| deepseek_r1_distill_llama_70b |
38.3 |
53.3 |
33.3 |
2 |
8.9 |
5.4 |
7.1 |
| deepseek_r1_distill_qwen_32b |
35 |
46.7 |
30 |
2 |
8.7 |
6.1 |
6.2 |
| google_gemma_3_27b_it |
27.8 |
43.3 |
23.1 |
3 |
8.2 |
5.5 |
6.1 |
| deepseek_r1_distill_qwen_7b |
25.8 |
40 |
21.8 |
4 |
8 |
6.1 |
5.2 |
| qwen3-32b |
25.6 |
40 |
20.8 |
3 |
8 |
5.8 |
5.4 |
| qwen3-14b |
23.3 |
30 |
18.8 |
3 |
7.7 |
6.7 |
3.8 |
| deepseek_r1_distill_qwen_14b |
21.7 |
43.3 |
18 |
4 |
7.5 |
5.5 |
5.1 |
| google_gemma_3_12b_it |
19.2 |
26.7 |
15.1 |
4 |
7.2 |
6.1 |
3.7 |
| qwen3-8b |
17.8 |
26.7 |
14.2 |
3 |
7 |
5.1 |
4.7 |
| qwen3-4b |
17.5 |
26.7 |
13.6 |
4 |
6.9 |
5.9 |
3.7 |
| llama-3.1-70B-instruct |
16.7 |
16.7 |
13.6 |
4 |
6.8 |
6.8 |
0 |
| deepseek_r1_distill_qwen_1.5b |
13.3 |
23.3 |
10.4 |
4 |
6.2 |
4.9 |
3.8 |
| deepseek_r1_distill_llama_8b |
13.3 |
23.3 |
10.4 |
4 |
6.2 |
4.5 |
4.3 |
| qwen2.5-coder-32b-instruct |
11.7 |
20 |
9.03 |
2 |
5.9 |
2.6 |
5.3 |
| google_gemma_3_4b_it |
8 |
13.3 |
5.68 |
5 |
5 |
4 |
3 |
| qwen2.5-coder-14b-instruct |
7.78 |
10 |
6.31 |
3 |
4.9 |
4.5 |
1.9 |
| llama-3.2-3B-instruct |
6.67 |
6.67 |
4.59 |
10 |
4.6 |
4.6 |
0 |
| llama-3.1-8B-instruct |
6.67 |
6.67 |
6.31 |
7 |
4.6 |
4.6 |
0 |
| qwen2.5-coder-7b-instruct |
4.17 |
10 |
2.97 |
4 |
3.6 |
2.2 |
2.9 |
| qwen3-1.7b |
4.17 |
6.67 |
2.87 |
4 |
3.6 |
3.2 |
1.7 |
| qwen2-math-7b-instruct |
3.33 |
6.67 |
2.26 |
2 |
3.3 |
0 |
3.3 |
| qwen2-72b-instruct |
3.33 |
6.67 |
2.68 |
2 |
3.3 |
0 |
3.3 |
| qwen2-math-1.5b-instruct |
3.33 |
3.33 |
2.32 |
3 |
3.3 |
3.3 |
0 |
| llama-3.2-1B-instruct |
3.33 |
3.33 |
3 |
13 |
3.3 |
3.3 |
0 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
2.22 |
6.67 |
2.14 |
3 |
2.7 |
0 |
2.7 |
| google_gemma_2_27b_it |
1.67 |
3.33 |
1.14 |
2 |
2.3 |
0 |
2.4 |
| google_gemma_3_1b_it |
1.67 |
6.67 |
1.53 |
4 |
2.3 |
0 |
2.4 |
| mistralai_mathstral_7b_v0.1 |
1.67 |
3.33 |
1.43 |
4 |
2.3 |
1.3 |
1.9 |
| qwen2.5-coder-3b-instruct |
1.67 |
6.67 |
1.28 |
4 |
2.3 |
0 |
2.4 |
| qwen1.5-14b-chat |
1.11 |
3.33 |
0.757 |
3 |
1.9 |
0 |
1.9 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
1.11 |
3.33 |
0.743 |
3 |
1.9 |
0 |
1.9 |
| google_gemma_2_9b_it |
0.833 |
3.33 |
0.556 |
4 |
1.7 |
0 |
1.7 |
| qwen2.5-coder-1.5b-instruct |
0.833 |
3.33 |
0.71 |
4 |
1.7 |
0 |
1.7 |
| qwen2.5-coder-0.5b-instruct |
0.667 |
3.33 |
0.453 |
5 |
1.5 |
0 |
1.5 |
| google_codegemma_1.1_7b_it |
0.667 |
3.33 |
0.453 |
5 |
1.5 |
0 |
1.5 |
| google_gemma_7b_it |
0 |
0 |
0 |
4 |
0 |
0 |
0 |
| google_gemma_2b_it |
0 |
0 |
0 |
4 |
0 |
0 |
0 |
| deepseek_v2_lite_chat |
0 |
0 |
0 |
3 |
0 |
0 |
0 |
| qwen1.5-7b-chat |
0 |
0 |
0 |
3 |
0 |
0 |
0 |
| qwen2-1.5b-instruct |
0 |
0 |
0 |
4 |
0 |
0 |
0 |
| qwen2-0.5b-instruct |
0 |
0 |
0 |
5 |
0 |
0 |
0 |
| qwen1.5-0.5b-chat |
0 |
0 |
0 |
5 |
0 |
0 |
0 |
| mistralai_mistral_7b_instruct_v0.2 |
0 |
0 |
0 |
4 |
0 |
0 |
0 |
| mistralai_ministral_8b_instruct_2410 |
0 |
0 |
0 |
4 |
0 |
0 |
0 |
| mistralai_mistral_7b_instruct_v0.3 |
0 |
0 |
0 |
4 |
0 |
0 |
0 |
| mistralai_mistral_7b_instruct_v0.1 |
0 |
0 |
0 |
4 |
0 |
0 |
0 |
| qwen1.5-72b-chat |
0 |
0 |
0 |
2 |
0 |
0 |
0 |
| qwen1.5-32b-chat |
0 |
0 |
0 |
3 |
0 |
0 |
0 |
| qwen1.5-1.8b-chat |
0 |
0 |
0 |
3 |
0 |
0 |
0 |
| qwen2-7b-instruct |
0 |
0 |
0 |
4 |
0 |
0 |
0 |
| qwen3-0.6b |
0 |
0 |
0 |
5 |
0 |
0 |
0 |