |
4 |
1.8 |
1.4 |
0.99 |
| qwen2-1.5b-instruct |
31.2 |
62.6 |
9.15 |
4 |
1.7 |
0.99 |
1.4 |
| qwen2.5-coder-1.5b-instruct |
31.1 |
68.8 |
9.98 |
4 |
1.7 |
0.69 |
1.6 |
| llama-3.2-1B-instruct |
29.3 |
29.3 |
8.74 |
13 |
1.7 |
1.7 |
0 |
| qwen1.5-1.8b-chat |
24 |
46.6 |
7.02 |
3 |
1.6 |
0.81 |
1.4 |
| deepseek_r1_distill_qwen_1.5b |
21.8 |
50.4 |
6.34 |
4 |
1.5 |
0.73 |
1.4 |
| qwen2-math-1.5b-instruct |
21.8 |
52.3 |
7.79 |
4 |
1.5 |
0.71 |
1.4 |
| qwen2-0.5b-instruct |
18.5 |
56 |
6.14 |
5 |
1.5 |
0.49 |
1.4 |
| qwen2.5-coder-0.5b-instruct |
18.1 |
58.6 |
6.47 |
5 |
1.4 |
0.35 |
1.4 |
| qwen1.5-0.5b-chat |
15.1 |
48.5 |
5.34 |
5 |
1.3 |
0.5 |
1.2 |