| qwen3-32b |
26.8 |
45.6 |
22.8 |
3 |
2 |
1.2 |
1.5 |
| google_gemma_3_12b_it |
26.1 |
45.4 |
21.9 |
4 |
1.9 |
1.4 |
1.4 |
| qwen3-14b |
25.8 |
41.7 |
21.7 |
3 |
1.9 |
1.3 |
1.4 |
| qwen3-4b |
22.3 |
41 |
18.5 |
4 |
1.8 |
1.3 |
1.3 |
| qwen2-72b-instruct |
22.1 |
32.6 |
18.5 |
2 |
1.8 |
1.1 |
1.4 |
| qwen2.5-coder-32b-instruct |
21.2 |
31.3 |
17.5 |
2 |
1.8 |
1.1 |
1.4 |
| qwen3-8b |
18.8 |
33.6 |
15.6 |
3 |
1.7 |
1.1 |
1.3 |
| qwen2.5-coder-14b-instruct |
15.1 |
29.9 |
12.3 |
3 |
1.6 |
0.88 |
1.3 |
| qwen1.5-32b-chat |
14.6 |
28.2 |
12.1 |
3 |
1.6 |
0.91 |
1.3 |
| google_gemma_2_27b_it |
13.2 |
19.4 |
11 |
2 |
1.5 |
1 |
1.1 |
| qwen1.5-72b-chat |
13 |
20.8 |
10.7 |
2 |
1.5 |
0.83 |
1.2 |
| google_gemma_7b_it |
11.9 |
23.3 |
10.1 |
4 |
1.4 |
1 |
1 |
| google_gemma_3_4b_it |
11.5 |
28.9 |
9.42 |
5 |
1.4 |
0.87 |
1.1 |
| google_gemma_2_9b_it |
9.13 |
21 |
7.57 |
4 |
1.3 |
0.78 |
1 |
| qwen2.5-coder-7b-instruct |
8.74 |
23.3 |
7.02 |
4 |
1.2 |
0.57 |
1.1 |
| qwen1.5-14b-chat |
8.61 |
19 |
7.1 |
3 |
1.2 |
0.65 |
1.1 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
8.48 |
18.3 |
6.71 |
3 |
1.2 |
0.64 |
1 |
| qwen2-math-72b-instruct |
7.96 |
11.7 |
6.29 |
2 |
1.2 |
0.84 |
0.85 |
| qwen3-1.7b |
6.99 |
15.1 |
5.5 |
4 |
1.1 |
0.72 |
0.86 |
| llama-3.1-8B-instruct |
6.6 |
6.6 |
5.52 |
7 |
1.1 |
1.1 |
0 |
| google_codegemma_1.1_7b_it |
6.33 |
21.9 |
5.16 |
5 |
1.1 |
0.4 |
0.99 |
| mistralai_mistral_7b_instruct_v0.2 |
6.17 |
18.3 |
5.21 |
4 |
1.1 |
0.46 |
0.96 |
| mistralai_mistral_7b_instruct_v0.3 |
6.12 |
16.9 |
4.97 |
4 |
1.1 |
0.51 |
0.92 |
| qwen2-7b-instruct |
6.02 |
18.8 |
4.82 |
4 |
1 |
0.37 |
0.98 |
| qwen2-1.5b-instruct |
5.63 |
17.1 |
4.91 |
4 |
1 |
0.38 |
0.94 |
| qwen2-math-7b-instruct |
5.63 |
8.93 |
4.32 |
2 |
1 |
0.63 |
0.8 |
| qwen1.5-7b-chat |
5.44 |
14.2 |
4.55 |
3 |
1 |
0.31 |
0.95 |
| deepseek_v2_lite_chat |
5.37 |
13.8 |
4.53 |
3 |
0.99 |
0.33 |
0.94 |
| deepseek_r1_distill_qwen_14b |
5.1 |
12 |
3.87 |
4 |
0.97 |
0.57 |
0.79 |
| qwen2.5-coder-3b-instruct |
4.76 |
14.2 |
3.84 |
4 |
0.94 |
0.39 |
0.85 |
| llama-3.2-3B-instruct |
4.66 |
4.66 |
3.86 |
10 |
0.93 |
0.93 |
0 |
| llama-3.2-1B-instruct |
4.66 |
4.66 |
3.9 |
13 |
0.93 |
0.93 |
0 |
| deepseek_r1_distill_qwen_32b |
4.66 |
7.96 |
3.54 |
2 |
0.93 |
0.47 |
0.8 |
| google_gemma_3_1b_it |
4.56 |
11.7 |
3.57 |
4 |
0.92 |
0.52 |
0.76 |
| google_gemma_2b_it |
4.47 |
9.71 |
3.71 |
4 |
0.91 |
0.62 |
0.66 |
| deepseek_r1_distill_llama_70b |
4.37 |
6.6 |
3.31 |
2 |
0.9 |
0.61 |
0.66 |
| mistralai_mathstral_7b_v0.1 |
4.27 |
13.4 |
3.42 |
4 |
0.89 |
0.34 |
0.82 |
| mistralai_ministral_8b_instruct_2410 |
3.83 |
12.8 |
3.05 |
4 |
0.85 |
0.27 |
0.8 |
| qwen2-math-1.5b-instruct |
3.56 |
7.38 |
2.63 |
3 |
0.82 |
0.5 |
0.64 |
| qwen1.5-1.8b-chat |
3.43 |
8.54 |
2.83 |
3 |
0.8 |
0.3 |
0.74 |
| qwen3-0.6b |
3.18 |
11.3 |
2.45 |
5 |
0.77 |
0.35 |
0.69 |
| qwen2-0.5b-instruct |
3.15 |
12 |
2.7 |
5 |
0.77 |
0.24 |
0.73 |
| mistralai_mistral_7b_instruct_v0.1 |
3.11 |
9.9 |
2.58 |
4 |
0.76 |
0.26 |
0.72 |
| deepseek_r1_distill_qwen_7b |
2.77 |
6.02 |
2.01 |
4 |
0.72 |
0.48 |
0.54 |
| deepseek_r1_distill_llama_8b |
1.89 |
5.63 |
1.43 |
4 |
0.6 |
0.27 |
0.53 |
| qwen2.5-coder-0.5b-instruct |
1.86 |
7.18 |
1.47 |
5 |
0.6 |
0.21 |
0.56 |
| qwen1.5-0.5b-chat |
1.86 |
8.16 |
1.56 |
5 |
0.6 |
0.14 |
0.58 |
| qwen2.5-coder-1.5b-instruct |
1.8 |
6.21 |
1.39 |
4 |
0.59 |
0.19 |
0.55 |
| deepseek_r1_distill_qwen_1.5b |
1.21 |
3.88 |
0.865 |
4 |
0.48 |
0.19 |
0.44 |