| google_gemma_3_27b_it |
85.5 |
92.8 |
44.9 |
3 |
1.6 |
1.2 |
0.99 |
| qwen3-32b |
81.5 |
89.4 |
41.6 |
2 |
1.7 |
1.2 |
1.3 |
| deepseek_r1_distill_qwen_32b |
81.1 |
89 |
41.8 |
2 |
1.8 |
1.2 |
1.3 |
| qwen3-14b |
80.7 |
89.4 |
41 |
3 |
1.8 |
1.4 |
1.1 |
| deepseek_r1_distill_llama_70b |
78.9 |
87.2 |
40 |
2 |
1.8 |
1.3 |
1.3 |
| google_gemma_3_12b_it |
78.3 |
87.4 |
39.4 |
3 |
1.8 |
1.5 |
1.1 |
| qwen3-8b |
78.3 |
86.6 |
39.2 |
3 |
1.8 |
1.5 |
1.1 |
| qwen3-4b |
77.1 |
88 |
38.3 |
4 |
1.9 |
1.5 |
1.2 |
| deepseek_r1_distill_qwen_14b |
76.3 |
89 |
38.5 |
3 |
1.9 |
1.4 |
1.3 |
| qwen2.5-coder-32b-instruct |
74.4 |
82.2 |
36.3 |
2 |
2 |
1.5 |
1.2 |
| deepseek_r1_distill_qwen_7b |
72.7 |
87.6 |
36 |
3 |
2 |
1.4 |
1.4 |
| qwen2-math-7b-instruct |
70.7 |
79.2 |
33.6 |
2 |
2 |
1.6 |
1.3 |
| qwen2.5-coder-14b-instruct |
67.2 |
80.4 |
31.2 |
3 |
2.1 |
1.6 |
1.4 |
| deepseek_r1_distill_llama_8b |
67.1 |
84.8 |
32.7 |
4 |
2.1 |
1.5 |
1.5 |
| qwen3-1.7b |
65.4 |
79.6 |
30.4 |
4 |
2.1 |
1.7 |
1.3 |
| google_gemma_3_4b_it |
65 |
79.6 |
31 |
4 |
2.1 |
1.7 |
1.3 |
| deepseek_r1_distill_qwen_1.5b |
64.6 |
82.6 |
30.3 |
4 |
2.1 |
1.5 |
1.5 |
| llama-3.1-70B-instruct |
63.4 |
63.6 |
29.4 |
4 |
2.2 |
2.1 |
0.2 |
| qwen2-72b-instruct |
63 |
72.2 |
28.7 |
2 |
2.2 |
1.7 |
1.4 |
| qwen2-math-1.5b-instruct |
61.5 |
71.8 |
27.7 |
2 |
2.2 |
1.6 |
1.4 |
| qwen2.5-coder-7b-instruct |
53.7 |
71.2 |
23.4 |
3 |
2.2 |
1.6 |
1.5 |
| google_gemma_2_27b_it |
52.8 |
52.8 |
22.1 |
1 |
2.2 |
NaN |
NaN |
| qwen2-7b-instruct |
45.7 |
64.8 |
18.5 |
3 |
2.2 |
1.6 |
1.6 |
| llama-3.1-8B-instruct |
45.1 |
45.4 |
18.7 |
6 |
2.2 |
2.2 |
0.25 |
| google_gemma_2_9b_it |
44.9 |
56.4 |
17.8 |
3 |
2.2 |
1.9 |
1.2 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
43.8 |
57.8 |
17.9 |
2 |
2.2 |
1.5 |
1.7 |
| qwen2.5-coder-3b-instruct |
40.8 |
65.2 |
16.9 |
4 |
2.2 |
1.4 |
1.7 |
| mistralai_mathstral_7b_v0.1 |
39.8 |
60.4 |
16.1 |
3 |
2.2 |
1.4 |
1.7 |
| mistralai_ministral_8b_instruct_2410 |
39.8 |
58.2 |
15.8 |
3 |
2.2 |
1.5 |
1.6 |
| llama-3.2-3B-instruct |
38.3 |
38.8 |
15.1 |
10 |
2.2 |
2.2 |
0.27 |
| qwen1.5-72b-chat |
37.9 |
48.4 |
14.7 |
2 |
2.2 |
1.6 |
1.4 |
| qwen1.5-32b-chat |
37.1 |
49.8 |
14.6 |
2 |
2.2 |
1.5 |
1.6 |
| qwen3-0.6b |
31.6 |
50.8 |
12.3 |
3 |
2.1 |
1.4 |
1.6 |
| qwen1.5-14b-chat |
28.3 |
44.4 |
10.1 |
3 |
2 |
1.5 |
1.4 |
| qwen2.5-coder-1.5b-instruct |
26.2 |
49.6 |
9.64 |
4 |
2 |
1.2 |
1.5 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
23.3 |
40.4 |
8.16 |
3 |
1.9 |
1.2 |
1.4 |
| llama-3.2-1B-instruct |
20.5 |
20.6 |
7.33 |
11 |
1.8 |
1.8 |
0.16 |
| deepseek_v2_lite_chat |
18.9 |
27.2 |
6.46 |
2 |
1.8 |
1.2 |
1.3 |
| google_codegemma_1.1_7b_it |
18.6 |
34.8 |
6.2 |
4 |
1.7 |
1.2 |
1.3 |
| qwen1.5-7b-chat |
15.9 |
28.6 |
5.26 |
3 |
1.6 |
1.1 |
1.2 |
| google_gemma_3_1b_it |
13.6 |
30.2 |
5.92 |
4 |
1.5 |
0.91 |
1.2 |
| mistralai_mistral_7b_instruct_v0.3 |
10.5 |
20.6 |
3.39 |
3 |
1.4 |
0.81 |
1.1 |
| mistralai_mistral_7b_instruct_v0.2 |
9 |
19 |
3.06 |
3 |
1.3 |
0.71 |
1.1 |
| qwen2.5-coder-0.5b-instruct |
6 |
18 |
2.38 |
4 |
1.1 |
0.44 |
0.97 |
| google_gemma_7b_it |
5.75 |
13.6 |
1.86 |
4 |
1 |
0.64 |
0.82 |
| qwen2-1.5b-instruct |
4.65 |
13.2 |
1.54 |
4 |
0.94 |
0.42 |
0.84 |
| mistralai_mistral_7b_instruct_v0.1 |
4.13 |
9.8 |
1.42 |
3 |
0.89 |
0.39 |
0.8 |
| qwen2-0.5b-instruct |
2.05 |
6.8 |
0.756 |
4 |
0.63 |
0.21 |
0.6 |
| qwen1.5-1.8b-chat |
0.867 |
2.2 |
0.293 |
3 |
0.41 |
0.16 |
0.38 |
| google_gemma_2b_it |
0.35 |
1.4 |
0.104 |
4 |
0.26 |
0 |
0.26 |
| qwen1.5-0.5b-chat |
0.3 |
1.2 |
0.145 |
4 |
0.24 |
0 |
0.24 |