| qwen3-32b |
49.4 |
83 |
31.9 |
11 |
2.4 |
1.7 |
1.6 |
| llama-3.1-70B-instruct |
43.8 |
43.8 |
27.6 |
13 |
2.3 |
2.3 |
0 |
| google_gemma_3_27b_it |
43.4 |
71 |
27.5 |
7 |
2.3 |
1.7 |
1.6 |
| qwen3-14b |
41.7 |
67.2 |
25.7 |
11 |
2.3 |
1.9 |
1.4 |
| qwen2-math-72b-instruct |
40.6 |
80.4 |
25.4 |
10 |
2.3 |
1.5 |
1.7 |
| qwen3-8b |
40.1 |
66.3 |
24.8 |
11 |
2.3 |
1.8 |
1.4 |
| qwen2.5-coder-32b-instruct |
39.5 |
72.3 |
24.3 |
10 |
2.3 |
1.7 |
1.6 |
| qwen2-72b-instruct |
39 |
70.1 |
23.5 |
10 |
2.3 |
1.8 |
1.5 |
| google_gemma_3_12b_it |
37.4 |
76.8 |
23.4 |
12 |
2.3 |
1.6 |
1.6 |
| qwen3-4b |
36.7 |
63.2 |
22.5 |
12 |
2.3 |
1.8 |
1.3 |
| qwen2.5-coder-14b-instruct |
34.6 |
82.1 |
21.3 |
11 |
2.2 |
1.3 |
1.8 |
| qwen1.5-32b-chat |
32.5 |
75.9 |
19.7 |
11 |
2.2 |
1.4 |
1.7 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
32.2 |
74.6 |
19.6 |
11 |
2.2 |
1.4 |
1.7 |
| llama-3.1-8B-instruct |
31.7 |
31.7 |
19.9 |
15 |
2.2 |
2.2 |
0 |
| qwen3-1.7b |
31.6 |
66.7 |
20.2 |
12 |
2.2 |
1.6 |
1.5 |
| qwen1.5-72b-chat |
31.5 |
67.4 |
19 |
10 |
2.2 |
1.5 |
1.6 |
| deepseek_r1_distill_qwen_32b |
31.5 |
53.6 |
19 |
10 |
2.2 |
1.8 |
1.3 |
| qwen2.5-coder-7b-instruct |
30.9 |
88.2 |
19.5 |
11 |
2.2 |
1.1 |
1.9 |
| mistralai_mathstral_7b_v0.1 |
30.8 |
81.2 |
19 |
11 |
2.2 |
1.2 |
1.8 |
| mistralai_ministral_8b_instruct_2410 |
30.8 |
81.5 |
19.3 |
12 |
2.2 |
1.2 |
1.9 |
| google_gemma_2_9b_it |
30.7 |
65.6 |
18.1 |
12 |
2.2 |
1.6 |
1.5 |
| google_gemma_3_4b_it |
30.4 |
72.8 |
19.2 |
13 |
2.2 |
1.5 |
1.6 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
29.8 |
74.1 |
18 |
11 |
2.2 |
1.3 |
1.7 |
| llama-3.2-3B-instruct |
29.7 |
29.7 |
18.7 |
17 |
2.2 |
2.2 |
0 |
| deepseek_r1_distill_qwen_14b |
28.6 |
51.6 |
17 |
11 |
2.1 |
1.7 |
1.3 |
| qwen1.5-14b-chat |
28.6 |
68.8 |
17.6 |
11 |
2.1 |
1.4 |
1.6 |
| qwen2-math-7b-instruct |
28.5 |
81.7 |
18.3 |
12 |
2.1 |
1.1 |
1.9 |
| google_codegemma_1.1_7b_it |
28.1 |
76.6 |
18.2 |
13 |
2.1 |
1.2 |
1.7 |
| qwen2-7b-instruct |
27.7 |
76.3 |
17.1 |
11 |
2.1 |
1.2 |
1.7 |
| mistralai_mistral_7b_instruct_v0.3 |
27.4 |
73.7 |
16.8 |
11 |
2.1 |
1.3 |
1.7 |
| qwen2.5-coder-3b-instruct |
27 |
89.1 |
17.7 |
12 |
2.1 |
0.75 |
2 |
| google_gemma_7b_it |
26.7 |
60.9 |
17.1 |
12 |
2.1 |
1.5 |
1.5 |
| deepseek_r1_distill_llama_70b |
26.3 |
44.9 |
15.3 |
10 |
2.1 |
1.7 |
1.2 |
| mistralai_mistral_7b_instruct_v0.1 |
25.2 |
83.7 |
16.7 |
11 |
2.1 |
0.85 |
1.9 |
| google_gemma_3_1b_it |
24.6 |
73.7 |
16.7 |
12 |
2 |
1 |
1.7 |
| deepseek_v2_lite_chat |
24.5 |
78.1 |
15.8 |
11 |
2 |
0.99 |
1.8 |
| deepseek_r1_distill_qwen_7b |
24.4 |
50.2 |
14.3 |
11 |
2 |
1.5 |
1.3 |
| mistralai_mistral_7b_instruct_v0.2 |
24.1 |
70.8 |
14.8 |
11 |
2 |
1.2 |
1.7 |
| deepseek_r1_distill_llama_8b |
23.8 |
52.5 |
13.6 |
12 |
2 |
1.5 |
1.4 |
| qwen3-0.6b |
23.6 |
68.3 |
15.6 |
13 |
2 |
1.2 |
1.6 |
| qwen2-math-1.5b-instruct |
23.1 |
81.5 |
15.3 |
11 |
2 |
0.79 |
1.8 |
| qwen1.5-7b-chat |
20.4 |
72.5 |
12.9 |
12 |
1.9 |
0.85 |
1.7 |
| qwen2.5-coder-1.5b-instruct |
19.1 |
88.8 |
13.1 |
12 |
1.9 |
0.34 |
1.8 |
| qwen2.5-coder-0.5b-instruct |
18 |
88.2 |
13 |
13 |
1.8 |
0.36 |
1.8 |
| llama-3.2-1B-instruct |
15.4 |
15.4 |
10.8 |
12 |
1.7 |
1.7 |
0 |
| qwen2-1.5b-instruct |
12.5 |
70.3 |
8.35 |
12 |
1.6 |
0.36 |
1.5 |
| google_gemma_2b_it |
12.1 |
50 |
8.34 |
12 |
1.5 |
0.72 |
1.4 |
| qwen2-0.5b-instruct |
12 |
75 |
8.48 |
13 |
1.5 |
0.28 |
1.5 |
| deepseek_r1_distill_qwen_1.5b |
10.9 |
40.2 |
6.08 |
12 |
1.5 |
0.81 |
1.2 |
| qwen1.5-0.5b-chat |
8.6 |
63.4 |
6.18 |
13 |
1.3 |
0.2 |
1.3 |
| qwen1.5-1.8b-chat |
7.92 |
54.5 |
5.37 |
12 |
1.3 |
0.29 |
1.2 |