| deepseek_r1_distill_qwen_32b |
37.9 |
73.3 |
32.4 |
11 |
8.9 |
6.4 |
6.1 |
| deepseek_r1_distill_llama_70b |
34.2 |
66.7 |
29.1 |
11 |
8.7 |
6.3 |
5.9 |
| deepseek_r1_distill_qwen_7b |
28.5 |
46.7 |
23.8 |
11 |
8.2 |
6.5 |
5.1 |
| deepseek_r1_distill_qwen_14b |
27.6 |
43.3 |
22.7 |
11 |
8.2 |
6.9 |
4.4 |
| google_gemma_3_27b_it |
25.6 |
56.7 |
20.8 |
12 |
8 |
5.4 |
5.9 |
| qwen3-14b |
24.4 |
33.3 |
19.5 |
12 |
7.8 |
6.7 |
4 |
| qwen3-32b |
22.7 |
43.3 |
18.1 |
11 |
7.7 |
5.9 |
4.9 |
| llama-3.1-70B-instruct |
20 |
20 |
16.6 |
13 |
7.3 |
7.3 |
0 |
| deepseek_r1_distill_llama_8b |
19 |
40 |
15.3 |
13 |
7.2 |
5.2 |
4.9 |
| qwen2-math-72b-instruct |
18.3 |
36.7 |
14.4 |
6 |
7.1 |
5.1 |
4.9 |
| google_gemma_3_12b_it |
18.2 |
46.7 |
14.6 |
11 |
7 |
5.2 |
4.7 |
| qwen3-8b |
17.5 |
50 |
14.2 |
12 |
6.9 |
5.3 |
4.4 |
| qwen2.5-coder-32b-instruct |
13 |
30 |
9.68 |
11 |
6.1 |
4.6 |
4 |
| qwen3-4b |
11.9 |
23.3 |
8.86 |
12 |
5.9 |
4.5 |
3.9 |
| deepseek_r1_distill_qwen_1.5b |
11.5 |
23.3 |
8.78 |
13 |
5.8 |
4.7 |
3.5 |
| qwen2.5-coder-14b-instruct |
10.8 |
20 |
7.77 |
12 |
5.7 |
4.5 |
3.4 |
| llama-3.2-3B-instruct |
10 |
10 |
7.48 |
18 |
5.5 |
5.5 |
0 |
| qwen3-1.7b |
9.44 |
23.3 |
7.16 |
12 |
5.3 |
3.9 |
3.7 |
| qwen2-math-7b-instruct |
8.33 |
13.3 |
6.38 |
6 |
5 |
4.3 |
2.7 |
| qwen2-math-1.5b-instruct |
7.5 |
13.3 |
5.05 |
4 |
4.8 |
3.8 |
2.9 |
| google_gemma_3_4b_it |
7.18 |
23.3 |
5.57 |
13 |
4.7 |
2.5 |
4 |
| qwen2-72b-instruct |
6.06 |
20 |
4.19 |
11 |
4.4 |
2.8 |
3.3 |
| qwen2.5-coder-7b-instruct |
4.55 |
10 |
3.19 |
11 |
3.8 |
2.4 |
2.9 |
| llama-3.1-8B-instruct |
3.33 |
3.33 |
2.36 |
15 |
3.3 |
3.3 |
0 |
| llama-3.2-1B-instruct |
3.33 |
3.33 |
2.29 |
21 |
3.3 |
3.3 |
0 |
| qwen2-7b-instruct |
3.03 |
6.67 |
2.23 |
11 |
3.1 |
2 |
2.4 |
| google_gemma_2_27b_it |
3 |
13.3 |
2 |
10 |
3.1 |
1.8 |
2.5 |
| qwen2.5-coder-3b-instruct |
2.22 |
6.67 |
1.53 |
12 |
2.7 |
1.4 |
2.3 |
| google_gemma_3_1b_it |
1.54 |
3.33 |
1.04 |
13 |
2.2 |
1.4 |
1.7 |
| mistralai_mathstral_7b_v0.1 |
1.52 |
6.67 |
1.12 |
11 |
2.2 |
0.86 |
2.1 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
1.52 |
13.3 |
1.06 |
11 |
2.2 |
0.35 |
2.2 |
| deepseek_v2_lite_chat |
1.21 |
3.33 |
0.818 |
11 |
2 |
1.1 |
1.7 |
| qwen3-0.6b |
1.03 |
3.33 |
0.691 |
13 |
1.8 |
0.91 |
1.6 |
| qwen1.5-72b-chat |
0.606 |
3.33 |
0.363 |
11 |
1.4 |
0.44 |
1.3 |
| qwen1.5-32b-chat |
0.606 |
6.67 |
0.384 |
11 |
1.4 |
0 |
1.4 |
| google_gemma_2_9b_it |
0.303 |
3.33 |
0.203 |
11 |
1 |
0 |
1 |
| mistralai_mistral_7b_instruct_v0.2 |
0.303 |
3.33 |
0.252 |
11 |
1 |
0 |
1 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
0.278 |
3.33 |
0.231 |
12 |
0.96 |
0 |
0.96 |
| google_codegemma_1.1_7b_it |
0 |
0 |
0 |
13 |
0 |
0 |
0 |
| google_gemma_2b_it |
0 |
0 |
0 |
13 |
0 |
0 |
0 |
| google_gemma_7b_it |
0 |
0 |
0 |
13 |
0 |
0 |
0 |
| qwen2-1.5b-instruct |
0 |
0 |
0 |
13 |
0 |
0 |
0 |
| mistralai_mistral_7b_instruct_v0.3 |
0 |
0 |
0 |
11 |
0 |
0 |
0 |
| qwen1.5-0.5b-chat |
0 |
0 |
0 |
13 |
0 |
0 |
0 |
| mistralai_mistral_7b_instruct_v0.1 |
0 |
0 |
0 |
11 |
0 |
0 |
0 |
| qwen2-0.5b-instruct |
0 |
0 |
0 |
13 |
0 |
0 |
0 |
| qwen1.5-7b-chat |
0 |
0 |
0 |
12 |
0 |
0 |
0 |
| qwen1.5-1.8b-chat |
0 |
0 |
0 |
11 |
0 |
0 |
0 |
| qwen1.5-14b-chat |
0 |
0 |
0 |
12 |
0 |
0 |
0 |
| mistralai_ministral_8b_instruct_2410 |
0 |
0 |
0 |
11 |
0 |
0 |
0 |
| qwen2.5-coder-0.5b-instruct |
0 |
0 |
0 |
13 |
0 |
0 |
0 |
| qwen2.5-coder-1.5b-instruct |
0 |
0 |
0 |
11 |
0 |
0 |
0 |