| qwen2.5-coder-14b-instruct |
43.2 |
62.6 |
30.9 |
12 |
1.6 |
1.3 |
0.88 |
| qwen3-14b |
38 |
56 |
26.2 |
12 |
1.5 |
1.3 |
0.77 |
| qwen2.5-coder-7b-instruct |
35.7 |
57.6 |
24.5 |
10 |
1.5 |
1.2 |
0.92 |
| google_gemma_3_12b_it |
32.8 |
42.4 |
21.5 |
11 |
1.5 |
1.4 |
0.57 |
| qwen3-8b |
31.2 |
50.3 |
20.3 |
12 |
1.5 |
1.2 |
0.79 |
| qwen3-4b |
28.9 |
47.3 |
18.5 |
12 |
1.4 |
1.2 |
0.79 |
| mistralai_ministral_8b_instruct_2410 |
24.7 |
49.5 |
15.3 |
11 |
1.4 |
1 |
0.9 |
| qwen2.5-coder-3b-instruct |
23.8 |
48.3 |
14.6 |
12 |
1.3 |
1 |
0.89 |
| qwen2-7b-instruct |
23.6 |
42.9 |
14.4 |
11 |
1.3 |
1.1 |
0.79 |
| mistralai_mathstral_7b_v0.1 |
22.6 |
48.2 |
13.7 |
11 |
1.3 |
0.97 |
0.89 |
| llama-3.1-8B-instruct |
22.3 |
22.6 |
13.6 |
15 |
1.3 |
1.3 |
0.15 |
| google_codegemma_1.1_7b_it |
20.9 |
43.9 |
12.7 |
13 |
1.3 |
0.97 |
0.84 |
| qwen1.5-14b-chat |
20.5 |
40.5 |
12.3 |
12 |
1.3 |
1 |
0.77 |
| qwen2-math-7b-instruct |
20.2 |
35.4 |
12.2 |
6 |
1.3 |
1 |
0.79 |
| google_gemma_3_4b_it |
19.5 |
29.4 |
11.2 |
13 |
1.3 |
1.1 |
0.56 |
| mistralai_mistral_7b_instruct_v0.3 |
18.2 |
36 |
10.5 |
11 |
1.2 |
0.98 |
0.73 |
| deepseek_v2_lite_chat |
17.4 |
39.8 |
10.2 |
11 |
1.2 |
0.88 |
0.81 |
| deepseek_r1_distill_qwen_14b |
16.1 |
39.2 |
9.82 |
11 |
1.2 |
0.82 |
0.83 |
| qwen3-1.7b |
15.2 |
28.6 |
8.08 |
12 |
1.1 |
0.97 |
0.58 |
| deepseek_r1_distill_qwen_7b |
14.8 |
35.7 |
8.42 |
11 |
1.1 |
0.81 |
0.78 |
| qwen2.5-coder-1.5b-instruct |
14.1 |
38.5 |
8.14 |
11 |
1.1 |
0.7 |
0.85 |
| mistralai_mistral_7b_instruct_v0.2 |
13.6 |
29.1 |
7.55 |
10 |
1.1 |
0.85 |
0.67 |
| google_gemma_2_9b_it |
10.6 |
22.6 |
5.6 |
12 |
0.97 |
0.83 |
0.51 |
| llama-3.2-3B-instruct |
10.1 |
10.2 |
5.18 |
17 |
0.95 |
0.95 |
0.072 |
| mistralai_mistral_7b_instruct_v0.1 |
9.23 |
24.7 |
4.58 |
11 |
0.92 |
0.65 |
0.65 |
| qwen1.5-7b-chat |
8.67 |
26.2 |
4.54 |
12 |
0.89 |
0.62 |
0.64 |
| qwen3-0.6b |
7.42 |
19.6 |
3.48 |
13 |
0.83 |
0.63 |
0.54 |
| deepseek_r1_distill_llama_8b |
6.85 |
22.1 |
3.71 |
13 |
0.8 |
0.54 |
0.59 |
| qwen2-1.5b-instruct |
5.78 |
21.1 |
2.68 |
13 |
0.74 |
0.47 |
0.57 |
| google_gemma_7b_it |
4.75 |
8.8 |
1.94 |
13 |
0.67 |
0.6 |
0.3 |
| llama-3.2-1B-instruct |
4.58 |
4.6 |
2.16 |
12 |
0.66 |
0.66 |
0.039 |
| qwen2.5-coder-0.5b-instruct |
4.55 |
17.3 |
2.07 |
13 |
0.66 |
0.38 |
0.53 |
| qwen2-math-1.5b-instruct |
4.08 |
10.6 |
2.21 |
4 |
0.63 |
0.34 |
0.52 |
| google_gemma_3_1b_it |
3.83 |
8.2 |
1.65 |
13 |
0.61 |
0.5 |
0.34 |
| qwen2-0.5b-instruct |
2.2 |
9.7 |
0.906 |
13 |
0.46 |
0.27 |
0.37 |
| deepseek_r1_distill_qwen_1.5b |
1.78 |
9.1 |
0.971 |
13 |
0.42 |
0.22 |
0.35 |
| qwen1.5-1.8b-chat |
1.37 |
7.9 |
0.6 |
12 |
0.37 |
0.17 |
0.32 |
| google_gemma_2b_it |
0.385 |
2.2 |
0.17 |
13 |
0.2 |
0.096 |
0.17 |
| qwen1.5-0.5b-chat |
0.354 |
2.4 |
0.13 |
13 |
0.19 |
0.071 |
0.17 |