| google_gemma_3_27b_it |
85.3 |
94.2 |
42.2 |
11 |
1.6 |
1.3 |
0.92 |
| deepseek_r1_distill_qwen_32b |
83.9 |
95.2 |
41.3 |
10 |
1.6 |
1.2 |
1.1 |
| qwen3-32b |
81.9 |
92.8 |
39.4 |
9 |
1.7 |
1.3 |
1.1 |
| deepseek_r1_distill_llama_70b |
81.1 |
94.2 |
39.4 |
10 |
1.7 |
1.3 |
1.2 |
| qwen3-14b |
81 |
93 |
38.7 |
11 |
1.8 |
1.4 |
1.1 |
| qwen2-math-72b-instruct |
80.4 |
91.4 |
38.1 |
7 |
1.8 |
1.5 |
1 |
| qwen3-8b |
79.2 |
93.4 |
37.3 |
11 |
1.8 |
1.5 |
1.1 |
| google_gemma_3_12b_it |
79 |
92 |
37.3 |
12 |
1.8 |
1.5 |
1 |
| deepseek_r1_distill_qwen_14b |
78.9 |
94.2 |
37.9 |
12 |
1.8 |
1.3 |
1.3 |
| qwen3-4b |
77.2 |
92.2 |
36 |
12 |
1.9 |
1.5 |
1.1 |
| deepseek_r1_distill_qwen_7b |
77.1 |
93 |
36.5 |
12 |
1.9 |
1.4 |
1.3 |
| qwen2.5-coder-32b-instruct |
76.1 |
90.2 |
35 |
10 |
1.9 |
1.5 |
1.2 |
| qwen2.5-coder-14b-instruct |
71.3 |
89 |
31.7 |
11 |
2 |
1.6 |
1.2 |
| deepseek_r1_distill_llama_8b |
70.4 |
91.2 |
32.7 |
12 |
2 |
1.5 |
1.4 |
| qwen2-math-1.5b-instruct |
68 |
68 |
29.7 |
1 |
2.1 |
NaN |
NaN |
| deepseek_r1_distill_qwen_1.5b |
67.6 |
89.6 |
30.1 |
12 |
2.1 |
1.5 |
1.4 |
| qwen3-1.7b |
66.7 |
87 |
29.1 |
12 |
2.1 |
1.6 |
1.3 |
| llama-3.1-70B-instruct |
65.6 |
65.8 |
28.7 |
12 |
2.1 |
2.1 |
0.21 |
| google_gemma_3_4b_it |
65.1 |
84.8 |
29.1 |
12 |
2.1 |
1.7 |
1.3 |
| qwen2-72b-instruct |
64.5 |
83.6 |
27.2 |
10 |
2.1 |
1.7 |
1.3 |
| qwen2.5-coder-7b-instruct |
61 |
86.8 |
25.7 |
12 |
2.2 |
1.6 |
1.5 |
| google_gemma_2_27b_it |
52.3 |
74.2 |
20.4 |
10 |
2.2 |
1.9 |
1.2 |
| qwen2-7b-instruct |
51.7 |
80.2 |
20.1 |
12 |
2.2 |
1.7 |
1.5 |
| mistralai_ministral_8b_instruct_2410 |
49.3 |
79.2 |
18.9 |
12 |
2.2 |
1.7 |
1.5 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
48.1 |
77.8 |
18.4 |
9 |
2.2 |
1.7 |
1.5 |
| llama-3.1-8B-instruct |
47.6 |
58.6 |
18 |
13 |
2.2 |
2 |
1.1 |
| mistralai_mathstral_7b_v0.1 |
47 |
76.6 |
17.7 |
12 |
2.2 |
1.7 |
1.5 |
| qwen2.5-coder-3b-instruct |
46.9 |
80 |
18.4 |
11 |
2.2 |
1.5 |
1.6 |
| google_gemma_2_9b_it |
46.4 |
67.8 |
16.9 |
11 |
2.2 |
1.9 |
1.2 |
| llama-3.2-3B-instruct |
44.1 |
55.6 |
16.6 |
18 |
2.2 |
1.9 |
1.1 |
| qwen1.5-72b-chat |
40.3 |
73 |
14.7 |
10 |
2.2 |
1.6 |
1.5 |
| qwen1.5-32b-chat |
38.9 |
70.4 |
14.1 |
9 |
2.2 |
1.6 |
1.5 |
| qwen3-0.6b |
33.7 |
71.4 |
12.2 |
13 |
2.1 |
1.5 |
1.5 |
| qwen2.5-coder-1.5b-instruct |
32.8 |
66.4 |
11.3 |
12 |
2.1 |
1.5 |
1.5 |
| qwen1.5-14b-chat |
30.5 |
63.6 |
10.3 |
11 |
2.1 |
1.5 |
1.4 |
| llama-3.2-1B-instruct |
27.9 |
28.2 |
9.67 |
11 |
2 |
2 |
0.23 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
25.2 |
61.2 |
8.44 |
11 |
1.9 |
1.3 |
1.4 |
| deepseek_v2_lite_chat |
22.5 |
55.8 |
7.25 |
9 |
1.9 |
1.2 |
1.4 |
| google_codegemma_1.1_7b_it |
20.8 |
52 |
6.55 |
12 |
1.8 |
1.3 |
1.3 |
| qwen1.5-7b-chat |
16.5 |
45.4 |
5.19 |
11 |
1.7 |
1.1 |
1.3 |
| google_gemma_3_1b_it |
14.5 |
43.2 |
5.93 |
12 |
1.6 |
1 |
1.2 |
| mistralai_mistral_7b_instruct_v0.3 |
12.9 |
41 |
3.86 |
12 |
1.5 |
0.95 |
1.2 |
| mistralai_mistral_7b_instruct_v0.2 |
10.1 |
37.6 |
2.98 |
12 |
1.3 |
0.82 |
1.1 |
| qwen2.5-coder-0.5b-instruct |
8.03 |
32.6 |
2.48 |
13 |
1.2 |
0.7 |
1 |
| qwen2-1.5b-instruct |
6.8 |
31.6 |
1.96 |
12 |
1.1 |
0.53 |
0.99 |
| mistralai_mistral_7b_instruct_v0.1 |
6.4 |
26.8 |
1.99 |
12 |
1.1 |
0.58 |
0.93 |
| google_gemma_7b_it |
5.77 |
21.4 |
1.68 |
12 |
1 |
0.68 |
0.79 |
| qwen2-0.5b-instruct |
2.91 |
19.4 |
0.985 |
13 |
0.75 |
0.31 |
0.69 |
| qwen1.5-1.8b-chat |
1.42 |
10.6 |
0.434 |
11 |
0.53 |
0.16 |
0.5 |
| qwen1.5-0.5b-chat |
0.8 |
6.6 |
0.307 |
12 |
0.4 |
0.11 |
0.38 |
| google_gemma_2b_it |
0.117 |
1.4 |
0.047 |
12 |
0.15 |
0 |
0.15 |