| qwen3-32b |
94.2 |
100 |
40.7 |
11 |
2.4 |
1.8 |
1.6 |
| qwen3-14b |
90.9 |
98.9 |
38.2 |
12 |
3 |
2.4 |
1.8 |
| qwen3-8b |
87 |
100 |
36.3 |
12 |
3.5 |
2.6 |
2.4 |
| qwen2.5-coder-32b-instruct |
87 |
95.7 |
35.5 |
11 |
3.5 |
2.9 |
2 |
| qwen2-72b-instruct |
84.8 |
96.7 |
34.8 |
11 |
3.7 |
2.8 |
2.4 |
| google_gemma_3_27b_it |
84 |
92.4 |
33.3 |
12 |
3.8 |
3.4 |
1.8 |
| deepseek_r1_distill_qwen_32b |
83.6 |
92.4 |
34.6 |
11 |
3.9 |
3.1 |
2.3 |
| deepseek_r1_distill_llama_70b |
83.1 |
92.4 |
34.4 |
11 |
3.9 |
3.2 |
2.2 |
| deepseek_r1_distill_qwen_14b |
80.6 |
92.4 |
32.7 |
11 |
4.1 |
3.3 |
2.5 |
| qwen3-4b |
80 |
93.5 |
31.3 |
12 |
4.2 |
3.3 |
2.6 |
| google_gemma_3_12b_it |
78.5 |
87 |
30.7 |
11 |
4.3 |
3.8 |
2 |
| qwen2.5-coder-14b-instruct |
78.2 |
96.7 |
30.7 |
12 |
4.3 |
3 |
3 |
| google_gemma_2_27b_it |
75 |
94.6 |
29.4 |
10 |
4.5 |
3.4 |
2.9 |
| qwen2-math-72b-instruct |
74.6 |
100 |
29.9 |
11 |
4.5 |
2.7 |
3.7 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
74 |
93.5 |
29.7 |
11 |
4.6 |
3.3 |
3.2 |
| qwen1.5-72b-chat |
70.6 |
92.4 |
27.1 |
11 |
4.8 |
3.3 |
3.4 |
| qwen1.5-32b-chat |
70.3 |
93.5 |
26.8 |
11 |
4.8 |
3.3 |
3.4 |
| google_gemma_2_9b_it |
69.9 |
89.1 |
26.3 |
11 |
4.8 |
3.6 |
3.2 |
| deepseek_r1_distill_qwen_7b |
67.3 |
92.4 |
25.8 |
11 |
4.9 |
3.6 |
3.3 |
| deepseek_r1_distill_llama_8b |
66.8 |
92.4 |
25.5 |
13 |
4.9 |
3.4 |
3.5 |
| google_gemma_3_4b_it |
66.1 |
87 |
24.8 |
13 |
4.9 |
3.8 |
3.2 |
| llama-3.1-8B-instruct |
65.2 |
65.2 |
24.2 |
15 |
5 |
5 |
0 |
| qwen2.5-coder-7b-instruct |
62.5 |
95.7 |
23.3 |
10 |
5 |
3.2 |
3.9 |
| qwen3-1.7b |
60.3 |
90.2 |
22.1 |
12 |
5.1 |
3.6 |
3.7 |
| mistralai_mathstral_7b_v0.1 |
58.3 |
91.3 |
21.6 |
11 |
5.1 |
3.3 |
4 |
| qwen1.5-14b-chat |
57.5 |
89.1 |
21 |
12 |
5.2 |
3.5 |
3.8 |
| llama-3.2-3B-instruct |
56.5 |
56.5 |
20.1 |
17 |
5.2 |
5.2 |
0 |
| qwen2-math-7b-instruct |
55.4 |
85.9 |
20.5 |
6 |
5.2 |
3.3 |
4 |
| qwen2-7b-instruct |
55.3 |
92.4 |
19.9 |
11 |
5.2 |
3.1 |
4.2 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
53.9 |
92.4 |
20.7 |
12 |
5.2 |
3.2 |
4.1 |
| mistralai_ministral_8b_instruct_2410 |
53.8 |
95.7 |
19.7 |
11 |
5.2 |
2.9 |
4.3 |
| qwen3-0.6b |
47.2 |
84.8 |
17.2 |
13 |
5.2 |
3.7 |
3.7 |
| mistralai_mistral_7b_instruct_v0.3 |
45.8 |
85.9 |
16.6 |
11 |
5.2 |
3.2 |
4.1 |
| mistralai_mistral_7b_instruct_v0.2 |
42.7 |
78.3 |
15.6 |
10 |
5.2 |
3.4 |
3.9 |
| qwen2.5-coder-3b-instruct |
42.2 |
87 |
14.2 |
12 |
5.1 |
3.1 |
4.1 |
| deepseek_v2_lite_chat |
41.7 |
78.3 |
14.8 |
11 |
5.1 |
3.4 |
3.8 |
| qwen1.5-7b-chat |
36.9 |
90.2 |
13.3 |
12 |
5 |
2.9 |
4.1 |
| google_codegemma_1.1_7b_it |
36.2 |
73.9 |
12 |
13 |
5 |
3.3 |
3.8 |
| google_gemma_7b_it |
35.7 |
67.4 |
12.7 |
13 |
5 |
3.6 |
3.4 |
| google_gemma_3_1b_it |
34.8 |
78.3 |
11.9 |
13 |
5 |
3.2 |
3.8 |
| mistralai_mistral_7b_instruct_v0.1 |
33.9 |
83.7 |
11.8 |
11 |
4.9 |
2.8 |
4 |
| google_gemma_2b_it |
33.3 |
43.5 |
10.8 |
13 |
4.9 |
4.6 |
1.8 |
| qwen2-1.5b-instruct |
28.6 |
72.8 |
10 |
13 |
4.7 |
2.7 |
3.9 |
| deepseek_r1_distill_qwen_1.5b |
28.3 |
81.5 |
10.2 |
13 |
4.7 |
2.3 |
4.1 |
| qwen2.5-coder-1.5b-instruct |
28.3 |
81.5 |
9.78 |
11 |
4.7 |
2.4 |
4.1 |
| llama-3.2-1B-instruct |
25 |
25 |
9.95 |
12 |
4.5 |
4.5 |
0 |
| qwen1.5-1.8b-chat |
19.4 |
73.9 |
7.2 |
11 |
4.1 |
1.9 |
3.7 |
| qwen2-0.5b-instruct |
15.9 |
76.1 |
6.2 |
13 |
3.8 |
1.2 |
3.6 |
| qwen2.5-coder-0.5b-instruct |
13.4 |
80.4 |
5.35 |
13 |
3.5 |
0.58 |
3.5 |
| qwen2-math-1.5b-instruct |
12.2 |
29.3 |
4.41 |
4 |
3.4 |
1.9 |
2.8 |
| qwen1.5-0.5b-chat |
9.95 |
59.8 |
4.46 |
13 |
3.1 |
0.79 |
3 |