| google_gemma_3_27b_it |
94.4 |
95.9 |
32.6 |
3 |
0.63 |
0.56 |
0.29 |
| qwen3-14b |
93.5 |
95.6 |
32.2 |
3 |
0.68 |
0.59 |
0.34 |
| qwen3-32b |
93.4 |
95.8 |
32.2 |
2 |
0.69 |
0.53 |
0.43 |
| llama-3.1-70B-instruct |
92.9 |
92.9 |
31.9 |
4 |
0.71 |
0.71 |
0 |
| google_gemma_3_12b_it |
92.3 |
95.6 |
31.4 |
4 |
0.73 |
0.61 |
0.4 |
| qwen3-8b |
92 |
94.8 |
31 |
3 |
0.75 |
0.63 |
0.4 |
| qwen2.5-coder-32b-instruct |
91.3 |
95.1 |
30.8 |
2 |
0.78 |
0.56 |
0.54 |
| deepseek_r1_distill_llama_70b |
90.6 |
94.8 |
30.9 |
2 |
0.8 |
0.57 |
0.56 |
| google_gemma_2_27b_it |
89.8 |
92.8 |
29.6 |
2 |
0.83 |
0.68 |
0.48 |
| qwen2-72b-instruct |
89.5 |
94.8 |
30.1 |
2 |
0.84 |
0.56 |
0.63 |
| qwen3-4b |
89.5 |
92.9 |
29.6 |
4 |
0.85 |
0.76 |
0.38 |
| google_gemma_2_9b_it |
86.8 |
92.8 |
28 |
3 |
0.93 |
0.74 |
0.57 |
| qwen2-math-72b-instruct |
84.4 |
93.9 |
27.7 |
2 |
1 |
0.52 |
0.85 |
| google_gemma_3_4b_it |
83.3 |
91.1 |
26.3 |
5 |
1 |
0.86 |
0.57 |
| qwen1.5-72b-chat |
82.7 |
90.1 |
26.4 |
2 |
1 |
0.72 |
0.75 |
| deepseek_r1_distill_qwen_7b |
81.9 |
94.5 |
26.3 |
4 |
1.1 |
0.67 |
0.82 |
| qwen1.5-32b-chat |
81.7 |
90.1 |
26 |
2 |
1.1 |
0.7 |
0.8 |
| deepseek_r1_distill_qwen_14b |
81.3 |
93.3 |
26.4 |
4 |
1.1 |
0.72 |
0.8 |
| qwen2.5-coder-14b-instruct |
81 |
95.6 |
26.1 |
3 |
1.1 |
0.58 |
0.91 |
| deepseek_r1_distill_qwen_32b |
80.3 |
91.3 |
26.8 |
2 |
1.1 |
0.61 |
0.91 |
| qwen2-math-7b-instruct |
79.8 |
93.3 |
24.8 |
4 |
1.1 |
0.74 |
0.82 |
| llama-3.1-8B-instruct |
78.3 |
78.3 |
23.8 |
7 |
1.1 |
1.1 |
0 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
78.3 |
89.3 |
24.4 |
2 |
1.1 |
0.67 |
0.91 |
| qwen2-math-1.5b-instruct |
75.2 |
90.6 |
22.7 |
4 |
1.2 |
0.81 |
0.87 |
| mistralai_ministral_8b_instruct_2410 |
73.9 |
92.3 |
22.3 |
4 |
1.2 |
0.74 |
0.96 |
| qwen3-1.7b |
73.4 |
84.8 |
21.6 |
4 |
1.2 |
0.99 |
0.71 |
| deepseek_r1_distill_llama_8b |
73 |
92.9 |
22.5 |
4 |
1.2 |
0.71 |
1 |
| qwen2-7b-instruct |
71.7 |
91.9 |
21.6 |
4 |
1.2 |
0.73 |
1 |
| qwen1.5-14b-chat |
70.4 |
85.5 |
20.3 |
3 |
1.3 |
0.87 |
0.9 |
| llama-3.2-3B-instruct |
67.6 |
67.6 |
19.4 |
10 |
1.3 |
1.3 |
0 |
| qwen2.5-coder-7b-instruct |
65.4 |
89.5 |
19.2 |
4 |
1.3 |
0.74 |
1.1 |
| mistralai_mathstral_7b_v0.1 |
63.4 |
89.8 |
18.2 |
4 |
1.3 |
0.73 |
1.1 |
| deepseek_v2_lite_chat |
62.1 |
75.2 |
17.1 |
2 |
1.3 |
0.89 |
1 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
60.8 |
81.9 |
17.1 |
3 |
1.3 |
0.84 |
1 |
| deepseek_r1_distill_qwen_1.5b |
59.8 |
86.6 |
17.3 |
4 |
1.4 |
0.72 |
1.1 |
| qwen1.5-7b-chat |
55.2 |
75.4 |
14.5 |
3 |
1.4 |
0.91 |
1 |
| qwen2.5-coder-3b-instruct |
54.9 |
82.1 |
14.6 |
4 |
1.4 |
0.81 |
1.1 |
| google_codegemma_1.1_7b_it |
50.3 |
79 |
13 |
5 |
1.4 |
0.89 |
1.1 |
| google_gemma_3_1b_it |
44.6 |
62.9 |
10.9 |
4 |
1.4 |
1.1 |
0.86 |
| mistralai_mistral_7b_instruct_v0.3 |
43.4 |
72.2 |
11 |
4 |
1.4 |
0.82 |
1.1 |
| qwen3-0.6b |
38.2 |
64.8 |
8.87 |
5 |
1.3 |
0.92 |
0.98 |
| qwen2.5-coder-1.5b-instruct |
37.4 |
64.8 |
8.72 |
4 |
1.3 |
0.82 |
1 |
| mistralai_mistral_7b_instruct_v0.2 |
36.8 |
62.4 |
8.82 |
4 |
1.3 |
0.86 |
1 |
| llama-3.2-1B-instruct |
29 |
29 |
6.29 |
13 |
1.2 |
1.2 |
0 |
| google_gemma_7b_it |
27.5 |
47.5 |
6.17 |
4 |
1.2 |
0.85 |
0.89 |
| mistralai_mistral_7b_instruct_v0.1 |
22.5 |
47.8 |
4.79 |
4 |
1.1 |
0.63 |
0.96 |
| qwen2-1.5b-instruct |
20.5 |
47.8 |
4.43 |
4 |
1.1 |
0.53 |
0.98 |
| qwen1.5-1.8b-chat |
11.1 |
24.5 |
2.12 |
3 |
0.86 |
0.41 |
0.76 |
| qwen2.5-coder-0.5b-instruct |
9.83 |
29.8 |
1.87 |
5 |
0.82 |
0.38 |
0.73 |
| google_gemma_2b_it |
9.17 |
21.1 |
1.77 |
4 |
0.79 |
0.49 |
0.62 |
| qwen2-0.5b-instruct |
8.49 |
27.1 |
1.58 |
5 |
0.77 |
0.33 |
0.69 |
| qwen1.5-0.5b-chat |
3.12 |
12.7 |
0.622 |
5 |
0.48 |
0.14 |
0.46 |