| google_gemma_3_27b_it |
40.1 |
60 |
38.5 |
12 |
3.7 |
3.2 |
1.8 |
| google_gemma_2_27b_it |
20.1 |
47.2 |
19 |
10 |
3 |
1.8 |
2.4 |
| llama-3.1-8B-instruct |
18.3 |
20 |
17 |
15 |
2.9 |
2.7 |
0.91 |
| google_gemma_3_4b_it |
17.5 |
27.8 |
16.4 |
13 |
2.8 |
2.5 |
1.3 |
| google_gemma_2_9b_it |
16.8 |
36.7 |
15.7 |
11 |
2.8 |
2 |
2 |
| llama-3.2-3B-instruct |
9.74 |
10.6 |
8.93 |
17 |
2.2 |
2.1 |
0.64 |
| google_gemma_3_12b_it |
6.97 |
16.1 |
6.56 |
11 |
1.9 |
1.5 |
1.2 |
| google_codegemma_1.1_7b_it |
6.28 |
26.1 |
5.76 |
13 |
1.8 |
1.2 |
1.4 |
| llama-3.2-1B-instruct |
4.03 |
4.44 |
3.64 |
12 |
1.5 |
1.4 |
0.46 |
| google_gemma_7b_it |
2.5 |
6.67 |
2.24 |
12 |
1.2 |
0.87 |
0.77 |
| mistralai_mixtral_8x22b_instruct_v0.1 |
0.859 |
8.33 |
0.795 |
11 |
0.69 |
0.084 |
0.68 |
| google_gemma_3_1b_it |
0.694 |
4.44 |
0.629 |
12 |
0.62 |
0.25 |
0.57 |
| google_gemma_2b_it |
0.641 |
3.33 |
0.565 |
13 |
0.59 |
0.24 |
0.54 |
| mistralai_mathstral_7b_v0.1 |
0.0505 |
0.556 |
0.0479 |
11 |
0.17 |
0 |
0.17 |
| qwen3-32b |
0.0505 |
0.556 |
0.048 |
11 |
0.17 |
0 |
0.17 |
| qwen2.5-coder-14b-instruct |
0.0463 |
0.556 |
0.044 |
12 |
0.16 |
0 |
0.16 |
| qwen2.5-coder-3b-instruct |
0.0463 |
0.556 |
0.0463 |
12 |
0.16 |
0 |
0.16 |
| deepseek_r1_distill_llama_70b |
0 |
0 |
0 |
9 |
0 |
0 |
0 |
| deepseek_r1_distill_qwen_1.5b |
0 |
0 |
0 |
12 |
0 |
0 |
0 |
| deepseek_v2_lite_chat |
0 |
0 |
0 |
11 |
0 |
0 |
0 |
| deepseek_r1_distill_qwen_7b |
0 |
0 |
0 |
11 |
0 |
0 |
0 |
| deepseek_r1_distill_qwen_32b |
0 |
0 |
0 |
9 |
0 |
0 |
0 |
| deepseek_r1_distill_qwen_14b |
0 |
0 |
0 |
11 |
0 |
0 |
0 |
| deepseek_r1_distill_llama_8b |
0 |
0 |
0 |
12 |
0 |
0 |
0 |
| mistralai_mistral_7b_instruct_v0.2 |
0 |
0 |
0 |
10 |
0 |
0 |
0 |
| mistralai_mistral_7b_instruct_v0.1 |
0 |
0 |
0 |
11 |
0 |
0 |
0 |
| mistralai_ministral_8b_instruct_2410 |
0 |
0 |
0 |
11 |
0 |
0 |
0 |
| qwen1.5-1.8b-chat |
0 |
0 |
0 |
11 |
0 |
0 |
0 |
| qwen1.5-14b-chat |
0 |
0 |
0 |
12 |
0 |
0 |
0 |
| qwen1.5-32b-chat |
0 |
0 |
0 |
11 |
0 |
0 |
0 |
| qwen1.5-72b-chat |
0 |
0 |
0 |
10 |
0 |
0 |
0 |
| qwen1.5-7b-chat |
0 |
0 |
0 |
12 |
0 |
0 |
0 |
| mistralai_mistral_7b_instruct_v0.3 |
0 |
0 |
0 |
11 |
0 |
0 |
0 |
| mistralai_mixtral_8x7b_instruct_v0.1 |
0 |
0 |
0 |
12 |
0 |
0 |
0 |
| qwen1.5-0.5b-chat |
0 |
0 |
0 |
13 |
0 |
0 |
0 |
| qwen2-72b-instruct |
0 |
0 |
0 |
10 |
0 |
0 |
0 |
| qwen2-1.5b-instruct |
0 |
0 |
0 |
13 |
0 |
0 |
0 |
| qwen2-0.5b-instruct |
0 |
0 |
0 |
13 |
0 |
0 |
0 |
| qwen2-7b-instruct |
0 |
0 |
0 |
11 |
0 |
0 |
0 |
| qwen2-math-7b-instruct |
0 |
0 |
0 |
6 |
0 |
0 |
0 |
| qwen2.5-coder-0.5b-instruct |
0 |
0 |
0 |
13 |
0 |
0 |
0 |
| qwen2-math-72b-instruct |
0 |
0 |
0 |
10 |
0 |
0 |
0 |
| qwen2-math-1.5b-instruct |
0 |
0 |
0 |
4 |
0 |
0 |
0 |
| qwen2.5-coder-32b-instruct |
0 |
0 |
0 |
10 |
0 |
0 |
0 |
| qwen2.5-coder-1.5b-instruct |
0 |
0 |
0 |
11 |
0 |
0 |
0 |
| qwen3-0.6b |
0 |
0 |
0 |
13 |
0 |
0 |
0 |
| qwen2.5-coder-7b-instruct |
0 |
0 |
0 |
10 |
0 |
0 |
0 |
| qwen3-1.7b |
0 |
0 |
0 |
12 |
0 |
0 |
0 |
| qwen3-14b |
0 |
0 |
0 |
12 |
0 |
0 |
0 |
| qwen3-4b |
0 |
0 |
0 |
12 |
0 |
0 |
0 |
| qwen3-8b |
0 |
0 |
0 |
12 |
0 |
0 |
0 |