| qwen3-32b |
50.2 |
62.9 |
33.6 |
2 |
2.4 |
1.7 |
1.7 |
| google_gemma_3_27b_it |
47.3 |
47.3 |
31.8 |
1 |
2.4 |
NaN |
NaN |
| llama-3.1-70B-instruct |
45.3 |
45.3 |
30.4 |
4 |
2.4 |
2.4 |
0 |
| qwen3-14b |
43.2 |
59.6 |
27.9 |
3 |
2.3 |
1.8 |
1.5 |
| qwen2.5-coder-32b-instruct |
39.7 |
52.5 |
25.5 |
2 |
2.3 |
1.6 |
1.7 |
| qwen3-8b |
39 |
54 |
24.8 |
3 |
2.3 |
1.8 |
1.5 |
| qwen2-72b-instruct |
36.5 |
48 |
23 |
2 |
2.3 |
1.6 |
1.6 |
| qwen3-4b |
35.8 |
51.3 |
22.7 |
4 |
2.3 |
1.8 |
1.3 |
| qwen2-math-72b-instruct |
35.3 |
52.5 |
22.7 |
2 |
2.3 |
1.1 |
2 |
| google_gemma_3_12b_it |
35 |
57.1 |
22.6 |
4 |
2.3 |
1.6 |
1.6 |
| qwen1.5-32b-chat |
32.3 |
45.8 |
20.2 |
2 |
2.2 |
1.4 |
1.7 |
| qwen3-1.7b |
32.1 |
53.6 |
21.1 |
4 |
2.2 |
1.6 |
1.5 |
| qwen2.5-coder-14b-instruct |
31.8 |
56 |
20 |
3 |
2.2 |
1.3 |
1.8 |
| llama-3.1-8B-instruct |
31.7 |
31.7 |
20.4 |
7 |
2.2 |
2.2 |
0 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
31.6 |
46.2 |
19.9 |
2 |
2.2 |
1.2 |
1.8 |
| google_gemma_2_9b_it |
30.6 |
46.4 |
18.8 |
3 |
2.2 |
1.6 |
1.5 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
30.4 |
52.2 |
19.5 |
3 |
2.2 |
1.3 |
1.8 |
| qwen1.5-72b-chat |
30.2 |
42.4 |
19 |
2 |
2.2 |
1.4 |
1.6 |
| google_gemma_3_4b_it |
30 |
56.5 |
19.6 |
5 |
2.2 |
1.5 |
1.6 |
| mistralai_mathstral_7b_v0.1 |
29.7 |
63.6 |
19.3 |
4 |
2.2 |
0.99 |
1.9 |
| qwen2-math-7b-instruct |
27.9 |
63.4 |
18.9 |
4 |
2.1 |
0.87 |
1.9 |
| qwen1.5-14b-chat |
27.7 |
48.4 |
17.8 |
3 |
2.1 |
1.3 |
1.7 |
| google_codegemma_1.1_7b_it |
27.1 |
63.2 |
18.3 |
5 |
2.1 |
1 |
1.8 |
| qwen2.5-coder-7b-instruct |
26.7 |
61.8 |
17.5 |
4 |
2.1 |
0.9 |
1.9 |
| mistralai_ministral_8b_instruct_2410 |
26.5 |
59.2 |
17.2 |
4 |
2.1 |
0.97 |
1.8 |
| mistralai_mistral_7b_instruct_v0.3 |
26.5 |
55.4 |
16.8 |
4 |
2.1 |
1.2 |
1.7 |
| deepseek_r1_distill_qwen_32b |
26.3 |
33.5 |
15.9 |
2 |
2.1 |
1.7 |
1.3 |
| llama-3.2-3B-instruct |
26.1 |
26.1 |
17.4 |
10 |
2.1 |
2.1 |
0 |
| google_gemma_7b_it |
26.1 |
45.5 |
17.4 |
4 |
2.1 |
1.4 |
1.5 |
| qwen2.5-coder-3b-instruct |
25.7 |
64.7 |
17.8 |
4 |
2.1 |
0.53 |
2 |
| deepseek_v2_lite_chat |
24.6 |
39.5 |
16.5 |
2 |
2 |
0.89 |
1.8 |
| google_gemma_3_1b_it |
24.4 |
54.2 |
17.1 |
4 |
2 |
0.99 |
1.8 |
| qwen2-7b-instruct |
24.2 |
50.9 |
15.2 |
4 |
2 |
1.2 |
1.7 |
| qwen3-0.6b |
23.5 |
56.7 |
16.2 |
5 |
2 |
1.1 |
1.7 |
| deepseek_r1_distill_qwen_14b |
23.2 |
36.4 |
13.7 |
4 |
2 |
1.6 |
1.2 |
| qwen1.5-7b-chat |
22.9 |
47.8 |
15.2 |
3 |
2 |
0.82 |
1.8 |
| mistralai_mistral_7b_instruct_v0.2 |
21.7 |
50.7 |
14.1 |
4 |
1.9 |
0.97 |
1.7 |
| mistralai_mistral_7b_instruct_v0.1 |
21.3 |
56.9 |
14.8 |
4 |
1.9 |
0.58 |
1.8 |
| deepseek_r1_distill_llama_70b |
20.4 |
25.4 |
12 |
2 |
1.9 |
1.6 |
1.1 |
| deepseek_r1_distill_llama_8b |
19.8 |
33.7 |
11.5 |
4 |
1.9 |
1.4 |
1.2 |
| deepseek_r1_distill_qwen_7b |
19.7 |
31.9 |
11.5 |
4 |
1.9 |
1.4 |
1.2 |
| qwen2-math-1.5b-instruct |
17.3 |
49.3 |
12.1 |
4 |
1.8 |
0.54 |
1.7 |
| qwen2.5-coder-0.5b-instruct |
16.2 |
58.3 |
11.8 |
5 |
1.7 |
0 |
1.7 |
| qwen2.5-coder-1.5b-instruct |
16.2 |
49.8 |
11.5 |
4 |
1.7 |
0.22 |
1.7 |
| google_gemma_2b_it |
12.3 |
33 |
8.69 |
4 |
1.6 |
0.67 |
1.4 |
| qwen2-1.5b-instruct |
11 |
35.5 |
7.72 |
4 |
1.5 |
0.38 |
1.4 |
| llama-3.2-1B-instruct |
10.9 |
10.9 |
7.96 |
13 |
1.5 |
1.5 |
0 |
| deepseek_r1_distill_qwen_1.5b |
9.6 |
22.3 |
5.59 |
4 |
1.4 |
0.8 |
1.1 |
| qwen1.5-1.8b-chat |
8.04 |
23 |
5.81 |
3 |
1.3 |
0 |
1.3 |
| qwen2-0.5b-instruct |
7.81 |
33 |
5.68 |
5 |
1.3 |
0 |
1.3 |
| qwen1.5-0.5b-chat |
1.88 |
8.48 |
1.37 |
5 |
0.64 |
0.11 |
0.63 |