| qwen3-32b |
78.5 |
85.9 |
35.4 |
2 |
2 |
1.5 |
1.3 |
| qwen3-14b |
75.2 |
83.6 |
32.8 |
3 |
2.2 |
1.8 |
1.2 |
| qwen2-72b-instruct |
74.7 |
74.7 |
33 |
1 |
2.2 |
NaN |
NaN |
| llama-3.1-70B-instruct |
73.9 |
73.9 |
32.6 |
4 |
2.2 |
2.2 |
0 |
| qwen3-8b |
72.1 |
84.9 |
31 |
3 |
2.2 |
1.7 |
1.4 |
| deepseek_r1_distill_llama_70b |
72 |
76.4 |
30.5 |
2 |
2.2 |
2 |
1.1 |
| qwen3-4b |
69.9 |
82.6 |
29.9 |
4 |
2.3 |
1.8 |
1.3 |
| deepseek_r1_distill_qwen_32b |
68.7 |
75.9 |
28.8 |
2 |
2.3 |
1.9 |
1.3 |
| qwen2.5-coder-32b-instruct |
68.6 |
76.2 |
28.8 |
2 |
2.3 |
1.9 |
1.4 |
| google_gemma_3_12b_it |
68.2 |
74.9 |
28.5 |
2 |
2.3 |
1.9 |
1.3 |
| deepseek_r1_distill_qwen_14b |
64.1 |
78.9 |
25.9 |
4 |
2.4 |
1.8 |
1.5 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
63.8 |
71.2 |
25.7 |
2 |
2.4 |
2 |
1.4 |
| qwen2.5-coder-14b-instruct |
61 |
74.9 |
24.3 |
3 |
2.4 |
1.9 |
1.5 |
| qwen1.5-14b-chat |
57.6 |
67.5 |
22.4 |
3 |
2.5 |
2.1 |
1.2 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
57.5 |
65 |
22.1 |
3 |
2.5 |
2.2 |
1 |
| qwen2-7b-instruct |
56.5 |
72 |
21.9 |
4 |
2.5 |
2 |
1.4 |
| qwen2.5-coder-7b-instruct |
53.4 |
70.5 |
20.3 |
4 |
2.5 |
2 |
1.5 |
| llama-3.1-8B-instruct |
51.9 |
51.9 |
20 |
7 |
2.5 |
2.5 |
0 |
| qwen3-1.7b |
50.7 |
73.4 |
20.1 |
4 |
2.5 |
1.8 |
1.7 |
| qwen1.5-7b-chat |
49.1 |
61.8 |
18.3 |
3 |
2.5 |
2.1 |
1.4 |
| mistralai_mistral_7b_instruct_v0.3 |
48.9 |
63.5 |
17.8 |
4 |
2.5 |
2.1 |
1.3 |
| google_gemma_3_4b_it |
47.3 |
67.7 |
18.1 |
5 |
2.5 |
2 |
1.5 |
| mistralai_mistral_7b_instruct_v0.2 |
47 |
53.1 |
17.5 |
4 |
2.5 |
2.3 |
0.92 |
| mistralai_mathstral_7b_v0.1 |
46.5 |
71.5 |
18.1 |
4 |
2.5 |
1.7 |
1.8 |
| mistralai_ministral_8b_instruct_2410 |
46 |
74.9 |
17.5 |
4 |
2.5 |
1.5 |
2 |
| deepseek_v2_lite_chat |
44.5 |
56.1 |
17.1 |
2 |
2.5 |
1.8 |
1.7 |
| deepseek_r1_distill_llama_8b |
43.9 |
73.7 |
16.3 |
4 |
2.5 |
1.5 |
1.9 |
| llama-3.2-3B-instruct |
43.9 |
43.9 |
16.7 |
8 |
2.5 |
2.5 |
0 |
| deepseek_r1_distill_qwen_7b |
41.4 |
67.7 |
15.7 |
4 |
2.5 |
1.5 |
1.9 |
| qwen2-math-7b-instruct |
40.5 |
60.8 |
15.9 |
3 |
2.4 |
1.7 |
1.8 |
| qwen2.5-coder-3b-instruct |
35.7 |
69 |
13.7 |
4 |
2.4 |
1.3 |
2 |
| qwen3-0.6b |
35 |
56.6 |
13.7 |
5 |
2.4 |
1.8 |
1.5 |
| mistralai_mistral_7b_instruct_v0.1 |
34 |
66.3 |
13 |
4 |
2.4 |
1.3 |
1.9 |
| qwen2-1.5b-instruct |
32.3 |
62.5 |
12.3 |
4 |
2.3 |
1.4 |
1.9 |
| llama-3.2-1B-instruct |
27 |
27 |
11.3 |
11 |
2.2 |
2.2 |
0 |
| qwen2.5-coder-1.5b-instruct |
25.8 |
62.8 |
11.3 |
4 |
2.2 |
0.85 |
2 |
| qwen1.5-1.8b-chat |
25.8 |
48.9 |
10.6 |
3 |
2.2 |
1.1 |
1.9 |
| qwen2-math-1.5b-instruct |
22 |
45.2 |
9.81 |
3 |
2.1 |
0.98 |
1.8 |
| qwen2.5-coder-0.5b-instruct |
20.3 |
67.5 |
9.97 |
5 |
2 |
0.077 |
2 |
| deepseek_r1_distill_qwen_1.5b |
20.3 |
50.6 |
8.72 |
4 |
2 |
0.79 |
1.8 |
| qwen2-0.5b-instruct |
19.8 |
61 |
9.09 |
5 |
2 |
0.6 |
1.9 |
| qwen1.5-0.5b-chat |
19.2 |
61.8 |
9.3 |
5 |
2 |
0.42 |
1.9 |