| qwen2-72b-instruct |
79.3 |
81.3 |
46.4 |
2 |
4.7 |
4.4 |
1.6 |
| google_gemma_3_27b_it |
72 |
82.7 |
42 |
3 |
5.2 |
4.1 |
3.2 |
| qwen2-math-72b-instruct |
71.3 |
85.3 |
41.2 |
2 |
5.2 |
2.9 |
4.3 |
| qwen3-8b |
70.2 |
81.3 |
40.1 |
3 |
5.3 |
4.1 |
3.3 |
| qwen3-4b |
70 |
86.7 |
39.9 |
4 |
5.3 |
3.8 |
3.7 |
| qwen3-14b |
69.3 |
77.3 |
39 |
3 |
5.3 |
4.6 |
2.7 |
| qwen3-32b |
65.8 |
84 |
37.1 |
3 |
5.5 |
3.7 |
4 |
| qwen2.5-coder-32b-instruct |
62 |
72 |
34.8 |
2 |
5.6 |
4.3 |
3.7 |
| google_gemma_2_27b_it |
58 |
70.7 |
31.9 |
2 |
5.7 |
3.9 |
4.1 |
| google_gemma_3_12b_it |
57.3 |
78.7 |
31.9 |
4 |
5.7 |
4.1 |
3.9 |
| qwen2.5-coder-14b-instruct |
56.9 |
73.3 |
30.7 |
3 |
5.7 |
4.3 |
3.8 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
56 |
74.7 |
30.6 |
3 |
5.7 |
4 |
4.1 |
| qwen1.5-72b-chat |
55.3 |
64 |
30.3 |
2 |
5.7 |
4.6 |
3.4 |
| qwen1.5-32b-chat |
55.1 |
66.7 |
29.4 |
3 |
5.7 |
4.8 |
3.1 |
| qwen1.5-14b-chat |
50.7 |
66.7 |
27.2 |
3 |
5.8 |
4.3 |
3.8 |
| qwen2.5-coder-7b-instruct |
48 |
77.3 |
26.4 |
4 |
5.8 |
3.4 |
4.7 |
| qwen2-math-7b-instruct |
47.3 |
58.7 |
25.5 |
2 |
5.8 |
4.3 |
3.9 |
| qwen2-7b-instruct |
46 |
66.7 |
24.6 |
4 |
5.8 |
4.3 |
3.8 |
| qwen3-1.7b |
44.3 |
64 |
23 |
4 |
5.7 |
4.4 |
3.7 |
| google_gemma_2_9b_it |
44 |
73.3 |
24.6 |
4 |
5.7 |
3.4 |
4.6 |
| qwen1.5-7b-chat |
43.1 |
58.7 |
23.6 |
3 |
5.7 |
4.2 |
3.9 |
| mistralai_mathstral_7b_v0.1 |
39.3 |
65.3 |
20.7 |
4 |
5.6 |
3.7 |
4.3 |
| llama-3.1-8B-instruct |
38.7 |
38.7 |
20.8 |
7 |
5.6 |
5.6 |
0 |
| deepseek_v2_lite_chat |
37.8 |
62.7 |
21.1 |
3 |
5.6 |
3.4 |
4.4 |
| mistralai_mistral_7b_instruct_v0.3 |
37.7 |
54.7 |
18.9 |
4 |
5.6 |
4.4 |
3.4 |
| qwen3-0.6b |
37.3 |
65.3 |
20.3 |
5 |
5.6 |
3.6 |
4.2 |
| mistralai_ministral_8b_instruct_2410 |
36.7 |
78.7 |
19.8 |
4 |
5.6 |
2.5 |
5 |
| google_gemma_3_4b_it |
36 |
53.3 |
19.6 |
5 |
5.5 |
4.2 |
3.6 |
| llama-3.2-3B-instruct |
32 |
32 |
16 |
10 |
5.4 |
5.4 |
0 |
| qwen2.5-coder-3b-instruct |
31.7 |
62.7 |
16.5 |
4 |
5.4 |
2.9 |
4.5 |
| qwen2-math-1.5b-instruct |
29.8 |
49.3 |
16.2 |
3 |
5.3 |
3.3 |
4.1 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
27.6 |
50.7 |
15.3 |
3 |
5.2 |
3 |
4.2 |
| google_codegemma_1.1_7b_it |
26.1 |
61.3 |
14.2 |
5 |
5.1 |
2.8 |
4.2 |
| qwen2.5-coder-1.5b-instruct |
25 |
68 |
14.3 |
4 |
5 |
0 |
5 |
| google_gemma_7b_it |
23.7 |
37.3 |
11.9 |
4 |
4.9 |
3.8 |
3.1 |
| mistralai_mistral_7b_instruct_v0.2 |
23.3 |
41.3 |
11.5 |
4 |
4.9 |
3.2 |
3.7 |
| qwen2-1.5b-instruct |
21.7 |
52 |
11.7 |
4 |
4.8 |
2 |
4.3 |
| mistralai_mistral_7b_instruct_v0.1 |
20 |
52 |
10.5 |
4 |
4.6 |
1.9 |
4.2 |
| llama-3.2-1B-instruct |
18.7 |
18.7 |
10.1 |
13 |
4.5 |
4.5 |
0 |
| google_gemma_2b_it |
17.7 |
33.3 |
10.7 |
4 |
4.4 |
2.9 |
3.3 |
| qwen1.5-0.5b-chat |
17.3 |
57.3 |
11.1 |
5 |
4.4 |
1.2 |
4.2 |
| deepseek_r1_distill_llama_70b |
16.7 |
24 |
8.03 |
2 |
4.3 |
3 |
3.1 |
| qwen2.5-coder-0.5b-instruct |
16.3 |
57.3 |
10.6 |
5 |
4.3 |
0.17 |
4.3 |
| qwen2-0.5b-instruct |
16 |
57.3 |
9.53 |
5 |
4.2 |
0.57 |
4.2 |
| google_gemma_3_1b_it |
16 |
33.3 |
10.2 |
4 |
4.2 |
2.7 |
3.3 |
| qwen1.5-1.8b-chat |
13.8 |
34.7 |
7.67 |
3 |
4 |
1 |
3.8 |
| deepseek_r1_distill_qwen_32b |
12.7 |
22.7 |
6.6 |
2 |
3.8 |
1.2 |
3.7 |
| deepseek_r1_distill_qwen_14b |
8.67 |
28 |
4.49 |
4 |
3.2 |
0.69 |
3.2 |
| deepseek_r1_distill_qwen_7b |
7.33 |
21.3 |
3.17 |
4 |
3 |
1.4 |
2.7 |
| deepseek_r1_distill_llama_8b |
7 |
21.3 |
3.19 |
4 |
2.9 |
0.91 |
2.8 |
| deepseek_r1_distill_qwen_1.5b |
4.67 |
14.7 |
2.2 |
4 |
2.4 |
0.77 |
2.3 |