| google_gemma_3_27b_it |
89.2 |
93.1 |
43.5 |
3 |
0.59 |
0.5 |
0.32 |
| qwen3-32b |
89 |
92.6 |
43.3 |
2.3 |
0.6 |
NaN |
NaN |
| google_gemma_3_12b_it |
86.2 |
91.4 |
41.2 |
3.4 |
0.66 |
NaN |
NaN |
| deepseek_r1_distill_llama_70b |
85.8 |
91.7 |
41.2 |
2.2 |
0.67 |
NaN |
NaN |
| qwen3-14b |
84.4 |
90.1 |
39.6 |
3 |
0.69 |
0.58 |
0.38 |
| google_gemma_2_27b_it |
82.5 |
82.5 |
38.8 |
1 |
0.73 |
NaN |
NaN |
| qwen3-8b |
80.1 |
87.8 |
36.5 |
3 |
0.76 |
0.62 |
0.44 |
| qwen2-72b-instruct |
79.4 |
85.7 |
35.9 |
2.2 |
0.77 |
NaN |
NaN |
| deepseek_r1_distill_qwen_32b |
79.4 |
86.1 |
36.1 |
2.2 |
0.77 |
NaN |
NaN |
| google_gemma_2_9b_it |
77.8 |
87.5 |
35.5 |
3 |
0.79 |
0.62 |
0.49 |
| qwen2.5-coder-32b-instruct |
77.3 |
84.2 |
34.6 |
2.2 |
0.8 |
NaN |
NaN |
| llama-3.1-70B-instruct |
77 |
77 |
35.8 |
4 |
0.8 |
0.8 |
0 |
| qwen3-4b |
73.7 |
83.1 |
32.1 |
4 |
0.84 |
0.71 |
0.44 |
| qwen2-math-72b-instruct |
73.7 |
83.4 |
32.7 |
2.2 |
0.84 |
NaN |
NaN |
| deepseek_r1_distill_qwen_14b |
73.7 |
84 |
32.3 |
3.4 |
0.84 |
NaN |
NaN |
| google_gemma_3_4b_it |
71.2 |
85.1 |
31.3 |
4 |
0.86 |
0.66 |
0.55 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
68 |
78.7 |
28.9 |
2.3 |
0.89 |
NaN |
NaN |
| qwen2.5-coder-14b-instruct |
64.9 |
79.6 |
26.9 |
3 |
0.91 |
0.67 |
0.61 |
| qwen1.5-72b-chat |
63.7 |
74.7 |
26 |
2.2 |
0.92 |
NaN |
NaN |
| qwen1.5-32b-chat |
58.6 |
70.7 |
23.5 |
2.3 |
0.94 |
NaN |
NaN |
| deepseek_r1_distill_qwen_7b |
58 |
73.9 |
22.9 |
3.4 |
0.94 |
NaN |
NaN |
| qwen3-1.7b |
54.9 |
70.2 |
21.1 |
4 |
0.95 |
0.77 |
0.56 |
| qwen2-7b-instruct |
52.6 |
70.1 |
19.9 |
3.4 |
0.95 |
NaN |
NaN |
| mistralai_ministral_8b_instruct_2410 |
51 |
69.1 |
19.2 |
3.4 |
0.95 |
NaN |
NaN |
| mistralai_mathstral_7b_v0.1 |
50.9 |
72.9 |
20.1 |
3.4 |
0.95 |
NaN |
NaN |
| qwen2.5-coder-7b-instruct |
50.8 |
69.1 |
18.9 |
3.4 |
0.95 |
NaN |
NaN |
| mistralai_mixtral_8x7b_instruct_v0.1 |
44.4 |
64.4 |
16.7 |
3 |
0.95 |
0.64 |
0.7 |
| llama-3.1-8B-instruct |
44 |
44 |
16.8 |
7 |
0.95 |
0.95 |
0 |
| qwen1.5-14b-chat |
43.5 |
61.5 |
15.6 |
3 |
0.95 |
0.67 |
0.66 |
| qwen2-math-7b-instruct |
43.3 |
65.1 |
15.4 |
4 |
0.94 |
0.68 |
0.66 |
| deepseek_r1_distill_llama_8b |
40.4 |
62.6 |
14.2 |
4 |
0.94 |
0.66 |
0.67 |
| google_codegemma_1.1_7b_it |
38.4 |
62.4 |
14 |
4 |
0.93 |
0.63 |
0.68 |
| deepseek_v2_lite_chat |
37.2 |
52.5 |
13 |
2.3 |
0.92 |
NaN |
NaN |
| llama-3.2-3B-instruct |
35.2 |
35.2 |
12.6 |
10 |
0.91 |
0.91 |
0 |
| qwen2.5-coder-3b-instruct |
34.3 |
57.6 |
11.5 |
4 |
0.91 |
0.61 |
0.67 |
| qwen1.5-7b-chat |
29.4 |
46.6 |
9.3 |
3 |
0.87 |
0.59 |
0.63 |
| deepseek_r1_distill_qwen_1.5b |
27.2 |
46 |
8.45 |
4 |
0.85 |
0.61 |
0.59 |
| google_gemma_3_1b_it |
26 |
45.5 |
8.38 |
4 |
0.84 |
0.6 |
0.59 |
| mistralai_mistral_7b_instruct_v0.3 |
24.5 |
44.7 |
7.91 |
3.4 |
0.82 |
NaN |
NaN |
| mistralai_mistral_7b_instruct_v0.2 |
23.9 |
43.2 |
7.99 |
3.4 |
0.81 |
NaN |
NaN |
| qwen3-0.6b |
21.9 |
39.9 |
6.84 |
4 |
0.79 |
0.55 |
0.57 |
| qwen2-math-1.5b-instruct |
20 |
36.6 |
5.99 |
4 |
0.76 |
0.54 |
0.54 |
| google_gemma_7b_it |
17.8 |
33.2 |
5.79 |
4 |
0.73 |
0.51 |
0.52 |
| qwen2.5-coder-1.5b-instruct |
17 |
36.1 |
4.89 |
4 |
0.72 |
0.43 |
0.57 |
| mistralai_mistral_7b_instruct_v0.1 |
12.1 |
26.3 |
3.48 |
3.4 |
0.62 |
NaN |
NaN |
| qwen2-1.5b-instruct |
8.15 |
21.9 |
2.3 |
4 |
0.52 |
0.26 |
0.46 |
| google_gemma_2b_it |
5.05 |
13.9 |
1.89 |
4 |
0.42 |
0.21 |
0.36 |
| qwen2.5-coder-0.5b-instruct |
3.46 |
10.7 |
1.08 |
4 |
0.35 |
0.14 |
0.32 |
| qwen1.5-1.8b-chat |
3.37 |
8.44 |
1.09 |
3 |
0.34 |
0.13 |
0.32 |
| qwen2-0.5b-instruct |
2.97 |
9.67 |
0.949 |
4 |
0.32 |
0.12 |
0.3 |
| qwen1.5-0.5b-chat |
1.42 |
5.09 |
0.6 |
4 |
0.23 |
0.055 |
0.22 |