| deepseek_r1_distill_llama_70b |
25.8 |
50 |
21.2 |
11 |
8 |
6.7 |
4.4 |
| deepseek_r1_distill_qwen_32b |
25.5 |
43.3 |
20.9 |
11 |
8 |
6.8 |
4.2 |
| deepseek_r1_distill_qwen_14b |
24.5 |
33.3 |
20.2 |
11 |
7.9 |
7.4 |
2.7 |
| google_gemma_3_27b_it |
24.4 |
36.7 |
19.9 |
12 |
7.8 |
6.5 |
4.4 |
| deepseek_r1_distill_llama_8b |
21.5 |
26.7 |
17 |
13 |
7.5 |
6.8 |
3.2 |
| google_gemma_3_12b_it |
20.9 |
36.7 |
16.6 |
11 |
7.4 |
6.2 |
4.1 |
| qwen3-32b |
19.1 |
36.7 |
15.4 |
11 |
7.2 |
5.3 |
4.8 |
| deepseek_r1_distill_qwen_7b |
18.8 |
26.7 |
14.6 |
11 |
7.1 |
6.6 |
2.7 |
| qwen3-14b |
18.1 |
40 |
14.5 |
12 |
7 |
5.3 |
4.6 |
| qwen3-8b |
17.5 |
33.3 |
13.8 |
12 |
6.9 |
5.2 |
4.6 |
| deepseek_r1_distill_qwen_1.5b |
17.2 |
20 |
13.2 |
13 |
6.9 |
6.3 |
2.7 |
| qwen3-4b |
16.4 |
26.7 |
12.8 |
12 |
6.8 |
5.6 |
3.8 |
| qwen2-math-72b-instruct |
12 |
33.3 |
9.48 |
10 |
5.9 |
3.8 |
4.5 |
| qwen2.5-coder-32b-instruct |
11.5 |
30 |
8.95 |
11 |
5.8 |
3.7 |
4.5 |
| qwen2-math-7b-instruct |
10 |
23.3 |
7.87 |
6 |
5.5 |
3.7 |
4 |
| google_gemma_3_4b_it |
9.23 |
20 |
6.97 |
13 |
5.3 |
4.2 |
3.3 |
| qwen3-1.7b |
8.06 |
30 |
6.47 |
12 |
5 |
2.8 |
4.1 |
| qwen2.5-coder-14b-instruct |
7.78 |
23.3 |
5.83 |
12 |
4.9 |
3.3 |
3.6 |
| qwen2-72b-instruct |
3.64 |
26.7 |
2.99 |
11 |
3.4 |
0.61 |
3.4 |
| llama-3.1-70B-instruct |
3.33 |
3.33 |
2.34 |
13 |
3.3 |
3.3 |
0 |
| qwen2-math-1.5b-instruct |
3.33 |
10 |
2.61 |
4 |
3.3 |
1.2 |
3 |
| qwen2.5-coder-7b-instruct |
1.82 |
20 |
1.41 |
11 |
2.4 |
0 |
2.5 |
| mistralai_ministral_8b_instruct_2410 |
1.21 |
13.3 |
0.943 |
11 |
2 |
0 |
2 |
| qwen2.5-coder-3b-instruct |
1.11 |
10 |
0.831 |
12 |
1.9 |
0.36 |
1.9 |
| google_gemma_2_27b_it |
1 |
6.67 |
0.812 |
10 |
1.8 |
0.46 |
1.8 |
| qwen3-0.6b |
0.769 |
10 |
0.596 |
13 |
1.6 |
0 |
1.6 |
| google_gemma_2_9b_it |
0.606 |
3.33 |
0.421 |
11 |
1.4 |
0.44 |
1.3 |
| mistralai_mathstral_7b_v0.1 |
0.606 |
6.67 |
0.438 |
11 |
1.4 |
0 |
1.4 |
| qwen2-1.5b-instruct |
0.513 |
3.33 |
0.387 |
13 |
1.3 |
0.37 |
1.3 |
| google_gemma_3_1b_it |
0.513 |
3.33 |
0.351 |
13 |
1.3 |
0.37 |
1.3 |
| qwen1.5-72b-chat |
0.303 |
3.33 |
0.303 |
11 |
1 |
0 |
1 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
0.303 |
3.33 |
0.207 |
11 |
1 |
0 |
1 |
| qwen2-7b-instruct |
0.303 |
3.33 |
0.281 |
11 |
1 |
0 |
1 |
| qwen1.5-32b-chat |
0.303 |
3.33 |
0.281 |
11 |
1 |
0 |
1 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
0.278 |
3.33 |
0.243 |
12 |
0.96 |
0 |
0.96 |
| google_codegemma_1.1_7b_it |
0.256 |
3.33 |
0.193 |
13 |
0.92 |
0 |
0.92 |
| llama-3.2-3B-instruct |
0 |
0 |
0 |
18 |
0 |
0 |
0 |
| llama-3.2-1B-instruct |
0 |
0 |
0 |
21 |
0 |
0 |
0 |
| llama-3.1-8B-instruct |
0 |
0 |
0 |
15 |
0 |
0 |
0 |
| google_gemma_7b_it |
0 |
0 |
0 |
13 |
0 |
0 |
0 |
| deepseek_v2_lite_chat |
0 |
0 |
0 |
11 |
0 |
0 |
0 |
| google_gemma_2b_it |
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 |
| qwen1.5-7b-chat |
0 |
0 |
0 |
12 |
0 |
0 |
0 |
| qwen2-0.5b-instruct |
0 |
0 |
0 |
13 |
0 |
0 |
0 |
| qwen1.5-14b-chat |
0 |
0 |
0 |
12 |
0 |
0 |
0 |
| qwen1.5-1.8b-chat |
0 |
0 |
0 |
11 |
0 |
0 |
0 |
| mistralai_mistral_7b_instruct_v0.2 |
0 |
0 |
0 |
11 |
0 |
0 |
0 |
| mistralai_mistral_7b_instruct_v0.1 |
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 |