| qwen3-32b |
69 |
76.1 |
39.3 |
2 |
0.42 |
0.34 |
0.24 |
| qwen3-14b |
67.2 |
72.9 |
37.8 |
2 |
0.43 |
0.37 |
0.22 |
| qwen3-8b |
62.5 |
68.7 |
34.2 |
2 |
0.44 |
0.38 |
0.23 |
| llama-3.1-70B-instruct |
60.3 |
60.3 |
33.2 |
3 |
0.45 |
0.45 |
0 |
| qwen2-72b-instruct |
60.1 |
60.1 |
32.7 |
1 |
0.45 |
NaN |
NaN |
| qwen2.5-coder-32b-instruct |
59.3 |
59.3 |
31.9 |
1 |
0.45 |
NaN |
NaN |
| google_gemma_3_12b_it |
58.4 |
69.1 |
31.2 |
3 |
0.45 |
0.38 |
0.24 |
| qwen3-4b |
57.7 |
67.3 |
31 |
3 |
0.45 |
0.39 |
0.23 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
47.1 |
60.1 |
23.9 |
2 |
0.46 |
0.31 |
0.33 |
| deepseek_r1_distill_qwen_32b |
46.6 |
46.6 |
23.2 |
1 |
0.45 |
NaN |
NaN |
| qwen1.5-72b-chat |
46.5 |
46.5 |
23.7 |
1 |
0.45 |
NaN |
NaN |
| deepseek_r1_distill_qwen_14b |
44.7 |
60.2 |
22 |
3 |
0.45 |
0.34 |
0.29 |
| qwen2-math-72b-instruct |
44.4 |
44.4 |
22.6 |
1 |
0.45 |
NaN |
NaN |
| qwen2.5-coder-14b-instruct |
43.3 |
57.3 |
21.5 |
2 |
0.45 |
0.3 |
0.34 |
| qwen1.5-32b-chat |
43.3 |
56 |
21.5 |
2 |
0.45 |
0.31 |
0.33 |
| qwen3-1.7b |
42.4 |
56.2 |
21.3 |
3 |
0.45 |
0.36 |
0.27 |
| google_gemma_3_4b_it |
41.5 |
57.1 |
20.2 |
4 |
0.45 |
0.37 |
0.26 |
| qwen2-7b-instruct |
41 |
59.8 |
20 |
3 |
0.45 |
0.32 |
0.32 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
38.4 |
51.1 |
19 |
2 |
0.44 |
0.3 |
0.33 |
| llama-3.1-8B-instruct |
37.5 |
37.5 |
18.1 |
7 |
0.44 |
0.44 |
0 |
| qwen1.5-14b-chat |
36 |
47.1 |
17.1 |
2 |
0.44 |
0.31 |
0.3 |
| mistralai_ministral_8b_instruct_2410 |
32.8 |
53.9 |
15.4 |
3 |
0.43 |
0.27 |
0.33 |
| deepseek_r1_distill_llama_8b |
32.4 |
49.1 |
14.5 |
3 |
0.43 |
0.3 |
0.3 |
| qwen2.5-coder-7b-instruct |
32.1 |
53.6 |
15.2 |
3 |
0.43 |
0.26 |
0.33 |
| deepseek_r1_distill_qwen_7b |
31.5 |
47.9 |
14.5 |
3 |
0.42 |
0.3 |
0.3 |
| mistralai_mistral_7b_instruct_v0.3 |
31.3 |
49.6 |
14.7 |
3 |
0.42 |
0.29 |
0.31 |
| mistralai_mathstral_7b_v0.1 |
29.7 |
52.1 |
14 |
3 |
0.42 |
0.24 |
0.34 |
| llama-3.2-3B-instruct |
29.2 |
29.2 |
13.8 |
10 |
0.41 |
0.41 |
0 |
| qwen2-math-7b-instruct |
29 |
49.9 |
14.3 |
3 |
0.41 |
0.25 |
0.33 |
| mistralai_mistral_7b_instruct_v0.2 |
27.9 |
44.3 |
12.9 |
3 |
0.41 |
0.29 |
0.29 |
| google_codegemma_1.1_7b_it |
27 |
27 |
12.7 |
1 |
0.4 |
NaN |
NaN |
| deepseek_v2_lite_chat |
26.1 |
37.8 |
12 |
2 |
0.4 |
0.25 |
0.31 |
| qwen2.5-coder-3b-instruct |
25.9 |
46.5 |
12 |
3 |
0.4 |
0.24 |
0.32 |
| qwen1.5-7b-chat |
23.1 |
41.7 |
10.5 |
3 |
0.38 |
0.23 |
0.31 |
| qwen3-0.6b |
23 |
42.9 |
11.6 |
4 |
0.38 |
0.26 |
0.28 |
| mistralai_mistral_7b_instruct_v0.1 |
19 |
37.5 |
8.87 |
3 |
0.36 |
0.2 |
0.3 |
| qwen2.5-coder-1.5b-instruct |
16.9 |
35.1 |
8.11 |
3 |
0.34 |
0.17 |
0.3 |
| qwen2-math-1.5b-instruct |
16.6 |
34 |
8.31 |
3 |
0.34 |
0.17 |
0.29 |
| llama-3.2-1B-instruct |
16.5 |
16.5 |
8.09 |
12 |
0.34 |
0.34 |
0 |
| deepseek_r1_distill_qwen_1.5b |
15.9 |
31.7 |
7.17 |
3 |
0.33 |
0.18 |
0.28 |
| qwen2-1.5b-instruct |
11.6 |
26.8 |
5.82 |
3 |
0.29 |
0.12 |
0.27 |
| qwen2-0.5b-instruct |
9.51 |
28.8 |
5.55 |
4 |
0.27 |
0.091 |
0.25 |
| qwen2.5-coder-0.5b-instruct |
9.26 |
28.8 |
5.62 |
4 |
0.26 |
0.077 |
0.25 |
| qwen1.5-1.8b-chat |
8.84 |
20.7 |
4.47 |
3 |
0.26 |
0.11 |
0.23 |
| qwen1.5-0.5b-chat |
5.49 |
19.1 |
3.24 |
4 |
0.21 |
0.042 |
0.2 |