gpt-4-0613 (few-shot, val) |
unknown |
100 |
8192 |
True |
597 ± 197 / 93 ± 33 |
1.21 |
1.15 |
1.14 |
1.14 |
1.45 |
1.19 |
1.19 |
1.23 |
64.94 ± 1.96 / 45.76 ± 3.31 |
59.97 ± 2.65 / 73.06 ± 1.77 |
71.56 ± 2.49 / 85.36 ± 1.29 |
56.43 ± 2.98 / 68.46 ± 1.64 |
66.76 ± 0.34 / 18.99 ± 0.52 |
94.93 ± 1.03 / 96.21 ± 0.77 |
93.98 ± 2.15 / 95.94 ± 1.44 |
81.64 ± 1.80 / 86.17 ± 1.34 |
81.16 ± 2.46 / 63.39 ± 4.07 |
75.75 ± 4.49 / 60.44 ± 5.46 |
72.72 ± 3.20 / 81.35 ± 2.22 |
65.92 ± 0.28 / 19.24 ± 0.59 |
77.30 ± 2.97 / 88.39 ± 1.60 |
57.18 ± 3.91 / 76.40 ± 2.66 |
47.50 ± 2.86 / 75.24 ± 1.32 |
68.77 ± 2.09 / 76.56 ± 1.57 |
88.30 ± 1.32 / 91.13 ± 0.98 |
76.86 ± 1.89 / 54.97 ± 4.44 |
79.19 ± 1.87 / 80.56 ± 1.82 |
80.93 ± 1.67 / 89.90 ± 0.93 |
53.81 ± 1.28 / 65.15 ± 1.11 |
67.83 ± 0.15 / 22.67 ± 0.39 |
72.53 ± 1.82 / 79.26 ± 1.44 |
85.67 ± 2.59 / 89.14 ± 2.05 |
78.67 ± 2.16 / 59.54 ± 4.85 |
33.65 ± 3.19 / 60.56 ± 2.35 |
32.25 ± 2.01 / 60.12 ± 1.31 |
69.21 ± 0.25 / 22.50 ± 0.53 |
86.32 ± 1.50 / 89.65 ± 1.16 |
74.02 ± 4.17 / 86.80 ± 2.02 |
69.48 ± 2.32 / 54.66 ± 2.17 |
64.91 ± 1.86 / 75.96 ± 1.59 |
50.23 ± 4.16 / 74.54 ± 2.10 |
33.17 ± 1.86 / 65.14 ± 1.53 |
66.35 ± 0.59 / 19.81 ± 1.46 |
71.92 ± 2.22 / 78.79 ± 1.65 |
82.85 ± 1.48 / 86.99 ± 1.12 |
73.35 ± 2.61 / 56.00 ± 2.82 |
18.92 ± 2.78 / 40.80 ± 2.43 |
76.70 ± 2.39 / 88.16 ± 1.21 |
55.03 ± 1.96 / 76.47 ± 1.22 |
69.97 ± 0.41 / 22.66 ± 0.68 |
70.71 ± 2.96 / 78.12 ± 2.24 |
90.07 ± 1.29 / 92.54 ± 0.98 |
78.06 ± 2.73 / 70.76 ± 3.80 |
69.06 ± 2.20 / 76.04 ± 1.60 |
55.76 ± 3.84 / 76.34 ± 1.44 |
67.35 ± 1.98 / 85.76 ± 0.77 |
70.54 ± 0.24 / 26.98 ± 0.49 |
72.27 ± 2.36 / 78.75 ± 1.88 |
91.51 ± 2.15 / 93.59 ± 1.62 |
0.0.0 |
0.0.0 |
0.0.0 |
12.9.0 |
12.6.1 |
10.0.1 |
10.0.1 |
9.1.2 |
0.0.0 |
0.0.0 |
0.0.0 |
9.3.2 |
0.0.0 |
0.0.0 |
12.9.0 |
9.3.2 |
9.3.2 |
0.0.0 |
0.0.0 |
0.0.0 |
12.9.0 |
9.3.2 |
9.3.2 |
9.3.2 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.8 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.2.0 |
12.1.0 |
12.2.0 |
12.2.0 |
12.5.2 |
12.5.2 |
12.5.2 |
gpt-4-1106-preview (few-shot, val) |
unknown |
100 |
128000 |
True |
576 ± 221 / 81 ± 28 |
1.28 |
1.22 |
1.27 |
1.22 |
1.14 |
1.36 |
1.50 |
1.22 |
66.80 ± 3.01 / 45.69 ± 2.85 |
61.62 ± 2.17 / 73.99 ± 1.48 |
66.84 ± 3.27 / 82.79 ± 1.86 |
56.85 ± 2.62 / 68.83 ± 1.50 |
66.21 ± 0.44 / 18.02 ± 0.61 |
95.21 ± 0.55 / 96.41 ± 0.41 |
97.19 ± 1.15 / 98.12 ± 0.76 |
78.74 ± 3.12 / 83.91 ± 2.42 |
77.48 ± 2.32 / 55.87 ± 2.83 |
78.70 ± 2.78 / 57.58 ± 4.23 |
62.55 ± 2.82 / 72.41 ± 2.42 |
63.60 ± 0.15 / 13.15 ± 0.35 |
74.45 ± 4.27 / 86.22 ± 2.49 |
56.31 ± 5.81 / 74.04 ± 4.03 |
44.67 ± 3.23 / 73.39 ± 1.83 |
70.84 ± 1.92 / 78.12 ± 1.44 |
86.30 ± 2.04 / 89.53 ± 1.60 |
74.45 ± 3.09 / 49.97 ± 4.23 |
77.59 ± 1.38 / 78.78 ± 1.69 |
71.35 ± 3.10 / 83.98 ± 2.23 |
56.56 ± 1.39 / 66.76 ± 1.10 |
66.08 ± 0.14 / 17.19 ± 0.38 |
71.32 ± 1.56 / 78.48 ± 1.15 |
84.09 ± 2.99 / 88.01 ± 2.26 |
86.37 ± 1.19 / 82.25 ± 2.73 |
43.03 ± 5.07 / 71.18 ± 2.64 |
37.26 ± 2.60 / 66.04 ± 1.95 |
69.61 ± 0.61 / 23.98 ± 1.17 |
89.09 ± 1.59 / 91.76 ± 1.19 |
72.03 ± 3.91 / 86.09 ± 1.96 |
68.94 ± 2.50 / 44.89 ± 2.85 |
60.47 ± 2.94 / 72.79 ± 1.90 |
51.26 ± 4.94 / 74.76 ± 2.45 |
30.04 ± 1.30 / 58.77 ± 1.50 |
63.62 ± 0.65 / 13.08 ± 0.87 |
73.80 ± 2.03 / 80.31 ± 1.54 |
83.93 ± 2.38 / 87.85 ± 1.80 |
66.44 ± 2.18 / 56.97 ± 2.87 |
14.22 ± 3.26 / 33.41 ± 3.24 |
72.30 ± 2.26 / 85.96 ± 1.13 |
57.81 ± 1.23 / 74.51 ± 0.62 |
67.13 ± 0.50 / 17.61 ± 0.76 |
70.04 ± 1.91 / 77.58 ± 1.42 |
88.29 ± 2.26 / 91.17 ± 1.70 |
81.79 ± 1.39 / 65.51 ± 4.16 |
67.55 ± 2.34 / 74.04 ± 1.80 |
51.21 ± 4.96 / 75.11 ± 2.42 |
66.60 ± 1.45 / 84.48 ± 0.76 |
68.80 ± 0.43 / 21.84 ± 0.45 |
81.71 ± 1.12 / 86.29 ± 0.83 |
89.91 ± 1.81 / 92.38 ± 1.34 |
12.10.0 |
12.10.2 |
12.10.2 |
12.10.0 |
12.10.0 |
12.10.2 |
12.10.2 |
12.10.2 |
12.10.0 |
12.10.0 |
12.10.2 |
12.10.0 |
12.10.2 |
12.10.2 |
12.10.0 |
12.10.2 |
12.10.2 |
12.10.0 |
12.10.2 |
12.10.2 |
12.10.0 |
12.10.0 |
12.10.2 |
12.10.2 |
12.5.1 |
12.10.2 |
12.5.1 |
12.5.1 |
12.10.8 |
12.10.2 |
12.6.1 |
12.10.2 |
12.10.2 |
12.6.1 |
12.6.1 |
12.10.2 |
12.10.2 |
12.3.2 |
12.10.2 |
12.10.2 |
12.3.2 |
12.3.2 |
12.10.2 |
12.10.2 |
12.10.0 |
12.10.2 |
12.10.2 |
12.10.0 |
12.10.0 |
12.10.2 |
12.10.2 |
gpt-4o-2024-05-13 (few-shot, val) |
unknown |
200 |
128000 |
True |
916 ± 329 / 114 ± 38 |
1.35 |
1.26 |
1.28 |
1.20 |
1.22 |
1.43 |
1.65 |
1.42 |
71.15 ± 2.89 / 52.24 ± 3.76 |
49.42 ± 3.29 / 61.74 ± 2.59 |
64.59 ± 2.97 / 79.93 ± 1.88 |
57.35 ± 2.51 / 67.87 ± 1.75 |
66.03 ± 0.24 / 17.74 ± 0.71 |
96.41 ± 0.63 / 97.30 ± 0.48 |
97.68 ± 1.06 / 98.44 ± 0.72 |
85.96 ± 1.48 / 89.41 ± 1.15 |
79.07 ± 3.01 / 64.17 ± 3.51 |
81.56 ± 2.45 / 64.06 ± 4.11 |
66.66 ± 1.91 / 77.70 ± 1.29 |
63.25 ± 0.26 / 13.02 ± 0.33 |
64.53 ± 6.09 / 79.17 ± 4.89 |
54.70 ± 4.36 / 74.94 ± 3.26 |
43.51 ± 3.40 / 74.52 ± 1.79 |
73.81 ± 1.88 / 80.39 ± 1.45 |
89.91 ± 1.13 / 92.42 ± 0.83 |
76.66 ± 2.11 / 60.34 ± 4.71 |
77.16 ± 2.65 / 79.22 ± 2.36 |
68.99 ± 4.33 / 83.37 ± 2.61 |
57.96 ± 1.35 / 67.71 ± 0.96 |
66.00 ± 0.29 / 16.97 ± 0.45 |
70.70 ± 1.32 / 77.97 ± 0.99 |
86.30 ± 2.23 / 89.65 ± 1.68 |
81.19 ± 2.45 / 54.02 ± 5.60 |
51.10 ± 5.09 / 73.25 ± 3.42 |
29.64 ± 2.12 / 55.46 ± 1.12 |
68.25 ± 0.27 / 19.22 ± 0.51 |
91.27 ± 1.41 / 93.40 ± 1.09 |
70.85 ± 5.98 / 85.55 ± 3.05 |
69.99 ± 1.63 / 45.58 ± 2.42 |
54.82 ± 2.19 / 68.42 ± 1.67 |
43.66 ± 5.67 / 64.64 ± 4.65 |
30.06 ± 1.04 / 60.77 ± 1.11 |
63.80 ± 0.60 / 13.87 ± 1.05 |
74.13 ± 1.60 / 80.59 ± 1.22 |
88.18 ± 1.79 / 91.13 ± 1.34 |
76.75 ± 3.44 / 61.13 ± 4.40 |
10.80 ± 2.24 / 32.52 ± 2.18 |
56.26 ± 4.51 / 73.83 ± 3.26 |
55.55 ± 2.54 / 76.28 ± 1.13 |
66.86 ± 0.46 / 16.93 ± 0.91 |
73.11 ± 1.87 / 79.69 ± 1.46 |
92.69 ± 1.46 / 94.53 ± 1.09 |
83.48 ± 1.52 / 75.51 ± 2.26 |
62.74 ± 2.04 / 71.28 ± 1.46 |
46.56 ± 3.35 / 71.13 ± 1.97 |
65.41 ± 1.96 / 84.78 ± 0.68 |
67.64 ± 0.97 / 20.90 ± 0.92 |
78.55 ± 1.82 / 83.91 ± 1.34 |
91.34 ± 1.66 / 93.48 ± 1.27 |
12.10.0 |
12.10.2 |
12.10.2 |
12.10.0 |
12.10.0 |
12.10.2 |
12.10.2 |
12.10.2 |
12.10.0 |
12.10.0 |
12.10.2 |
12.10.0 |
12.10.2 |
12.10.2 |
12.10.0 |
12.10.2 |
12.10.2 |
12.10.0 |
12.10.2 |
12.10.2 |
12.10.0 |
12.10.0 |
12.10.2 |
12.10.2 |
12.10.0 |
12.10.2 |
12.10.0 |
12.10.0 |
12.10.8 |
12.10.2 |
12.10.0 |
12.10.2 |
12.10.2 |
12.10.0 |
12.10.0 |
12.10.2 |
12.10.2 |
12.10.0 |
12.10.2 |
12.10.2 |
12.10.0 |
12.10.0 |
12.10.2 |
12.10.2 |
12.10.0 |
12.10.2 |
12.10.2 |
12.10.0 |
12.10.0 |
12.10.2 |
12.10.2 |
google/gemma-2-9b-it (few-shot) |
9242 |
256 |
8193 |
False |
2,062 ± 397 / 589 ± 178 |
1.94 |
1.72 |
1.82 |
1.79 |
2.76 |
1.70 |
2.07 |
1.69 |
49.05 ± 2.41 / 30.91 ± 2.53 |
52.26 ± 1.31 / 64.13 ± 1.93 |
58.38 ± 1.21 / 78.98 ± 0.68 |
55.34 ± 0.82 / 64.41 ± 0.42 |
67.67 ± 1.05 / 23.18 ± 1.13 |
80.62 ± 0.77 / 85.41 ± 0.58 |
75.37 ± 2.23 / 83.59 ± 1.49 |
66.17 ± 1.45 / 74.39 ± 1.13 |
61.82 ± 2.72 / 44.91 ± 3.62 |
60.41 ± 2.62 / 46.29 ± 3.79 |
61.06 ± 1.21 / 73.45 ± 0.94 |
65.94 ± 0.37 / 19.22 ± 0.79 |
62.46 ± 1.49 / 81.11 ± 0.72 |
52.99 ± 1.89 / 76.14 ± 1.20 |
39.10 ± 1.50 / 70.14 ± 1.53 |
49.45 ± 0.93 / 61.63 ± 0.72 |
67.96 ± 1.93 / 75.79 ± 1.47 |
52.50 ± 1.02 / 37.38 ± 2.57 |
78.51 ± 0.93 / 76.24 ± 1.64 |
61.28 ± 1.63 / 80.07 ± 1.22 |
55.22 ± 1.03 / 64.60 ± 0.52 |
66.30 ± 0.12 / 19.72 ± 0.19 |
51.58 ± 0.83 / 63.27 ± 0.62 |
66.61 ± 1.12 / 74.72 ± 0.93 |
45.42 ± 1.86 / 36.69 ± 2.74 |
24.23 ± 0.89 / 61.40 ± 0.70 |
24.96 ± 1.52 / 55.04 ± 0.80 |
68.19 ± 0.25 / 22.04 ± 0.48 |
54.30 ± 1.60 / 65.62 ± 1.20 |
24.35 ± 2.31 / 62.81 ± 1.08 |
50.35 ± 2.81 / 39.72 ± 2.62 |
58.60 ± 2.21 / 71.12 ± 1.12 |
45.78 ± 1.55 / 70.64 ± 0.61 |
30.46 ± 0.98 / 60.56 ± 2.25 |
67.99 ± 1.12 / 24.07 ± 2.91 |
53.61 ± 0.60 / 64.92 ± 0.47 |
68.16 ± 0.75 / 75.71 ± 0.65 |
52.62 ± 2.15 / 39.41 ± 1.72 |
11.78 ± 1.31 / 32.80 ± 0.87 |
59.23 ± 1.58 / 79.42 ± 0.88 |
55.78 ± 0.87 / 72.71 ± 0.70 |
67.39 ± 0.71 / 20.04 ± 1.05 |
53.99 ± 0.77 / 65.31 ± 0.62 |
65.58 ± 1.18 / 73.75 ± 0.94 |
58.07 ± 2.46 / 51.39 ± 2.35 |
68.40 ± 1.17 / 71.79 ± 0.65 |
51.58 ± 2.03 / 74.57 ± 1.48 |
62.03 ± 1.62 / 81.91 ± 0.76 |
69.72 ± 0.42 / 25.66 ± 0.38 |
63.99 ± 0.76 / 72.84 ± 0.57 |
75.87 ± 1.74 / 81.61 ± 1.30 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
gpt-3.5-turbo-0613 (few-shot, val) |
unknown |
100 |
4094 |
True |
921 ± 293 / 113 ± 37 |
2.02 |
1.64 |
1.91 |
1.79 |
2.79 |
2.04 |
2.19 |
1.78 |
61.31 ± 2.34 / 49.86 ± 2.18 |
52.52 ± 2.05 / 68.10 ± 1.35 |
57.63 ± 2.80 / 77.01 ± 1.83 |
57.03 ± 1.95 / 65.51 ± 1.48 |
66.38 ± 0.26 / 18.03 ± 0.27 |
81.95 ± 2.61 / 86.33 ± 2.03 |
77.66 ± 2.57 / 85.08 ± 1.77 |
62.21 ± 2.60 / 71.05 ± 2.09 |
77.70 ± 2.64 / 68.71 ± 2.97 |
73.92 ± 2.53 / 67.96 ± 2.67 |
58.88 ± 3.23 / 71.00 ± 2.87 |
64.18 ± 0.22 / 14.10 ± 0.37 |
54.29 ± 4.27 / 73.02 ± 3.26 |
32.82 ± 3.43 / 56.05 ± 4.14 |
45.35 ± 2.97 / 73.47 ± 1.69 |
40.26 ± 5.24 / 54.88 ± 3.85 |
59.02 ± 1.63 / 68.63 ± 1.34 |
73.04 ± 2.74 / 61.64 ± 3.63 |
72.77 ± 2.64 / 72.56 ± 2.45 |
58.06 ± 3.84 / 76.06 ± 2.51 |
58.02 ± 2.11 / 66.84 ± 1.38 |
66.92 ± 0.16 / 19.00 ± 0.28 |
40.73 ± 3.36 / 55.16 ± 2.75 |
50.51 ± 2.33 / 62.07 ± 1.95 |
69.59 ± 4.54 / 54.49 ± 4.31 |
7.28 ± 4.10 / 52.96 ± 2.00 |
28.50 ± 1.79 / 50.29 ± 1.79 |
67.10 ± 0.30 / 19.43 ± 0.48 |
49.88 ± 2.38 / 62.27 ± 1.75 |
18.61 ± 6.00 / 61.33 ± 2.93 |
61.50 ± 2.96 / 46.22 ± 3.41 |
55.50 ± 2.58 / 68.96 ± 2.00 |
38.96 ± 4.39 / 68.89 ± 2.54 |
30.20 ± 1.59 / 56.58 ± 1.78 |
64.90 ± 0.22 / 15.99 ± 0.32 |
35.39 ± 3.89 / 51.41 ± 2.98 |
56.88 ± 2.50 / 66.76 ± 2.02 |
68.96 ± 3.80 / 58.45 ± 3.71 |
8.81 ± 3.30 / 30.88 ± 2.25 |
58.95 ± 4.48 / 78.64 ± 2.32 |
55.57 ± 2.33 / 68.26 ± 1.85 |
69.13 ± 0.41 / 21.32 ± 0.75 |
42.28 ± 2.88 / 56.45 ± 2.26 |
61.52 ± 2.69 / 70.62 ± 2.20 |
71.48 ± 2.47 / 69.71 ± 1.59 |
66.41 ± 2.66 / 68.72 ± 1.87 |
41.43 ± 2.57 / 70.34 ± 1.35 |
67.90 ± 1.61 / 85.57 ± 0.84 |
69.57 ± 0.18 / 24.41 ± 0.39 |
43.69 ± 3.59 / 57.38 ± 3.06 |
75.60 ± 3.04 / 81.48 ± 2.31 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.6.1 |
10.0.1 |
10.0.1 |
12.9.0 |
0.0.0 |
0.0.0 |
0.0.0 |
11.0.0 |
0.0.0 |
0.0.0 |
12.9.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
12.9.0 |
11.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
12.10.8 |
12.1.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
google/gemma-2-9b (few-shot) |
9242 |
256 |
8193 |
True |
2,038 ± 406 / 566 ± 172 |
2.06 |
2.03 |
1.95 |
1.89 |
3.11 |
1.66 |
2.04 |
1.77 |
44.16 ± 3.11 / 25.93 ± 1.95 |
38.84 ± 2.31 / 45.52 ± 3.32 |
43.42 ± 3.95 / 69.40 ± 3.11 |
60.11 ± 0.96 / 66.24 ± 0.78 |
67.46 ± 1.14 / 24.10 ± 1.14 |
81.68 ± 0.62 / 86.22 ± 0.47 |
77.77 ± 1.30 / 85.06 ± 0.86 |
50.04 ± 3.99 / 61.09 ± 3.31 |
54.08 ± 2.08 / 34.62 ± 1.80 |
54.33 ± 3.02 / 37.70 ± 2.97 |
62.54 ± 1.17 / 75.53 ± 0.73 |
65.67 ± 0.85 / 20.11 ± 0.92 |
50.88 ± 2.84 / 74.69 ± 1.56 |
41.01 ± 1.91 / 69.35 ± 1.67 |
46.25 ± 3.89 / 72.99 ± 3.16 |
50.81 ± 1.18 / 62.98 ± 0.88 |
53.37 ± 3.87 / 63.52 ± 3.49 |
50.43 ± 3.97 / 27.20 ± 3.14 |
80.55 ± 1.46 / 77.22 ± 3.78 |
50.86 ± 3.91 / 72.14 ± 3.98 |
59.35 ± 1.16 / 65.35 ± 0.87 |
65.63 ± 0.26 / 19.75 ± 0.45 |
52.06 ± 0.97 / 63.92 ± 0.72 |
49.80 ± 3.86 / 60.88 ± 3.42 |
30.89 ± 4.28 / 24.06 ± 1.93 |
5.29 ± 3.38 / 35.79 ± 2.12 |
32.25 ± 1.89 / 58.20 ± 1.70 |
67.58 ± 0.63 / 21.53 ± 0.99 |
55.69 ± 1.49 / 66.84 ± 1.09 |
17.50 ± 2.56 / 58.33 ± 1.75 |
47.39 ± 1.96 / 34.14 ± 1.70 |
62.89 ± 2.21 / 74.51 ± 1.63 |
37.22 ± 4.67 / 67.37 ± 2.22 |
39.11 ± 2.14 / 67.67 ± 2.90 |
70.44 ± 1.18 / 30.83 ± 2.69 |
53.28 ± 1.15 / 64.86 ± 0.90 |
54.51 ± 2.74 / 64.51 ± 2.33 |
57.13 ± 2.73 / 36.21 ± 1.71 |
17.43 ± 2.17 / 40.83 ± 1.50 |
31.39 ± 5.53 / 56.70 ± 5.97 |
59.33 ± 1.35 / 73.56 ± 0.52 |
66.59 ± 1.21 / 21.08 ± 1.63 |
53.71 ± 0.86 / 65.15 ± 0.63 |
53.26 ± 3.38 / 63.65 ± 2.84 |
50.90 ± 2.39 / 44.74 ± 1.46 |
68.91 ± 0.89 / 70.46 ± 1.23 |
43.79 ± 3.15 / 71.10 ± 1.74 |
69.17 ± 1.55 / 84.25 ± 1.13 |
69.67 ± 0.46 / 25.26 ± 0.45 |
61.34 ± 0.86 / 70.95 ± 0.66 |
62.23 ± 3.55 / 70.69 ± 3.11 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
gpt-4o-mini-2024-07-18 (few-shot) |
unknown |
200 |
128000 |
True |
1,171 ± 378 / 120 ± 39 |
2.07 |
1.94 |
2.09 |
1.97 |
2.56 |
1.86 |
2.41 |
1.65 |
63.59 ± 2.16 / 42.42 ± 3.34 |
29.47 ± 4.78 / 50.59 ± 4.36 |
38.37 ± 9.13 / 60.56 ± 8.53 |
54.63 ± 0.51 / 65.79 ± 0.42 |
65.94 ± 0.11 / 17.32 ± 0.29 |
80.46 ± 4.74 / 84.69 ± 3.92 |
76.16 ± 4.99 / 83.11 ± 4.13 |
62.12 ± 2.52 / 70.60 ± 2.10 |
75.05 ± 1.56 / 57.52 ± 4.29 |
74.08 ± 1.43 / 62.50 ± 4.89 |
37.79 ± 4.47 / 55.88 ± 3.23 |
63.80 ± 0.16 / 13.40 ± 0.32 |
31.59 ± 11.25 / 54.68 ± 10.28 |
39.25 ± 7.82 / 62.90 ± 7.12 |
39.43 ± 2.31 / 72.15 ± 1.71 |
51.93 ± 1.39 / 62.52 ± 1.41 |
68.29 ± 1.51 / 75.45 ± 1.24 |
67.38 ± 1.52 / 52.86 ± 4.83 |
65.51 ± 4.81 / 67.01 ± 3.84 |
29.41 ± 10.34 / 52.38 ± 8.76 |
55.67 ± 0.89 / 66.26 ± 0.48 |
65.70 ± 0.71 / 16.98 ± 0.75 |
50.06 ± 2.65 / 61.33 ± 2.36 |
64.58 ± 2.48 / 72.57 ± 2.06 |
67.56 ± 1.93 / 43.20 ± 1.44 |
23.28 ± 7.61 / 52.43 ± 7.20 |
24.91 ± 1.14 / 52.48 ± 0.90 |
67.32 ± 0.95 / 17.55 ± 1.32 |
67.57 ± 3.31 / 75.27 ± 2.62 |
15.36 ± 5.77 / 49.21 ± 3.61 |
67.90 ± 1.07 / 45.53 ± 3.11 |
51.88 ± 5.19 / 67.24 ± 3.71 |
46.77 ± 2.33 / 69.48 ± 2.55 |
24.70 ± 1.31 / 56.87 ± 0.77 |
64.65 ± 0.10 / 14.11 ± 0.26 |
51.72 ± 2.53 / 62.88 ± 2.10 |
62.80 ± 1.97 / 70.65 ± 1.80 |
68.20 ± 1.93 / 49.92 ± 2.53 |
5.65 ± 1.80 / 14.84 ± 2.18 |
31.15 ± 7.70 / 52.16 ± 7.03 |
53.17 ± 1.82 / 72.08 ± 0.90 |
67.62 ± 0.45 / 18.21 ± 0.81 |
54.56 ± 1.84 / 64.78 ± 1.89 |
65.27 ± 1.51 / 72.80 ± 1.37 |
78.84 ± 1.47 / 68.25 ± 3.41 |
60.72 ± 1.81 / 67.08 ± 1.16 |
50.99 ± 1.31 / 72.72 ± 1.34 |
61.45 ± 1.95 / 83.59 ± 0.82 |
68.66 ± 0.07 / 21.97 ± 0.19 |
62.15 ± 1.02 / 71.31 ± 0.77 |
79.13 ± 1.02 / 83.93 ± 0.81 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
upstage/SOLAR-10.7B-v1.0 (few-shot) |
10732 |
32 |
4096 |
True |
3,780 ± 906 / 799 ± 261 |
2.07 |
1.98 |
2.16 |
2.05 |
3.26 |
1.55 |
2.05 |
1.47 |
58.03 ± 2.18 / 38.25 ± 2.31 |
46.63 ± 2.35 / 59.02 ± 3.07 |
15.09 ± 3.06 / 40.04 ± 1.77 |
62.15 ± 0.63 / 67.21 ± 0.55 |
66.81 ± 1.08 / 22.82 ± 1.04 |
64.79 ± 1.37 / 73.46 ± 1.07 |
68.59 ± 2.23 / 78.59 ± 1.60 |
65.29 ± 0.94 / 73.54 ± 0.74 |
68.11 ± 1.83 / 57.57 ± 3.10 |
68.19 ± 1.01 / 56.90 ± 2.54 |
55.33 ± 1.95 / 69.71 ± 1.56 |
65.51 ± 1.32 / 19.63 ± 1.66 |
10.15 ± 3.24 / 36.27 ± 1.44 |
7.51 ± 2.97 / 35.89 ± 1.30 |
55.33 ± 3.29 / 80.42 ± 1.68 |
35.57 ± 0.78 / 51.45 ± 0.56 |
62.76 ± 1.85 / 71.77 ± 1.45 |
59.65 ± 2.22 / 39.33 ± 3.33 |
77.48 ± 1.23 / 70.13 ± 2.81 |
16.94 ± 2.36 / 40.98 ± 1.82 |
62.65 ± 0.56 / 68.15 ± 0.56 |
65.19 ± 0.36 / 19.09 ± 0.55 |
39.82 ± 0.69 / 54.84 ± 0.53 |
68.87 ± 1.35 / 76.46 ± 1.04 |
62.08 ± 2.27 / 51.09 ± 4.15 |
7.58 ± 1.03 / 44.38 ± 3.90 |
29.66 ± 3.02 / 56.60 ± 2.22 |
66.11 ± 0.85 / 18.74 ± 0.90 |
18.75 ± 1.02 / 38.96 ± 0.70 |
7.64 ± 1.91 / 49.40 ± 1.45 |
68.11 ± 1.32 / 56.25 ± 1.65 |
59.79 ± 1.60 / 71.47 ± 1.54 |
35.45 ± 3.06 / 66.13 ± 1.28 |
37.27 ± 1.23 / 68.54 ± 1.94 |
69.31 ± 0.95 / 28.82 ± 2.24 |
41.20 ± 0.85 / 55.90 ± 0.66 |
72.65 ± 0.69 / 79.18 ± 0.58 |
65.37 ± 1.61 / 46.10 ± 1.53 |
11.93 ± 1.80 / 34.67 ± 2.84 |
41.67 ± 1.53 / 69.81 ± 1.38 |
67.75 ± 0.62 / 78.01 ± 0.45 |
68.83 ± 0.35 / 26.12 ± 0.52 |
40.18 ± 0.57 / 55.06 ± 0.44 |
65.34 ± 1.05 / 73.48 ± 0.83 |
69.50 ± 1.14 / 63.41 ± 0.77 |
70.01 ± 0.93 / 59.77 ± 0.59 |
41.35 ± 2.01 / 70.11 ± 0.82 |
76.79 ± 0.43 / 89.35 ± 0.19 |
71.16 ± 0.12 / 29.84 ± 0.23 |
51.95 ± 0.84 / 63.78 ± 0.62 |
90.94 ± 0.54 / 93.17 ± 0.41 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.10.8 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
mistralai/Mistral-Nemo-Instruct-2407 (few-shot) |
12248 |
131 |
1024001 |
True |
7,095 ± 2,193 / 1,063 ± 344 |
2.15 |
2.09 |
2.09 |
2.15 |
3.00 |
1.74 |
2.30 |
1.67 |
53.95 ± 2.29 / 34.84 ± 2.23 |
48.97 ± 1.81 / 64.19 ± 1.99 |
31.78 ± 4.52 / 61.53 ± 5.44 |
56.44 ± 1.24 / 65.53 ± 1.09 |
66.24 ± 0.66 / 20.00 ± 0.80 |
67.09 ± 1.38 / 74.85 ± 1.04 |
72.87 ± 2.11 / 81.97 ± 1.42 |
42.77 ± 2.30 / 55.61 ± 2.33 |
70.14 ± 1.60 / 51.03 ± 3.02 |
68.74 ± 1.21 / 51.48 ± 2.96 |
60.64 ± 2.52 / 73.91 ± 1.86 |
64.61 ± 0.40 / 16.10 ± 0.86 |
35.59 ± 2.29 / 61.96 ± 3.72 |
29.22 ± 2.86 / 60.98 ± 4.02 |
49.87 ± 4.84 / 76.01 ± 3.10 |
39.07 ± 0.84 / 53.89 ± 0.69 |
37.95 ± 3.53 / 51.35 ± 3.17 |
62.86 ± 1.95 / 36.42 ± 3.49 |
70.54 ± 6.38 / 73.39 ± 6.37 |
37.50 ± 2.48 / 66.32 ± 1.77 |
58.00 ± 0.85 / 65.98 ± 0.82 |
65.93 ± 0.19 / 19.24 ± 0.33 |
40.58 ± 1.17 / 55.16 ± 0.88 |
42.99 ± 2.04 / 56.16 ± 1.93 |
59.70 ± 1.67 / 41.69 ± 2.75 |
4.64 ± 3.09 / 38.48 ± 2.74 |
29.68 ± 1.85 / 58.88 ± 0.87 |
68.13 ± 0.31 / 20.42 ± 0.65 |
41.76 ± 1.72 / 56.28 ± 1.30 |
13.24 ± 4.12 / 56.22 ± 1.89 |
66.27 ± 1.13 / 49.86 ± 1.62 |
57.70 ± 2.68 / 71.63 ± 1.94 |
35.54 ± 4.25 / 60.12 ± 5.53 |
34.45 ± 1.61 / 66.90 ± 2.58 |
68.65 ± 1.15 / 25.16 ± 2.66 |
47.05 ± 1.12 / 60.01 ± 0.86 |
52.68 ± 3.39 / 63.07 ± 2.88 |
66.57 ± 1.86 / 48.40 ± 2.67 |
10.10 ± 1.55 / 33.62 ± 2.04 |
40.31 ± 2.25 / 69.53 ± 1.51 |
59.99 ± 0.95 / 74.24 ± 0.63 |
68.66 ± 0.68 / 20.75 ± 1.15 |
42.50 ± 0.84 / 56.53 ± 0.62 |
48.51 ± 1.44 / 60.59 ± 1.34 |
75.24 ± 0.84 / 67.78 ± 2.01 |
63.05 ± 1.41 / 70.34 ± 0.52 |
44.75 ± 2.73 / 71.43 ± 1.71 |
67.70 ± 1.57 / 83.88 ± 1.27 |
70.56 ± 0.58 / 25.57 ± 0.59 |
57.55 ± 1.00 / 68.02 ± 0.70 |
67.97 ± 1.89 / 75.51 ± 1.48 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
Nexusflow/Starling-LM-7B-beta (few-shot) |
7242 |
32 |
8192 |
False |
5,876 ± 1,021 / 1,677 ± 546 |
2.26 |
2.05 |
2.33 |
2.19 |
3.66 |
1.95 |
2.11 |
1.53 |
53.20 ± 1.97 / 32.89 ± 2.00 |
51.75 ± 1.18 / 67.38 ± 0.95 |
32.72 ± 1.79 / 62.53 ± 2.00 |
56.44 ± 0.99 / 65.36 ± 0.51 |
67.46 ± 0.76 / 23.35 ± 0.88 |
59.78 ± 1.61 / 69.68 ± 1.23 |
58.63 ± 2.54 / 71.72 ± 1.82 |
50.74 ± 1.16 / 62.79 ± 0.92 |
66.22 ± 2.15 / 48.98 ± 4.65 |
64.14 ± 1.26 / 49.59 ± 4.31 |
55.48 ± 1.77 / 69.68 ± 1.45 |
65.32 ± 0.41 / 18.53 ± 0.65 |
26.13 ± 1.28 / 56.08 ± 2.05 |
17.32 ± 0.77 / 54.57 ± 1.49 |
49.75 ± 1.22 / 77.08 ± 0.60 |
29.72 ± 1.33 / 46.95 ± 0.96 |
46.78 ± 2.83 / 59.65 ± 2.28 |
60.38 ± 1.60 / 36.17 ± 3.66 |
77.49 ± 0.98 / 72.07 ± 1.56 |
29.32 ± 2.34 / 54.43 ± 2.67 |
56.79 ± 0.83 / 65.84 ± 0.48 |
65.75 ± 0.16 / 20.23 ± 0.23 |
36.05 ± 1.10 / 51.86 ± 0.87 |
51.15 ± 1.71 / 63.20 ± 1.32 |
49.20 ± 2.64 / 40.79 ± 4.46 |
4.45 ± 1.40 / 51.11 ± 0.87 |
24.61 ± 3.36 / 54.99 ± 2.36 |
63.74 ± 2.25 / 18.29 ± 1.40 |
8.45 ± 1.35 / 31.54 ± 1.03 |
1.14 ± 0.97 / 50.10 ± 0.82 |
65.01 ± 0.68 / 43.34 ± 2.80 |
51.80 ± 1.29 / 67.45 ± 0.87 |
36.18 ± 1.31 / 67.86 ± 0.51 |
32.12 ± 2.08 / 67.30 ± 1.66 |
66.92 ± 0.41 / 23.23 ± 1.24 |
37.90 ± 1.03 / 53.36 ± 0.80 |
60.66 ± 1.28 / 70.32 ± 1.01 |
64.47 ± 2.31 / 40.89 ± 2.81 |
13.83 ± 1.91 / 41.53 ± 1.23 |
45.69 ± 1.76 / 72.13 ± 1.39 |
58.03 ± 1.37 / 73.17 ± 0.58 |
69.34 ± 0.77 / 22.22 ± 0.98 |
37.60 ± 0.83 / 53.13 ± 0.62 |
54.33 ± 0.84 / 65.41 ± 0.59 |
71.81 ± 1.02 / 59.93 ± 2.52 |
69.98 ± 1.00 / 69.79 ± 0.76 |
45.34 ± 2.51 / 72.10 ± 1.10 |
72.49 ± 1.57 / 87.51 ± 0.74 |
70.37 ± 0.32 / 27.70 ± 0.38 |
50.93 ± 1.34 / 62.98 ± 0.98 |
83.82 ± 0.80 / 87.83 ± 0.60 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.10.8 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
meta-llama/Meta-Llama-3.1-8B-Instruct (few-shot) |
8030 |
128 |
131073 |
True |
2,411 ± 465 / 686 ± 215 |
2.35 |
2.33 |
2.30 |
2.26 |
3.15 |
2.07 |
2.42 |
1.93 |
57.19 ± 1.73 / 44.34 ± 2.43 |
51.30 ± 1.32 / 64.44 ± 1.47 |
10.31 ± 3.91 / 42.59 ± 5.19 |
48.80 ± 1.66 / 60.46 ± 0.60 |
67.38 ± 1.09 / 23.21 ± 0.94 |
61.78 ± 1.70 / 71.28 ± 1.27 |
66.61 ± 1.90 / 77.73 ± 1.31 |
39.62 ± 2.26 / 53.92 ± 1.96 |
74.77 ± 0.84 / 71.87 ± 0.97 |
72.80 ± 1.57 / 69.98 ± 1.84 |
57.30 ± 0.98 / 71.58 ± 0.90 |
66.08 ± 0.56 / 19.80 ± 0.86 |
5.23 ± 1.83 / 34.90 ± 0.81 |
11.51 ± 3.24 / 45.73 ± 5.97 |
43.93 ± 3.73 / 70.96 ± 3.00 |
38.10 ± 0.57 / 52.64 ± 0.47 |
39.30 ± 1.01 / 54.03 ± 0.82 |
71.52 ± 1.43 / 59.28 ± 3.63 |
80.46 ± 0.83 / 78.67 ± 1.13 |
12.29 ± 3.59 / 40.53 ± 4.13 |
53.54 ± 1.52 / 62.08 ± 0.98 |
66.27 ± 0.15 / 19.05 ± 0.30 |
39.40 ± 1.44 / 53.87 ± 1.19 |
38.88 ± 1.25 / 53.72 ± 0.91 |
55.09 ± 1.76 / 40.34 ± 2.34 |
8.45 ± 1.33 / 51.00 ± 1.95 |
29.65 ± 1.09 / 56.96 ± 1.35 |
68.27 ± 0.25 / 22.14 ± 0.62 |
30.33 ± 1.72 / 47.81 ± 1.31 |
10.48 ± 2.28 / 54.89 ± 1.49 |
67.61 ± 1.23 / 60.39 ± 1.02 |
59.96 ± 2.00 / 70.71 ± 1.80 |
28.25 ± 3.57 / 59.54 ± 3.88 |
28.79 ± 2.02 / 55.82 ± 3.28 |
66.87 ± 0.54 / 21.31 ± 1.47 |
40.00 ± 0.97 / 54.88 ± 0.70 |
45.93 ± 1.38 / 58.95 ± 1.06 |
69.76 ± 1.36 / 57.66 ± 1.36 |
15.51 ± 1.59 / 39.71 ± 1.21 |
37.58 ± 3.42 / 66.98 ± 2.22 |
41.26 ± 2.09 / 65.63 ± 0.90 |
68.84 ± 0.62 / 21.41 ± 1.20 |
40.98 ± 0.71 / 55.51 ± 0.59 |
39.98 ± 1.59 / 54.32 ± 1.27 |
76.95 ± 0.95 / 72.47 ± 0.82 |
68.12 ± 0.92 / 72.48 ± 0.53 |
34.34 ± 3.37 / 65.84 ± 1.59 |
47.88 ± 3.37 / 76.21 ± 1.69 |
69.57 ± 0.25 / 26.30 ± 0.35 |
56.62 ± 0.49 / 67.29 ± 0.39 |
69.03 ± 1.19 / 76.69 ± 0.89 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
meta-llama/Meta-Llama-3.1-8B (few-shot) |
8030 |
128 |
131073 |
True |
2,439 ± 459 / 703 ± 219 |
2.35 |
2.31 |
2.31 |
2.19 |
3.24 |
2.02 |
2.42 |
1.97 |
47.68 ± 2.50 / 32.67 ± 2.45 |
49.71 ± 1.43 / 64.00 ± 1.96 |
25.48 ± 2.83 / 58.45 ± 2.63 |
60.31 ± 1.24 / 65.79 ± 0.84 |
64.74 ± 0.50 / 17.82 ± 0.98 |
57.60 ± 1.58 / 67.81 ± 1.23 |
65.98 ± 1.72 / 77.34 ± 1.16 |
28.65 ± 2.52 / 45.11 ± 2.33 |
64.62 ± 1.26 / 53.50 ± 3.27 |
65.10 ± 1.86 / 56.43 ± 2.58 |
52.87 ± 1.18 / 68.71 ± 1.01 |
63.88 ± 1.12 / 16.54 ± 1.58 |
28.34 ± 3.26 / 58.57 ± 4.45 |
22.40 ± 3.12 / 53.51 ± 5.42 |
53.20 ± 3.15 / 75.98 ± 2.62 |
35.80 ± 0.97 / 51.22 ± 0.67 |
30.31 ± 1.70 / 46.84 ± 1.59 |
63.85 ± 2.49 / 44.62 ± 4.10 |
79.96 ± 0.93 / 75.75 ± 2.22 |
31.70 ± 4.07 / 59.28 ± 5.00 |
59.33 ± 0.88 / 65.24 ± 0.79 |
65.07 ± 0.28 / 18.94 ± 0.35 |
37.48 ± 0.64 / 52.46 ± 0.52 |
31.27 ± 1.39 / 47.97 ± 1.30 |
52.57 ± 2.04 / 36.81 ± 2.12 |
4.87 ± 2.28 / 40.95 ± 4.97 |
30.12 ± 4.65 / 57.81 ± 4.78 |
66.17 ± 0.86 / 18.71 ± 0.89 |
25.93 ± 1.51 / 44.54 ± 1.14 |
8.48 ± 2.66 / 53.76 ± 1.54 |
60.46 ± 1.26 / 47.72 ± 1.69 |
58.57 ± 2.53 / 71.30 ± 1.70 |
26.25 ± 5.90 / 61.41 ± 3.94 |
34.85 ± 3.43 / 64.05 ± 3.68 |
69.58 ± 1.37 / 28.95 ± 2.96 |
38.77 ± 0.95 / 53.99 ± 0.67 |
34.29 ± 1.05 / 49.79 ± 0.88 |
64.79 ± 1.96 / 45.48 ± 2.24 |
11.95 ± 2.83 / 37.12 ± 2.19 |
32.97 ± 2.68 / 58.52 ± 2.92 |
63.89 ± 1.06 / 74.73 ± 1.02 |
66.29 ± 1.29 / 20.14 ± 1.64 |
38.44 ± 1.33 / 53.68 ± 1.01 |
30.88 ± 2.27 / 47.18 ± 1.81 |
69.86 ± 2.10 / 62.68 ± 2.21 |
66.76 ± 0.72 / 68.58 ± 0.72 |
30.96 ± 2.46 / 61.29 ± 3.61 |
71.39 ± 2.20 / 84.24 ± 1.55 |
67.93 ± 0.44 / 22.00 ± 0.51 |
52.47 ± 0.85 / 64.25 ± 0.66 |
43.95 ± 3.26 / 57.04 ± 2.74 |
12.11.0 |
12.11.0 |
12.11.0 |
12.11.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
12.11.0 |
12.11.0 |
12.11.0 |
13.0.0 |
12.11.0 |
12.11.0 |
13.0.0 |
13.0.0 |
13.0.0 |
12.11.0 |
12.11.0 |
12.11.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
12.11.0 |
12.11.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
12.11.0 |
12.11.0 |
12.11.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
12.11.0 |
12.11.0 |
12.11.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
12.11.0 |
12.11.0 |
12.11.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
meta-llama/Meta-Llama-3-8B-Instruct (few-shot) |
8030 |
128 |
8192 |
True |
4,909 ± 1,215 / 978 ± 319 |
2.45 |
2.44 |
2.42 |
2.43 |
3.21 |
2.18 |
2.50 |
1.98 |
57.74 ± 2.06 / 40.66 ± 2.58 |
48.43 ± 3.31 / 62.09 ± 3.62 |
27.12 ± 2.83 / 60.40 ± 2.70 |
46.76 ± 1.20 / 59.77 ± 0.51 |
66.36 ± 0.47 / 19.75 ± 0.84 |
57.87 ± 1.67 / 67.43 ± 1.34 |
50.42 ± 3.32 / 65.43 ± 2.41 |
29.17 ± 2.24 / 44.59 ± 2.00 |
74.47 ± 1.47 / 65.57 ± 2.39 |
72.93 ± 1.00 / 65.44 ± 2.55 |
50.62 ± 3.52 / 65.69 ± 3.50 |
63.98 ± 0.50 / 14.75 ± 0.79 |
27.77 ± 1.63 / 61.75 ± 1.77 |
20.35 ± 1.92 / 57.74 ± 2.28 |
42.90 ± 3.57 / 69.90 ± 3.17 |
33.44 ± 0.67 / 48.76 ± 0.58 |
30.91 ± 1.88 / 45.85 ± 1.93 |
69.67 ± 1.30 / 52.94 ± 4.01 |
59.93 ± 4.70 / 67.54 ± 3.04 |
27.63 ± 3.19 / 60.85 ± 3.29 |
49.84 ± 1.61 / 60.85 ± 0.93 |
66.60 ± 0.07 / 19.13 ± 0.31 |
33.54 ± 1.40 / 49.20 ± 1.13 |
30.32 ± 2.27 / 45.96 ± 1.87 |
61.69 ± 2.17 / 41.25 ± 3.12 |
6.10 ± 1.61 / 48.74 ± 3.05 |
31.52 ± 2.08 / 58.96 ± 1.57 |
66.98 ± 1.04 / 19.84 ± 1.97 |
25.16 ± 1.55 / 43.57 ± 1.26 |
1.50 ± 1.22 / 48.33 ± 1.21 |
68.18 ± 0.95 / 57.72 ± 1.15 |
58.33 ± 2.83 / 69.31 ± 3.16 |
29.12 ± 3.17 / 63.60 ± 1.63 |
28.68 ± 1.99 / 56.42 ± 3.34 |
65.23 ± 0.49 / 16.56 ± 0.94 |
38.44 ± 0.81 / 53.38 ± 0.60 |
37.69 ± 1.00 / 51.24 ± 0.73 |
68.72 ± 1.81 / 54.89 ± 2.10 |
14.67 ± 2.51 / 41.36 ± 2.04 |
32.91 ± 2.56 / 64.93 ± 1.97 |
45.36 ± 1.31 / 67.50 ± 0.69 |
67.62 ± 0.82 / 18.19 ± 1.14 |
36.18 ± 1.31 / 51.68 ± 1.05 |
33.91 ± 1.71 / 48.01 ± 1.47 |
75.02 ± 1.31 / 69.47 ± 1.18 |
67.64 ± 1.12 / 71.04 ± 1.17 |
32.29 ± 3.05 / 64.85 ± 2.07 |
54.84 ± 2.22 / 79.10 ± 1.10 |
69.28 ± 0.17 / 25.48 ± 0.61 |
53.77 ± 1.03 / 64.91 ± 0.80 |
57.64 ± 1.55 / 67.29 ± 1.30 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.10.8 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
meta-llama/Meta-Llama-3-8B (few-shot) |
8030 |
128 |
8192 |
True |
4,687 ± 1,121 / 967 ± 313 |
2.46 |
2.33 |
2.49 |
2.30 |
3.31 |
2.16 |
2.58 |
2.07 |
46.31 ± 3.22 / 29.09 ± 2.52 |
51.29 ± 1.47 / 66.35 ± 1.70 |
25.70 ± 4.59 / 55.65 ± 5.87 |
59.79 ± 1.21 / 65.44 ± 0.76 |
65.16 ± 0.48 / 18.74 ± 0.83 |
56.20 ± 2.22 / 66.91 ± 1.68 |
61.16 ± 2.54 / 73.63 ± 1.85 |
24.99 ± 2.12 / 42.57 ± 1.91 |
61.48 ± 1.83 / 47.65 ± 2.94 |
61.58 ± 2.21 / 50.10 ± 2.68 |
49.87 ± 1.88 / 66.15 ± 1.44 |
63.38 ± 1.15 / 15.74 ± 1.68 |
21.20 ± 6.57 / 52.29 ± 7.43 |
19.65 ± 4.32 / 56.66 ± 4.40 |
53.35 ± 4.33 / 74.98 ± 3.70 |
33.02 ± 1.35 / 49.25 ± 1.04 |
24.93 ± 3.13 / 42.47 ± 2.74 |
60.36 ± 2.84 / 39.37 ± 3.56 |
79.74 ± 0.75 / 75.11 ± 1.91 |
28.24 ± 4.19 / 55.29 ± 5.35 |
59.73 ± 1.13 / 65.72 ± 0.94 |
64.81 ± 0.24 / 18.56 ± 0.35 |
35.86 ± 0.90 / 51.39 ± 0.69 |
26.49 ± 1.89 / 44.41 ± 1.56 |
48.70 ± 3.02 / 34.52 ± 2.66 |
7.49 ± 2.51 / 43.40 ± 4.41 |
29.56 ± 5.47 / 55.53 ± 5.79 |
66.34 ± 1.09 / 19.13 ± 0.96 |
26.78 ± 1.59 / 45.17 ± 1.12 |
7.41 ± 3.26 / 52.13 ± 1.97 |
56.00 ± 1.94 / 43.49 ± 2.05 |
56.40 ± 3.89 / 70.17 ± 2.91 |
22.01 ± 5.17 / 56.97 ± 3.54 |
35.39 ± 2.49 / 64.61 ± 2.42 |
68.92 ± 0.99 / 26.93 ± 2.01 |
38.12 ± 0.75 / 53.52 ± 0.56 |
31.37 ± 1.37 / 47.65 ± 1.09 |
62.26 ± 2.20 / 42.41 ± 2.02 |
10.45 ± 2.69 / 33.45 ± 1.99 |
30.30 ± 3.94 / 62.28 ± 2.89 |
62.99 ± 1.00 / 73.73 ± 0.98 |
65.17 ± 1.24 / 18.63 ± 1.85 |
36.38 ± 0.86 / 52.08 ± 0.66 |
28.33 ± 2.31 / 45.29 ± 1.78 |
66.31 ± 2.09 / 58.68 ± 1.95 |
64.30 ± 0.65 / 69.26 ± 0.50 |
28.18 ± 3.96 / 58.97 ± 4.03 |
70.38 ± 3.51 / 82.95 ± 2.38 |
67.90 ± 0.49 / 21.54 ± 0.57 |
52.54 ± 0.88 / 64.26 ± 0.66 |
41.19 ± 4.40 / 54.78 ± 3.62 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.10.8 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
mlabonne/NeuralBeagle14-7B (few-shot, val) |
7242 |
32 |
8192 |
False |
2,549 ± 472 / 784 ± 245 |
2.48 |
2.26 |
2.59 |
2.40 |
3.50 |
2.16 |
2.47 |
2.00 |
53.02 ± 2.85 / 41.35 ± 3.42 |
51.29 ± 3.42 / 66.57 ± 2.46 |
19.73 ± 4.11 / 57.07 ± 3.09 |
51.69 ± 2.29 / 61.26 ± 1.32 |
67.33 ± 1.40 / 22.77 ± 1.39 |
65.38 ± 2.59 / 73.95 ± 1.84 |
62.78 ± 4.04 / 74.61 ± 2.90 |
39.07 ± 2.57 / 53.83 ± 2.06 |
62.47 ± 2.56 / 57.71 ± 3.02 |
66.69 ± 2.91 / 58.83 ± 3.70 |
54.04 ± 2.91 / 66.46 ± 2.59 |
65.74 ± 0.37 / 19.13 ± 0.54 |
16.75 ± 4.54 / 49.11 ± 4.45 |
13.00 ± 4.46 / 49.33 ± 2.69 |
34.48 ± 2.13 / 65.43 ± 2.07 |
28.39 ± 1.76 / 45.59 ± 1.28 |
35.19 ± 3.28 / 50.12 ± 3.13 |
61.25 ± 3.35 / 50.76 ± 5.94 |
76.03 ± 2.11 / 78.25 ± 1.95 |
16.28 ± 4.81 / 49.04 ± 3.60 |
50.96 ± 2.34 / 60.05 ± 1.18 |
68.35 ± 0.32 / 24.05 ± 0.66 |
32.30 ± 2.48 / 48.98 ± 1.96 |
38.78 ± 5.70 / 52.89 ± 4.91 |
49.86 ± 4.28 / 42.54 ± 5.03 |
1.26 ± 3.83 / 48.46 ± 2.37 |
22.48 ± 4.43 / 55.51 ± 2.89 |
65.60 ± 0.69 / 19.46 ± 0.80 |
5.19 ± 3.15 / 28.44 ± 2.45 |
12.90 ± 6.92 / 56.88 ± 3.57 |
64.81 ± 3.03 / 53.01 ± 3.41 |
59.60 ± 2.81 / 72.42 ± 1.83 |
27.06 ± 4.53 / 63.33 ± 2.30 |
25.22 ± 3.84 / 60.93 ± 2.99 |
67.31 ± 1.05 / 24.72 ± 2.95 |
35.84 ± 2.16 / 51.64 ± 1.56 |
49.13 ± 2.71 / 61.68 ± 2.03 |
63.53 ± 3.80 / 50.43 ± 2.90 |
11.25 ± 4.22 / 39.00 ± 3.14 |
27.76 ± 4.44 / 62.44 ± 2.43 |
50.94 ± 1.12 / 70.12 ± 0.96 |
71.20 ± 0.46 / 23.47 ± 0.80 |
40.23 ± 2.86 / 54.77 ± 2.16 |
47.87 ± 2.49 / 60.78 ± 1.85 |
69.16 ± 2.80 / 57.28 ± 2.82 |
63.85 ± 2.16 / 72.40 ± 1.71 |
28.40 ± 3.60 / 62.70 ± 1.51 |
52.69 ± 2.21 / 76.37 ± 1.27 |
70.55 ± 0.73 / 26.32 ± 0.97 |
51.74 ± 1.82 / 63.44 ± 1.40 |
71.96 ± 2.38 / 78.87 ± 1.66 |
9.3.2 |
9.3.2 |
9.3.2 |
12.5.2 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.2 |
9.3.2 |
9.3.2 |
9.3.2 |
9.3.2 |
9.3.2 |
9.3.2 |
12.5.2 |
9.3.2 |
9.3.2 |
9.3.2 |
9.3.2 |
9.3.2 |
12.5.2 |
9.3.2 |
9.3.2 |
9.3.2 |
9.3.2 |
9.3.2 |
12.5.2 |
9.3.2 |
9.3.2 |
12.1.0 |
9.3.2 |
9.3.2 |
9.3.2 |
12.5.2 |
9.3.2 |
9.3.2 |
9.3.2 |
9.3.2 |
9.3.2 |
9.3.2 |
12.5.2 |
9.3.2 |
9.3.2 |
9.3.2 |
9.3.2 |
9.3.2 |
9.3.2 |
12.5.2 |
9.3.2 |
9.3.2 |
9.3.2 |
senseable/WestLake-7B-v2 (few-shot) |
7242 |
32 |
32768 |
False |
5,993 ± 1,028 / 1,742 ± 561 |
2.54 |
2.37 |
2.58 |
2.52 |
3.64 |
2.17 |
2.41 |
2.08 |
52.61 ± 1.77 / 33.64 ± 2.67 |
49.81 ± 1.43 / 66.32 ± 1.25 |
19.64 ± 1.63 / 54.22 ± 2.32 |
48.03 ± 1.24 / 57.94 ± 1.02 |
66.67 ± 0.87 / 21.08 ± 0.83 |
57.65 ± 1.99 / 68.08 ± 1.51 |
51.99 ± 3.67 / 66.43 ± 2.85 |
44.44 ± 1.52 / 58.16 ± 1.21 |
64.37 ± 2.17 / 52.81 ± 2.48 |
62.77 ± 0.83 / 51.80 ± 2.77 |
50.60 ± 4.90 / 66.76 ± 3.04 |
65.09 ± 0.31 / 17.27 ± 0.66 |
18.09 ± 2.04 / 52.56 ± 2.60 |
12.25 ± 2.18 / 50.79 ± 2.42 |
38.34 ± 2.39 / 69.54 ± 1.96 |
27.33 ± 0.72 / 45.16 ± 0.55 |
41.59 ± 2.61 / 56.02 ± 2.08 |
58.90 ± 1.34 / 42.48 ± 3.97 |
67.74 ± 2.79 / 71.89 ± 1.89 |
16.52 ± 2.55 / 46.30 ± 2.62 |
49.41 ± 1.21 / 59.91 ± 0.48 |
66.09 ± 0.17 / 19.64 ± 0.27 |
31.76 ± 0.89 / 48.64 ± 0.69 |
45.84 ± 1.47 / 59.27 ± 1.16 |
56.71 ± 1.98 / 46.71 ± 5.28 |
3.44 ± 2.02 / 50.18 ± 1.14 |
21.55 ± 2.79 / 54.79 ± 2.02 |
65.39 ± 0.80 / 18.24 ± 1.00 |
9.11 ± 0.92 / 32.06 ± 0.70 |
3.30 ± 2.81 / 44.40 ± 1.61 |
64.38 ± 1.60 / 50.26 ± 2.53 |
54.44 ± 1.45 / 69.32 ± 1.02 |
26.03 ± 2.23 / 61.88 ± 1.38 |
25.68 ± 2.81 / 62.48 ± 2.93 |
68.16 ± 0.95 / 24.52 ± 2.45 |
33.84 ± 1.54 / 50.24 ± 1.19 |
50.99 ± 0.99 / 63.11 ± 0.75 |
64.25 ± 2.23 / 46.52 ± 1.72 |
13.66 ± 1.99 / 39.45 ± 1.52 |
28.59 ± 1.48 / 61.24 ± 1.46 |
49.64 ± 0.86 / 68.04 ± 0.55 |
68.66 ± 0.57 / 19.51 ± 0.67 |
35.37 ± 1.30 / 51.43 ± 0.96 |
47.50 ± 1.75 / 60.41 ± 1.32 |
70.62 ± 0.90 / 58.92 ± 2.15 |
67.78 ± 1.03 / 72.29 ± 0.47 |
30.99 ± 2.94 / 62.20 ± 2.56 |
49.56 ± 2.85 / 76.72 ± 1.15 |
70.76 ± 0.56 / 24.95 ± 1.03 |
44.11 ± 4.39 / 57.76 ± 3.36 |
69.20 ± 2.71 / 76.75 ± 2.06 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.10.8 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
google/gemma-7b (few-shot) |
8538 |
256 |
8192 |
True |
1,378 ± 260 / 387 ± 119 |
2.58 |
2.46 |
2.67 |
2.34 |
3.44 |
2.13 |
2.77 |
2.22 |
19.59 ± 2.54 / 15.47 ± 2.19 |
46.55 ± 1.89 / 59.52 ± 3.56 |
32.64 ± 2.91 / 63.84 ± 1.69 |
59.40 ± 1.02 / 64.81 ± 0.91 |
66.63 ± 0.82 / 22.82 ± 0.62 |
74.32 ± 0.96 / 80.31 ± 0.79 |
65.58 ± 2.10 / 76.41 ± 1.54 |
24.74 ± 2.86 / 39.03 ± 1.70 |
26.43 ± 3.36 / 26.32 ± 2.35 |
32.66 ± 3.42 / 29.43 ± 1.74 |
41.82 ± 3.69 / 53.06 ± 5.15 |
64.02 ± 1.35 / 17.65 ± 1.59 |
25.82 ± 4.43 / 59.85 ± 4.07 |
20.16 ± 3.43 / 53.83 ± 5.61 |
52.68 ± 3.58 / 75.16 ± 2.44 |
39.96 ± 0.97 / 53.03 ± 0.89 |
27.82 ± 4.59 / 41.21 ± 4.09 |
43.68 ± 3.65 / 29.40 ± 3.10 |
77.72 ± 4.50 / 77.58 ± 4.13 |
36.25 ± 2.66 / 65.08 ± 2.92 |
58.62 ± 0.98 / 64.23 ± 0.88 |
64.44 ± 0.29 / 18.70 ± 0.57 |
39.94 ± 1.17 / 53.25 ± 0.89 |
25.96 ± 3.94 / 40.33 ± 3.17 |
30.61 ± 4.61 / 25.80 ± 3.57 |
5.60 ± 1.68 / 38.26 ± 2.47 |
32.22 ± 3.19 / 55.22 ± 2.59 |
65.03 ± 1.82 / 18.15 ± 2.24 |
32.53 ± 0.82 / 48.03 ± 0.80 |
1.14 ± 1.26 / 39.92 ± 1.92 |
39.88 ± 2.56 / 35.40 ± 2.63 |
56.23 ± 3.17 / 68.87 ± 2.73 |
32.71 ± 1.60 / 64.55 ± 1.54 |
36.58 ± 2.81 / 64.92 ± 2.97 |
69.41 ± 1.20 / 29.96 ± 3.00 |
41.56 ± 0.82 / 54.79 ± 0.60 |
30.77 ± 2.85 / 43.20 ± 2.53 |
47.75 ± 2.33 / 35.64 ± 1.89 |
7.68 ± 0.61 / 26.25 ± 1.18 |
28.28 ± 2.48 / 62.81 ± 1.70 |
61.49 ± 1.15 / 73.19 ± 0.81 |
65.60 ± 1.18 / 19.95 ± 1.23 |
42.19 ± 0.97 / 55.52 ± 0.93 |
31.45 ± 2.79 / 44.15 ± 3.09 |
47.20 ± 3.34 / 41.96 ± 3.12 |
63.88 ± 2.24 / 66.49 ± 0.81 |
35.75 ± 2.65 / 66.41 ± 2.26 |
69.40 ± 4.29 / 82.46 ± 2.86 |
69.25 ± 0.80 / 24.32 ± 0.95 |
50.57 ± 1.00 / 61.48 ± 0.80 |
35.79 ± 4.89 / 46.37 ± 3.67 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.10.0 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.10.8 |
12.10.0 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.10.0 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.10.0 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.10.0 |
mistralai/Mistral-7B-v0.1 (few-shot) |
7242 |
32 |
32768 |
True |
2,657 ± 524 / 880 ± 278 |
2.68 |
2.57 |
2.87 |
2.53 |
3.61 |
2.33 |
2.82 |
2.03 |
45.42 ± 2.88 / 32.66 ± 2.49 |
43.16 ± 1.69 / 54.53 ± 2.83 |
8.79 ± 3.23 / 38.38 ± 4.22 |
59.43 ± 1.04 / 64.55 ± 0.68 |
66.47 ± 1.00 / 22.11 ± 1.08 |
53.26 ± 1.94 / 64.50 ± 1.68 |
58.26 ± 2.62 / 71.56 ± 1.79 |
18.53 ± 2.03 / 37.79 ± 1.68 |
52.00 ± 1.91 / 43.55 ± 2.21 |
55.12 ± 3.14 / 45.34 ± 4.15 |
47.25 ± 4.11 / 64.53 ± 3.71 |
63.49 ± 1.49 / 16.48 ± 1.62 |
8.66 ± 4.12 / 38.87 ± 3.40 |
6.80 ± 1.59 / 39.72 ± 2.50 |
46.86 ± 3.27 / 70.86 ± 2.79 |
27.78 ± 1.08 / 45.76 ± 0.79 |
10.88 ± 3.63 / 32.43 ± 2.67 |
53.34 ± 2.55 / 40.48 ± 3.66 |
80.00 ± 0.70 / 79.80 ± 0.66 |
4.61 ± 2.18 / 34.51 ± 0.86 |
58.99 ± 1.05 / 64.65 ± 0.83 |
64.87 ± 0.31 / 19.30 ± 0.43 |
35.52 ± 1.01 / 51.52 ± 0.73 |
19.67 ± 2.31 / 38.98 ± 1.98 |
47.24 ± 2.54 / 37.77 ± 3.87 |
1.35 ± 1.70 / 39.37 ± 3.87 |
25.70 ± 5.36 / 49.31 ± 5.21 |
61.96 ± 3.10 / 16.11 ± 1.80 |
10.25 ± 0.96 / 32.89 ± 0.83 |
1.99 ± 2.95 / 54.48 ± 1.27 |
55.37 ± 1.32 / 44.65 ± 2.48 |
54.27 ± 1.71 / 68.13 ± 1.16 |
23.12 ± 4.07 / 57.81 ± 3.70 |
31.89 ± 3.29 / 59.77 ± 4.31 |
68.24 ± 0.70 / 25.71 ± 1.33 |
35.63 ± 1.12 / 51.69 ± 0.85 |
26.40 ± 1.86 / 43.98 ± 1.58 |
58.15 ± 1.14 / 40.78 ± 1.91 |
7.94 ± 1.25 / 31.02 ± 3.45 |
25.41 ± 3.46 / 61.11 ± 2.36 |
62.56 ± 1.10 / 73.16 ± 0.93 |
64.24 ± 0.91 / 17.54 ± 1.10 |
35.49 ± 0.57 / 51.51 ± 0.42 |
19.88 ± 1.80 / 39.13 ± 1.56 |
63.40 ± 2.72 / 56.92 ± 2.17 |
68.17 ± 1.33 / 70.74 ± 0.93 |
30.92 ± 4.81 / 63.79 ± 4.42 |
73.45 ± 1.83 / 84.54 ± 1.42 |
69.11 ± 0.31 / 23.70 ± 0.53 |
47.74 ± 1.26 / 60.63 ± 0.97 |
34.96 ± 4.19 / 49.62 ± 3.28 |
0.0.0 |
0.0.0 |
0.0.0 |
12.5.1 |
12.6.1 |
10.0.1 |
10.0.1 |
9.1.2 |
0.0.0 |
0.0.0 |
0.0.0 |
11.0.0 |
0.0.0 |
0.0.0 |
12.5.1 |
9.1.2 |
9.1.2 |
0.0.0 |
0.0.0 |
0.0.0 |
12.5.1 |
11.0.0 |
9.1.2 |
9.1.2 |
9.1.2 |
9.1.2 |
12.5.1 |
11.0.0 |
12.10.8 |
12.1.0 |
9.1.2 |
9.1.2 |
9.1.2 |
12.5.1 |
11.0.0 |
9.1.2 |
9.2.0 |
9.1.2 |
9.1.2 |
9.1.2 |
12.5.1 |
11.0.0 |
9.2.0 |
9.2.0 |
9.1.2 |
9.1.2 |
9.1.2 |
12.5.1 |
11.0.0 |
9.2.0 |
9.2.0 |
mistralai/Mistral-7B-v0.3 (few-shot) |
7248 |
33 |
32768 |
True |
4,120 ± 976 / 926 ± 306 |
2.71 |
2.51 |
2.88 |
2.56 |
3.66 |
2.36 |
2.96 |
2.06 |
43.60 ± 2.94 / 32.17 ± 2.26 |
45.92 ± 1.50 / 61.91 ± 1.50 |
15.43 ± 3.79 / 46.20 ± 5.54 |
59.13 ± 0.86 / 64.43 ± 0.58 |
66.33 ± 0.98 / 22.03 ± 0.96 |
53.81 ± 1.88 / 64.81 ± 1.53 |
61.06 ± 2.83 / 73.89 ± 2.00 |
20.64 ± 1.95 / 39.21 ± 1.79 |
50.56 ± 2.04 / 44.38 ± 1.85 |
52.65 ± 2.27 / 46.48 ± 3.65 |
44.61 ± 2.28 / 62.22 ± 2.10 |
63.13 ± 1.63 / 16.19 ± 1.73 |
12.10 ± 4.22 / 43.27 ± 5.24 |
9.30 ± 0.99 / 46.11 ± 3.47 |
45.15 ± 3.72 / 68.61 ± 3.30 |
28.31 ± 1.01 / 45.93 ± 0.80 |
13.59 ± 2.44 / 33.95 ± 1.83 |
49.18 ± 2.71 / 39.25 ± 3.60 |
79.08 ± 0.77 / 78.81 ± 0.94 |
11.06 ± 3.55 / 38.96 ± 3.77 |
58.98 ± 1.04 / 64.79 ± 0.79 |
64.79 ± 0.32 / 19.30 ± 0.42 |
34.51 ± 1.13 / 50.46 ± 0.88 |
20.84 ± 2.19 / 39.88 ± 1.85 |
44.68 ± 3.50 / 36.20 ± 4.20 |
0.12 ± 1.68 / 35.09 ± 1.17 |
25.52 ± 5.24 / 49.15 ± 5.21 |
61.40 ± 2.38 / 14.90 ± 1.60 |
10.25 ± 1.54 / 32.81 ± 1.22 |
5.24 ± 1.65 / 52.80 ± 2.41 |
55.41 ± 1.45 / 48.39 ± 1.46 |
52.58 ± 2.42 / 67.52 ± 1.82 |
24.10 ± 2.12 / 59.47 ± 2.92 |
31.52 ± 2.95 / 60.03 ± 3.81 |
68.96 ± 1.13 / 28.26 ± 2.32 |
35.06 ± 0.54 / 51.20 ± 0.43 |
28.85 ± 1.70 / 45.83 ± 1.39 |
56.52 ± 1.42 / 41.84 ± 1.84 |
7.02 ± 1.21 / 26.40 ± 2.96 |
23.41 ± 2.91 / 59.14 ± 3.11 |
61.90 ± 1.07 / 72.49 ± 1.05 |
64.37 ± 0.74 / 17.69 ± 0.90 |
34.93 ± 1.11 / 51.02 ± 0.87 |
23.73 ± 1.97 / 41.93 ± 1.68 |
61.02 ± 2.74 / 55.65 ± 2.55 |
67.29 ± 0.80 / 70.81 ± 0.84 |
30.10 ± 5.12 / 62.99 ± 4.71 |
73.59 ± 1.75 / 84.31 ± 1.35 |
69.04 ± 0.56 / 23.86 ± 0.77 |
47.63 ± 1.17 / 60.45 ± 0.88 |
35.63 ± 4.21 / 49.72 ± 3.73 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.8 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.4 |
12.10.4 |
meta-llama/Llama-2-13b-chat-hf (few-shot) |
13016 |
32 |
4096 |
True |
2,849 ± 622 / 723 ± 229 |
2.82 |
2.59 |
2.90 |
2.63 |
3.86 |
2.46 |
3.02 |
2.31 |
44.00 ± 2.63 / 29.00 ± 2.26 |
45.41 ± 1.79 / 62.27 ± 2.34 |
16.17 ± 2.17 / 56.93 ± 1.29 |
57.06 ± 0.83 / 63.94 ± 0.49 |
66.88 ± 0.98 / 21.84 ± 1.04 |
45.21 ± 1.90 / 57.54 ± 1.55 |
51.06 ± 2.13 / 67.44 ± 1.41 |
16.50 ± 1.48 / 36.77 ± 1.21 |
57.21 ± 1.51 / 40.40 ± 2.79 |
59.62 ± 1.34 / 41.07 ± 2.58 |
38.93 ± 3.56 / 57.45 ± 3.77 |
65.12 ± 0.35 / 17.27 ± 0.70 |
8.65 ± 3.33 / 47.18 ± 3.98 |
5.92 ± 1.58 / 47.50 ± 3.58 |
42.32 ± 2.80 / 69.24 ± 2.68 |
23.88 ± 1.01 / 42.37 ± 0.80 |
22.33 ± 1.67 / 41.00 ± 1.40 |
49.90 ± 2.28 / 35.48 ± 3.44 |
77.19 ± 2.05 / 79.13 ± 1.43 |
14.67 ± 2.27 / 53.90 ± 2.24 |
57.12 ± 0.70 / 63.72 ± 0.73 |
66.25 ± 0.10 / 19.64 ± 0.19 |
24.40 ± 1.20 / 42.73 ± 0.90 |
19.30 ± 1.27 / 38.75 ± 1.05 |
37.53 ± 3.42 / 30.51 ± 3.50 |
0.14 ± 1.96 / 39.45 ± 3.51 |
20.91 ± 2.93 / 43.86 ± 1.90 |
66.15 ± 0.59 / 19.08 ± 1.08 |
7.17 ± 1.32 / 30.61 ± 0.94 |
-0.55 ± 2.76 / 47.83 ± 2.20 |
57.57 ± 1.46 / 44.84 ± 2.12 |
49.40 ± 2.11 / 63.02 ± 2.68 |
23.32 ± 2.20 / 59.16 ± 2.36 |
30.24 ± 1.18 / 61.10 ± 1.87 |
68.01 ± 1.28 / 25.44 ± 3.23 |
27.06 ± 0.92 / 45.06 ± 0.75 |
26.96 ± 0.49 / 44.79 ± 0.39 |
57.80 ± 1.53 / 39.43 ± 1.53 |
8.57 ± 1.27 / 29.84 ± 2.35 |
17.40 ± 1.54 / 57.26 ± 1.96 |
56.35 ± 0.85 / 69.69 ± 0.76 |
66.11 ± 0.58 / 18.31 ± 0.61 |
27.15 ± 1.09 / 44.95 ± 0.78 |
19.18 ± 1.46 / 38.84 ± 1.26 |
68.75 ± 1.54 / 60.01 ± 1.57 |
62.37 ± 1.68 / 67.79 ± 1.51 |
25.07 ± 3.20 / 61.02 ± 2.86 |
61.56 ± 1.18 / 80.11 ± 0.70 |
69.40 ± 0.49 / 24.79 ± 0.61 |
38.00 ± 0.83 / 52.95 ± 0.66 |
42.14 ± 2.47 / 55.96 ± 1.93 |
12.10.5 |
12.10.4 |
12.10.4 |
12.11.0 |
12.11.0 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.4 |
12.11.0 |
12.10.4 |
12.10.4 |
12.11.0 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.4 |
12.11.0 |
12.11.0 |
12.10.4 |
12.10.4 |
12.11.0 |
12.10.4 |
12.11.0 |
12.11.0 |
12.11.0 |
12.10.4 |
12.11.0 |
12.10.4 |
12.10.4 |
12.11.0 |
12.11.0 |
12.10.4 |
12.10.4 |
12.11.0 |
12.10.4 |
12.10.4 |
12.11.0 |
12.11.0 |
12.10.4 |
12.10.4 |
12.11.0 |
12.10.4 |
12.10.4 |
12.11.0 |
12.11.0 |
12.10.4 |
12.10.4 |
timpal0l/Mistral-7B-v0.1-flashback-v2 (few-shot) |
7242 |
32 |
32768 |
True |
5,054 ± 1,200 / 1,056 ± 339 |
2.85 |
2.62 |
2.86 |
2.43 |
3.84 |
2.63 |
3.31 |
2.23 |
42.43 ± 3.36 / 29.30 ± 2.53 |
47.82 ± 2.00 / 63.19 ± 2.09 |
16.51 ± 2.59 / 52.73 ± 3.91 |
56.95 ± 1.21 / 62.20 ± 0.83 |
65.43 ± 1.12 / 20.36 ± 0.95 |
50.76 ± 1.75 / 62.66 ± 1.43 |
50.82 ± 1.17 / 66.66 ± 0.76 |
14.47 ± 2.35 / 34.86 ± 1.97 |
48.97 ± 2.42 / 39.15 ± 2.78 |
51.52 ± 2.96 / 40.17 ± 3.62 |
49.05 ± 2.73 / 63.94 ± 2.42 |
63.32 ± 1.58 / 16.33 ± 1.63 |
14.37 ± 2.18 / 47.80 ± 4.36 |
9.96 ± 1.34 / 48.97 ± 3.77 |
44.07 ± 3.40 / 68.49 ± 2.97 |
25.07 ± 1.48 / 43.13 ± 1.15 |
15.56 ± 3.55 / 35.85 ± 2.56 |
44.14 ± 2.40 / 29.77 ± 4.06 |
80.14 ± 1.11 / 80.19 ± 0.78 |
34.23 ± 2.23 / 65.29 ± 2.17 |
57.07 ± 1.56 / 62.52 ± 1.11 |
65.15 ± 0.31 / 18.72 ± 0.57 |
33.24 ± 0.85 / 49.69 ± 0.67 |
25.50 ± 2.25 / 43.44 ± 2.03 |
36.47 ± 4.24 / 30.33 ± 3.70 |
2.54 ± 1.29 / 50.66 ± 0.62 |
18.66 ± 4.26 / 38.73 ± 3.66 |
63.68 ± 1.75 / 16.38 ± 1.24 |
5.12 ± 1.30 / 28.85 ± 0.99 |
8.30 ± 1.28 / 57.35 ± 0.75 |
50.66 ± 1.53 / 39.89 ± 2.43 |
54.79 ± 3.53 / 68.79 ± 3.00 |
20.17 ± 1.69 / 58.67 ± 1.13 |
27.86 ± 4.70 / 54.38 ± 5.91 |
65.53 ± 1.07 / 19.46 ± 1.48 |
27.04 ± 1.04 / 44.99 ± 0.77 |
17.47 ± 3.26 / 36.70 ± 2.93 |
54.56 ± 2.96 / 37.86 ± 2.49 |
8.43 ± 1.27 / 24.23 ± 0.94 |
10.99 ± 2.55 / 50.46 ± 4.17 |
55.91 ± 1.08 / 66.78 ± 1.13 |
57.88 ± 1.41 / 12.36 ± 1.30 |
25.12 ± 1.17 / 43.50 ± 0.92 |
10.65 ± 1.55 / 31.51 ± 1.52 |
59.10 ± 1.87 / 51.31 ± 1.87 |
68.41 ± 1.17 / 70.85 ± 0.74 |
25.43 ± 4.22 / 60.79 ± 3.45 |
71.89 ± 2.20 / 82.99 ± 1.78 |
67.99 ± 0.41 / 22.12 ± 0.52 |
44.09 ± 1.21 / 56.37 ± 0.96 |
32.29 ± 4.57 / 45.16 ± 4.28 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.6.1 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.10.8 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
meta-llama/Llama-2-13b-hf (few-shot) |
13016 |
32 |
4096 |
True |
2,898 ± 637 / 736 ± 236 |
2.87 |
2.79 |
3.03 |
2.57 |
3.90 |
2.42 |
3.16 |
2.24 |
41.28 ± 3.92 / 31.98 ± 3.26 |
23.01 ± 3.87 / 36.55 ± 6.42 |
23.50 ± 2.75 / 58.11 ± 3.45 |
60.29 ± 0.81 / 65.52 ± 0.58 |
66.28 ± 1.20 / 21.69 ± 1.21 |
50.30 ± 2.37 / 61.85 ± 1.93 |
56.24 ± 2.29 / 70.27 ± 1.64 |
15.43 ± 0.95 / 35.31 ± 0.71 |
51.12 ± 3.13 / 47.26 ± 2.62 |
55.35 ± 1.60 / 49.99 ± 2.21 |
23.75 ± 3.25 / 42.92 ± 4.45 |
64.56 ± 1.30 / 18.13 ± 1.51 |
14.00 ± 4.25 / 42.71 ± 5.83 |
7.61 ± 2.57 / 45.86 ± 3.96 |
49.24 ± 4.28 / 72.68 ± 3.66 |
23.60 ± 1.05 / 42.20 ± 0.80 |
16.55 ± 2.83 / 35.97 ± 1.94 |
54.52 ± 3.33 / 44.11 ± 5.29 |
78.45 ± 1.21 / 79.73 ± 0.97 |
21.55 ± 3.74 / 49.54 ± 4.41 |
59.71 ± 0.68 / 65.01 ± 0.64 |
64.59 ± 0.34 / 18.56 ± 0.39 |
25.51 ± 0.81 / 43.68 ± 0.60 |
14.97 ± 1.73 / 34.85 ± 1.34 |
36.56 ± 3.03 / 34.23 ± 3.45 |
1.73 ± 1.56 / 45.02 ± 2.05 |
21.97 ± 4.26 / 46.27 ± 3.94 |
63.50 ± 2.92 / 16.51 ± 2.19 |
5.60 ± 1.25 / 29.83 ± 1.00 |
-5.80 ± 2.91 / 46.82 ± 2.65 |
52.08 ± 1.86 / 46.67 ± 1.17 |
46.38 ± 2.70 / 60.32 ± 2.80 |
22.39 ± 3.96 / 57.26 ± 4.22 |
33.43 ± 2.38 / 62.65 ± 2.83 |
69.50 ± 1.29 / 29.74 ± 3.10 |
28.79 ± 1.53 / 45.87 ± 1.26 |
21.50 ± 2.52 / 39.80 ± 2.47 |
52.55 ± 1.64 / 43.32 ± 1.70 |
4.26 ± 2.09 / 28.32 ± 2.68 |
24.57 ± 3.54 / 54.94 ± 5.33 |
60.99 ± 0.95 / 72.74 ± 0.78 |
64.02 ± 0.84 / 16.97 ± 0.98 |
28.73 ± 0.90 / 45.62 ± 0.64 |
19.43 ± 1.53 / 38.57 ± 1.39 |
63.75 ± 2.50 / 59.28 ± 2.20 |
61.85 ± 1.70 / 69.02 ± 0.76 |
26.41 ± 4.93 / 59.67 ± 4.84 |
73.48 ± 2.06 / 85.27 ± 1.15 |
67.73 ± 0.58 / 22.39 ± 0.65 |
38.04 ± 1.30 / 53.30 ± 0.99 |
28.16 ± 3.07 / 44.80 ± 2.46 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.8 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.4 |
12.10.4 |
mistralai/Mistral-7B-Instruct-v0.2 (few-shot) |
7242 |
32 |
32768 |
False |
634 ± 179 / 110 ± 35 |
2.87 |
2.62 |
3.02 |
2.78 |
3.80 |
2.60 |
2.87 |
2.37 |
44.89 ± 2.46 / 29.13 ± 1.92 |
48.09 ± 1.00 / 65.40 ± 0.75 |
19.06 ± 2.34 / 58.77 ± 1.37 |
51.56 ± 1.16 / 60.81 ± 0.74 |
66.84 ± 0.77 / 21.21 ± 1.08 |
51.60 ± 1.33 / 63.50 ± 1.03 |
35.85 ± 2.68 / 52.62 ± 2.08 |
22.21 ± 1.60 / 40.78 ± 1.32 |
53.42 ± 2.48 / 42.63 ± 1.66 |
54.34 ± 1.93 / 41.06 ± 2.40 |
38.79 ± 2.56 / 53.72 ± 3.01 |
64.43 ± 0.45 / 16.11 ± 0.97 |
17.06 ± 1.53 / 56.51 ± 2.06 |
11.00 ± 1.00 / 53.26 ± 2.32 |
35.74 ± 2.44 / 64.27 ± 2.42 |
20.37 ± 1.34 / 39.32 ± 1.03 |
21.16 ± 2.07 / 39.85 ± 1.73 |
47.92 ± 2.66 / 33.00 ± 3.24 |
62.90 ± 2.44 / 70.61 ± 1.19 |
19.95 ± 2.24 / 56.49 ± 2.10 |
52.51 ± 0.36 / 61.42 ± 0.52 |
66.11 ± 0.18 / 19.64 ± 0.28 |
25.60 ± 1.10 / 43.53 ± 0.90 |
21.75 ± 1.61 / 40.57 ± 1.45 |
43.11 ± 2.23 / 29.34 ± 3.27 |
3.40 ± 1.87 / 48.75 ± 1.47 |
19.18 ± 3.69 / 49.62 ± 2.59 |
65.01 ± 1.51 / 18.34 ± 1.35 |
5.49 ± 1.98 / 28.73 ± 1.39 |
0.24 ± 0.71 / 38.95 ± 0.84 |
55.10 ± 1.35 / 41.89 ± 1.61 |
47.69 ± 2.35 / 64.93 ± 1.71 |
24.14 ± 2.09 / 60.83 ± 1.63 |
23.93 ± 2.11 / 57.64 ± 1.89 |
67.51 ± 0.71 / 22.63 ± 1.73 |
26.06 ± 1.65 / 44.13 ± 1.29 |
31.09 ± 1.35 / 47.48 ± 0.98 |
55.56 ± 2.66 / 39.56 ± 2.13 |
12.37 ± 1.64 / 37.37 ± 1.35 |
21.50 ± 1.70 / 59.10 ± 1.32 |
50.77 ± 0.95 / 66.54 ± 0.79 |
67.99 ± 0.49 / 19.54 ± 0.55 |
22.86 ± 1.89 / 41.71 ± 1.45 |
24.80 ± 1.77 / 42.93 ± 1.38 |
62.11 ± 1.61 / 52.36 ± 2.00 |
59.91 ± 2.10 / 68.92 ± 1.21 |
30.66 ± 3.60 / 64.32 ± 2.03 |
58.27 ± 2.09 / 77.85 ± 0.70 |
69.75 ± 0.63 / 24.71 ± 0.72 |
34.93 ± 1.35 / 50.71 ± 1.00 |
44.91 ± 2.44 / 58.07 ± 1.93 |
9.2.0 |
9.2.0 |
9.3.1 |
12.4.0 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.2 |
9.2.0 |
9.2.0 |
9.2.0 |
12.4.0 |
9.3.1 |
9.3.1 |
12.4.0 |
9.3.2 |
9.3.2 |
9.2.0 |
9.2.0 |
9.3.1 |
12.4.0 |
12.4.0 |
9.3.2 |
9.3.2 |
9.2.0 |
9.3.1 |
12.4.0 |
12.4.0 |
12.10.8 |
12.1.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
9.3.1 |
9.2.0 |
9.3.1 |
12.4.0 |
12.4.0 |
9.3.2 |
9.3.2 |
9.3.1 |
9.2.0 |
9.3.1 |
12.4.0 |
12.4.0 |
9.3.2 |
9.3.2 |
occiglot/occiglot-7b-eu5-instruct (few-shot) |
7242 |
32 |
32768 |
False |
2,088 ± 352 / 706 ± 214 |
2.87 |
2.77 |
2.98 |
2.78 |
3.87 |
2.35 |
2.98 |
2.35 |
40.19 ± 2.55 / 29.73 ± 1.44 |
42.31 ± 1.55 / 59.29 ± 2.00 |
1.14 ± 1.22 / 33.83 ± 0.72 |
57.89 ± 1.16 / 63.95 ± 0.82 |
66.68 ± 0.81 / 22.38 ± 0.71 |
44.30 ± 2.46 / 57.00 ± 2.30 |
48.76 ± 2.39 / 65.51 ± 1.72 |
15.44 ± 1.66 / 35.82 ± 1.14 |
45.50 ± 2.71 / 40.02 ± 3.16 |
45.96 ± 2.67 / 41.28 ± 2.25 |
44.46 ± 3.40 / 62.00 ± 2.71 |
63.95 ± 0.42 / 16.91 ± 0.61 |
0.00 ± 0.00 / 33.41 ± 0.30 |
0.00 ± 0.00 / 33.86 ± 0.33 |
52.19 ± 2.88 / 74.97 ± 2.11 |
20.61 ± 1.27 / 39.79 ± 1.10 |
16.18 ± 1.88 / 36.19 ± 1.66 |
47.67 ± 2.81 / 36.91 ± 3.50 |
71.73 ± 2.40 / 74.97 ± 1.84 |
7.90 ± 3.20 / 41.24 ± 4.78 |
57.78 ± 0.79 / 64.48 ± 0.73 |
65.07 ± 0.34 / 19.59 ± 0.38 |
25.52 ± 1.30 / 43.68 ± 1.03 |
14.06 ± 1.68 / 35.12 ± 1.47 |
40.71 ± 2.93 / 34.57 ± 4.02 |
0.71 ± 2.00 / 36.90 ± 2.10 |
20.66 ± 3.67 / 45.91 ± 3.45 |
65.25 ± 0.97 / 19.09 ± 1.05 |
5.35 ± 1.32 / 28.11 ± 1.13 |
0.35 ± 2.49 / 51.16 ± 2.74 |
52.63 ± 1.89 / 42.99 ± 2.40 |
43.16 ± 4.45 / 57.79 ± 4.61 |
27.09 ± 1.92 / 60.29 ± 1.99 |
34.01 ± 4.01 / 63.29 ± 3.97 |
69.43 ± 0.97 / 29.48 ± 2.59 |
32.56 ± 1.16 / 49.02 ± 0.79 |
23.61 ± 2.42 / 41.55 ± 2.14 |
53.78 ± 1.86 / 41.29 ± 2.07 |
7.78 ± 1.43 / 24.33 ± 1.57 |
16.23 ± 2.49 / 55.09 ± 3.18 |
63.09 ± 1.18 / 73.88 ± 0.72 |
66.46 ± 0.67 / 19.49 ± 0.92 |
28.37 ± 0.99 / 45.81 ± 0.88 |
15.25 ± 1.71 / 35.83 ± 1.42 |
56.90 ± 3.08 / 51.16 ± 2.56 |
62.10 ± 1.65 / 68.81 ± 0.76 |
20.17 ± 3.68 / 54.76 ± 4.24 |
75.29 ± 1.37 / 86.48 ± 0.72 |
69.63 ± 0.46 / 25.61 ± 0.45 |
38.48 ± 1.10 / 53.32 ± 0.83 |
27.67 ± 2.08 / 43.61 ± 2.08 |
12.5.2 |
12.2.0 |
12.3.1 |
12.4.0 |
12.6.1 |
12.3.1 |
12.3.1 |
12.3.1 |
12.5.2 |
12.5.2 |
12.2.0 |
12.4.0 |
12.3.1 |
12.3.1 |
12.4.0 |
12.3.1 |
12.3.1 |
12.5.2 |
12.2.0 |
12.3.1 |
12.4.0 |
12.4.0 |
12.3.1 |
12.3.1 |
12.5.2 |
12.3.1 |
12.4.0 |
12.4.0 |
12.10.8 |
12.3.1 |
12.5.2 |
12.2.0 |
12.3.1 |
12.4.0 |
12.4.0 |
12.3.1 |
12.3.1 |
12.5.2 |
12.2.0 |
12.3.1 |
12.4.0 |
12.4.0 |
12.3.1 |
12.3.1 |
12.5.2 |
12.2.0 |
12.3.1 |
12.4.0 |
12.4.0 |
12.3.1 |
12.3.1 |
microsoft/Phi-3-mini-4k-instruct (few-shot) |
3821 |
32 |
4096 |
True |
5,224 ± 1,371 / 1,063 ± 358 |
2.90 |
2.98 |
3.25 |
3.09 |
4.11 |
2.09 |
2.95 |
1.80 |
41.37 ± 2.50 / 24.64 ± 2.50 |
42.60 ± 1.06 / 61.52 ± 0.75 |
6.52 ± 1.34 / 45.01 ± 2.64 |
50.57 ± 1.03 / 57.75 ± 0.64 |
64.55 ± 0.78 / 19.26 ± 0.48 |
38.64 ± 1.52 / 53.92 ± 1.16 |
42.12 ± 2.16 / 61.23 ± 1.46 |
13.66 ± 1.32 / 35.16 ± 1.02 |
56.33 ± 1.63 / 36.68 ± 3.27 |
54.68 ± 1.29 / 37.85 ± 3.79 |
37.18 ± 1.30 / 55.44 ± 1.46 |
61.44 ± 0.71 / 13.62 ± 0.60 |
6.76 ± 2.81 / 41.69 ± 2.82 |
6.79 ± 1.51 / 45.45 ± 3.51 |
30.11 ± 2.09 / 52.56 ± 2.38 |
15.54 ± 0.89 / 36.69 ± 0.67 |
17.55 ± 0.88 / 37.93 ± 0.71 |
46.15 ± 2.77 / 24.28 ± 3.74 |
67.17 ± 1.93 / 70.99 ± 1.64 |
5.30 ± 1.62 / 47.01 ± 3.23 |
51.12 ± 1.02 / 57.49 ± 0.81 |
59.20 ± 0.99 / 15.57 ± 0.62 |
21.33 ± 1.03 / 41.04 ± 0.78 |
16.12 ± 1.15 / 36.99 ± 0.85 |
33.05 ± 4.29 / 29.75 ± 3.67 |
0.71 ± 1.18 / 34.80 ± 0.88 |
17.23 ± 2.51 / 39.88 ± 1.59 |
60.08 ± 1.45 / 13.80 ± 0.81 |
2.67 ± 1.35 / 27.04 ± 1.07 |
2.74 ± 2.28 / 53.18 ± 0.93 |
59.68 ± 0.41 / 48.00 ± 2.44 |
54.75 ± 2.36 / 68.54 ± 1.62 |
30.22 ± 2.94 / 64.51 ± 1.55 |
29.27 ± 1.03 / 59.19 ± 2.46 |
66.64 ± 0.91 / 22.90 ± 2.24 |
39.50 ± 0.93 / 54.61 ± 0.68 |
51.29 ± 1.38 / 63.10 ± 1.12 |
50.31 ± 1.94 / 41.54 ± 2.19 |
12.58 ± 1.62 / 36.56 ± 1.79 |
14.72 ± 1.84 / 50.23 ± 3.10 |
56.19 ± 0.80 / 66.72 ± 0.92 |
64.40 ± 0.77 / 17.47 ± 0.56 |
28.31 ± 0.70 / 46.18 ± 0.50 |
21.25 ± 1.25 / 40.78 ± 1.02 |
66.13 ± 1.16 / 53.55 ± 2.73 |
63.66 ± 1.31 / 70.60 ± 0.63 |
34.07 ± 2.32 / 66.51 ± 1.23 |
68.10 ± 1.44 / 83.46 ± 1.01 |
69.32 ± 0.53 / 24.97 ± 0.93 |
59.24 ± 1.04 / 69.46 ± 0.78 |
74.58 ± 0.91 / 80.88 ± 0.69 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.8 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
meta-llama/Llama-3.2-3B-Instruct (few-shot) |
3213 |
128 |
131073 |
False |
3,602 ± 855 / 779 ± 245 |
2.96 |
2.81 |
3.17 |
2.77 |
3.95 |
2.76 |
3.00 |
2.28 |
41.18 ± 3.20 / 32.45 ± 2.58 |
43.08 ± 2.67 / 55.24 ± 4.09 |
11.45 ± 2.51 / 48.94 ± 3.94 |
51.34 ± 0.97 / 60.36 ± 0.48 |
65.15 ± 0.76 / 18.26 ± 1.21 |
49.85 ± 1.21 / 62.33 ± 0.91 |
45.59 ± 2.48 / 63.79 ± 1.63 |
21.76 ± 1.73 / 41.05 ± 1.41 |
49.69 ± 1.94 / 39.29 ± 2.44 |
52.21 ± 1.52 / 42.35 ± 3.13 |
43.89 ± 2.81 / 60.00 ± 3.12 |
60.43 ± 0.73 / 10.79 ± 0.59 |
1.41 ± 1.13 / 33.83 ± 0.32 |
0.37 ± 1.54 / 33.05 ± 0.44 |
28.31 ± 4.35 / 56.65 ± 4.40 |
26.91 ± 1.15 / 45.39 ± 0.88 |
20.36 ± 1.44 / 39.83 ± 1.18 |
44.07 ± 2.72 / 34.70 ± 2.81 |
77.02 ± 1.42 / 71.72 ± 3.23 |
15.99 ± 2.27 / 51.80 ± 3.49 |
48.73 ± 1.71 / 58.15 ± 0.93 |
65.00 ± 0.44 / 17.46 ± 0.50 |
29.49 ± 0.69 / 47.24 ± 0.51 |
21.55 ± 1.88 / 40.77 ± 1.53 |
27.62 ± 1.70 / 22.55 ± 1.19 |
-1.62 ± 1.10 / 34.28 ± 1.83 |
23.02 ± 2.62 / 51.06 ± 1.56 |
62.22 ± 1.82 / 14.45 ± 1.88 |
13.54 ± 1.19 / 35.59 ± 0.88 |
0.50 ± 1.49 / 50.68 ± 1.09 |
55.42 ± 1.99 / 46.19 ± 2.30 |
50.29 ± 2.09 / 62.31 ± 2.47 |
8.97 ± 3.25 / 42.52 ± 3.62 |
20.74 ± 3.25 / 47.89 ± 5.28 |
66.54 ± 0.96 / 21.46 ± 2.28 |
33.51 ± 0.52 / 50.21 ± 0.36 |
28.84 ± 1.08 / 46.33 ± 0.83 |
43.19 ± 1.84 / 39.97 ± 1.68 |
13.18 ± 1.38 / 37.51 ± 1.49 |
18.16 ± 3.57 / 56.12 ± 3.80 |
47.91 ± 1.66 / 64.60 ± 1.26 |
66.84 ± 0.97 / 18.41 ± 1.24 |
33.80 ± 0.79 / 50.30 ± 0.56 |
20.78 ± 1.30 / 40.04 ± 1.10 |
68.47 ± 1.03 / 56.81 ± 2.29 |
66.08 ± 1.48 / 70.50 ± 1.03 |
31.70 ± 3.54 / 65.45 ± 1.97 |
49.55 ± 2.95 / 75.21 ± 1.57 |
69.23 ± 0.19 / 24.73 ± 0.38 |
45.37 ± 0.72 / 58.87 ± 0.55 |
46.70 ± 1.80 / 59.57 ± 1.46 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
occiglot/occiglot-7b-eu5 (few-shot) |
7242 |
32 |
32768 |
True |
2,219 ± 427 / 717 ± 224 |
2.96 |
2.86 |
3.09 |
2.78 |
3.95 |
2.45 |
3.13 |
2.47 |
37.93 ± 3.09 / 29.50 ± 2.18 |
44.62 ± 1.98 / 62.62 ± 1.54 |
0.28 ± 0.54 / 33.48 ± 0.24 |
58.05 ± 1.02 / 62.89 ± 0.89 |
66.05 ± 1.13 / 21.82 ± 0.96 |
38.54 ± 1.47 / 53.57 ± 1.26 |
45.89 ± 3.00 / 63.14 ± 1.98 |
12.38 ± 1.99 / 33.54 ± 1.61 |
45.28 ± 3.06 / 41.73 ± 2.14 |
46.00 ± 4.26 / 42.96 ± 3.38 |
44.95 ± 3.19 / 61.88 ± 2.88 |
63.26 ± 1.07 / 16.04 ± 1.34 |
0.00 ± 0.00 / 33.41 ± 0.30 |
0.00 ± 0.00 / 33.86 ± 0.33 |
43.88 ± 4.07 / 66.65 ± 4.20 |
20.87 ± 1.54 / 39.98 ± 1.27 |
13.10 ± 2.04 / 34.20 ± 1.55 |
49.02 ± 3.23 / 41.69 ± 3.74 |
76.56 ± 1.52 / 78.16 ± 1.12 |
2.18 ± 2.34 / 36.26 ± 3.89 |
58.98 ± 0.95 / 63.65 ± 0.89 |
64.42 ± 0.45 / 18.79 ± 0.47 |
23.68 ± 1.41 / 42.15 ± 1.14 |
14.05 ± 1.60 / 34.81 ± 1.58 |
40.08 ± 2.82 / 37.15 ± 4.07 |
1.59 ± 1.86 / 39.93 ± 4.19 |
15.98 ± 3.74 / 39.67 ± 3.36 |
62.55 ± 3.03 / 15.26 ± 2.31 |
5.98 ± 1.66 / 28.18 ± 1.30 |
-0.51 ± 1.95 / 47.23 ± 2.39 |
51.39 ± 1.35 / 44.47 ± 2.77 |
47.30 ± 4.44 / 62.28 ± 4.24 |
21.83 ± 1.98 / 57.05 ± 2.18 |
31.55 ± 3.67 / 60.39 ± 4.29 |
69.31 ± 0.68 / 28.27 ± 1.70 |
32.49 ± 0.91 / 48.82 ± 0.70 |
22.25 ± 2.13 / 40.28 ± 1.67 |
51.31 ± 2.32 / 42.95 ± 2.58 |
7.41 ± 1.24 / 26.93 ± 1.56 |
13.04 ± 1.93 / 53.54 ± 2.70 |
59.28 ± 1.15 / 69.67 ± 0.95 |
64.66 ± 0.74 / 18.22 ± 0.85 |
27.12 ± 0.86 / 44.36 ± 0.75 |
13.99 ± 2.04 / 34.45 ± 1.89 |
55.37 ± 2.94 / 51.08 ± 2.87 |
63.32 ± 1.29 / 68.50 ± 0.53 |
18.92 ± 2.39 / 57.96 ± 1.89 |
72.38 ± 2.57 / 83.46 ± 1.49 |
68.61 ± 0.55 / 23.48 ± 0.74 |
37.04 ± 1.33 / 52.33 ± 1.02 |
23.54 ± 2.08 / 40.78 ± 1.59 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.2.0 |
12.5.2 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.2.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.2.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.10.8 |
12.2.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.2.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.2.0 |
12.2.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.2.0 |
12.2.0 |
01-ai/Yi-1.5-6B (few-shot) |
6061 |
64 |
4097 |
True |
2,867 ± 550 / 793 ± 253 |
2.97 |
3.19 |
3.14 |
2.82 |
3.86 |
2.69 |
3.19 |
1.90 |
35.21 ± 2.52 / 23.65 ± 2.52 |
12.73 ± 2.87 / 22.69 ± 1.80 |
4.75 ± 2.45 / 35.71 ± 3.01 |
55.95 ± 1.09 / 61.53 ± 0.75 |
64.28 ± 0.93 / 18.81 ± 0.83 |
46.17 ± 1.83 / 59.04 ± 1.44 |
36.46 ± 2.46 / 57.64 ± 1.59 |
18.01 ± 1.66 / 38.12 ± 1.37 |
46.02 ± 2.12 / 35.05 ± 2.84 |
48.72 ± 1.76 / 35.97 ± 2.78 |
27.86 ± 0.76 / 31.62 ± 0.80 |
60.92 ± 1.45 / 13.73 ± 1.28 |
2.41 ± 1.92 / 35.60 ± 2.65 |
2.50 ± 2.05 / 34.90 ± 1.27 |
44.70 ± 3.79 / 67.06 ± 2.85 |
23.93 ± 1.18 / 42.87 ± 0.91 |
22.39 ± 1.04 / 41.71 ± 0.79 |
45.55 ± 2.18 / 26.78 ± 3.65 |
70.71 ± 1.99 / 71.19 ± 1.14 |
4.83 ± 3.48 / 36.64 ± 2.95 |
55.25 ± 1.21 / 61.21 ± 0.89 |
63.18 ± 0.45 / 17.62 ± 0.51 |
26.05 ± 0.80 / 44.56 ± 0.62 |
27.09 ± 1.66 / 44.95 ± 1.30 |
38.15 ± 2.30 / 28.10 ± 4.65 |
0.98 ± 1.44 / 35.86 ± 1.12 |
20.39 ± 3.04 / 44.20 ± 2.72 |
61.23 ± 2.31 / 14.45 ± 1.79 |
7.59 ± 1.44 / 31.07 ± 1.05 |
3.44 ± 2.28 / 46.89 ± 1.02 |
48.20 ± 1.57 / 39.04 ± 2.38 |
47.12 ± 4.20 / 59.69 ± 4.45 |
12.39 ± 1.39 / 45.13 ± 3.93 |
30.50 ± 3.67 / 57.48 ± 4.51 |
65.48 ± 1.73 / 22.72 ± 3.33 |
30.83 ± 1.40 / 48.12 ± 1.03 |
24.90 ± 1.67 / 43.21 ± 1.49 |
51.18 ± 1.62 / 35.45 ± 1.88 |
9.23 ± 2.84 / 19.38 ± 4.37 |
1.99 ± 2.56 / 34.69 ± 1.59 |
54.66 ± 1.25 / 65.31 ± 1.06 |
60.81 ± 1.16 / 15.41 ± 0.63 |
28.03 ± 1.02 / 45.90 ± 0.79 |
23.64 ± 1.21 / 42.59 ± 0.96 |
55.51 ± 1.48 / 50.61 ± 1.37 |
68.74 ± 0.81 / 58.25 ± 0.31 |
40.81 ± 3.66 / 69.94 ± 1.98 |
72.33 ± 2.68 / 84.50 ± 1.61 |
67.71 ± 0.08 / 23.57 ± 0.14 |
48.36 ± 0.95 / 61.21 ± 0.76 |
68.50 ± 0.63 / 76.04 ± 0.47 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
google/gemma-2-2b-it (few-shot) |
2614 |
256 |
8193 |
False |
6,789 ± 2,167 / 981 ± 327 |
2.97 |
2.71 |
3.05 |
2.84 |
4.08 |
2.67 |
3.07 |
2.40 |
28.34 ± 1.72 / 20.08 ± 1.61 |
47.17 ± 1.42 / 63.35 ± 1.40 |
19.92 ± 2.10 / 58.84 ± 1.15 |
47.94 ± 0.95 / 58.43 ± 0.48 |
66.74 ± 1.00 / 21.93 ± 1.02 |
52.56 ± 1.29 / 63.53 ± 1.07 |
52.88 ± 1.84 / 68.65 ± 1.24 |
30.08 ± 1.38 / 47.13 ± 1.08 |
35.53 ± 1.34 / 28.77 ± 2.22 |
37.56 ± 3.01 / 30.27 ± 2.44 |
46.73 ± 2.20 / 63.18 ± 1.91 |
64.61 ± 0.31 / 16.99 ± 0.45 |
17.03 ± 1.94 / 55.44 ± 2.06 |
14.39 ± 1.77 / 55.01 ± 1.62 |
29.73 ± 1.55 / 63.84 ± 1.50 |
23.03 ± 1.25 / 41.86 ± 1.00 |
33.07 ± 1.04 / 49.42 ± 0.79 |
35.15 ± 2.05 / 25.81 ± 2.54 |
75.93 ± 1.39 / 77.29 ± 1.06 |
15.29 ± 1.77 / 51.23 ± 3.09 |
47.83 ± 0.97 / 58.79 ± 0.78 |
65.23 ± 0.12 / 18.93 ± 0.14 |
26.95 ± 0.83 / 44.91 ± 0.67 |
31.49 ± 1.14 / 48.03 ± 0.86 |
15.18 ± 4.72 / 13.28 ± 3.01 |
0.78 ± 1.20 / 34.61 ± 0.83 |
25.45 ± 1.12 / 51.86 ± 1.32 |
62.85 ± 1.56 / 17.06 ± 1.33 |
10.73 ± 1.48 / 32.33 ± 0.96 |
-5.15 ± 1.58 / 53.06 ± 0.94 |
37.72 ± 2.33 / 31.43 ± 2.08 |
45.86 ± 2.52 / 63.18 ± 1.66 |
23.65 ± 1.37 / 60.93 ± 0.32 |
27.96 ± 1.91 / 59.70 ± 2.05 |
66.41 ± 1.02 / 21.50 ± 2.36 |
30.32 ± 0.99 / 47.64 ± 0.76 |
35.22 ± 0.57 / 50.78 ± 0.52 |
40.49 ± 2.13 / 29.05 ± 1.71 |
11.34 ± 1.45 / 33.08 ± 1.98 |
19.49 ± 2.50 / 52.71 ± 2.64 |
49.35 ± 1.21 / 67.25 ± 0.76 |
66.86 ± 0.85 / 19.21 ± 0.94 |
29.30 ± 1.02 / 46.88 ± 0.79 |
31.33 ± 1.47 / 47.78 ± 1.34 |
44.56 ± 1.47 / 38.77 ± 1.52 |
66.26 ± 1.37 / 67.49 ± 1.29 |
34.36 ± 2.40 / 66.99 ± 1.24 |
55.04 ± 1.78 / 78.93 ± 0.79 |
68.12 ± 0.19 / 23.61 ± 0.31 |
42.95 ± 1.18 / 57.07 ± 0.88 |
45.79 ± 0.69 / 58.61 ± 0.55 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
mistralai/Mistral-7B-Instruct-v0.1 (few-shot) |
7242 |
32 |
32768 |
False |
634 ± 179 / 110 ± 35 |
2.99 |
2.84 |
3.07 |
2.91 |
3.97 |
2.69 |
3.16 |
2.27 |
37.93 ± 2.71 / 23.54 ± 1.99 |
44.49 ± 2.56 / 60.64 ± 3.00 |
14.09 ± 2.94 / 42.43 ± 3.30 |
51.38 ± 2.31 / 58.78 ± 1.27 |
65.80 ± 0.93 / 19.91 ± 1.41 |
45.07 ± 1.34 / 58.18 ± 1.03 |
35.36 ± 2.19 / 55.82 ± 1.48 |
14.85 ± 1.19 / 35.26 ± 1.24 |
50.08 ± 1.54 / 34.52 ± 1.17 |
51.27 ± 1.52 / 33.37 ± 2.37 |
43.65 ± 1.98 / 60.88 ± 1.36 |
62.39 ± 0.76 / 14.24 ± 0.81 |
14.09 ± 2.85 / 44.91 ± 3.95 |
8.28 ± 1.82 / 47.22 ± 3.72 |
37.23 ± 3.15 / 63.67 ± 2.98 |
20.44 ± 1.03 / 39.51 ± 0.72 |
15.87 ± 1.29 / 35.89 ± 1.06 |
45.01 ± 2.11 / 27.59 ± 3.35 |
73.33 ± 1.98 / 76.19 ± 1.59 |
11.59 ± 3.45 / 40.89 ± 4.15 |
52.12 ± 1.42 / 59.29 ± 1.17 |
63.10 ± 0.60 / 18.05 ± 0.36 |
24.03 ± 1.09 / 42.32 ± 0.70 |
15.37 ± 0.71 / 35.78 ± 0.69 |
36.04 ± 2.59 / 24.74 ± 2.79 |
-0.36 ± 1.36 / 33.94 ± 0.32 |
18.06 ± 3.16 / 42.57 ± 2.89 |
62.80 ± 1.69 / 15.23 ± 1.01 |
5.44 ± 1.14 / 28.13 ± 1.06 |
6.35 ± 2.71 / 50.49 ± 1.57 |
47.19 ± 3.74 / 33.02 ± 2.09 |
47.26 ± 3.14 / 63.48 ± 2.94 |
22.32 ± 1.78 / 56.73 ± 4.00 |
24.36 ± 3.78 / 54.61 ± 4.44 |
67.75 ± 1.10 / 25.91 ± 2.95 |
26.79 ± 1.01 / 44.58 ± 0.85 |
20.33 ± 1.63 / 39.63 ± 1.09 |
52.72 ± 2.58 / 33.51 ± 1.22 |
7.91 ± 2.16 / 27.82 ± 1.97 |
18.14 ± 2.10 / 55.42 ± 3.05 |
52.75 ± 0.88 / 67.15 ± 1.08 |
64.77 ± 0.97 / 16.55 ± 0.81 |
26.06 ± 0.77 / 44.08 ± 0.51 |
14.26 ± 1.48 / 35.14 ± 1.18 |
57.58 ± 2.30 / 47.94 ± 2.89 |
61.44 ± 2.02 / 69.47 ± 0.98 |
34.92 ± 2.40 / 66.67 ± 1.41 |
65.38 ± 1.76 / 81.90 ± 0.57 |
69.62 ± 0.31 / 24.65 ± 0.44 |
38.40 ± 0.98 / 53.43 ± 0.76 |
35.72 ± 1.56 / 49.69 ± 1.42 |
9.3.1 |
9.3.1 |
9.3.1 |
12.4.0 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
12.4.0 |
9.3.1 |
9.3.1 |
12.4.0 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
12.4.0 |
12.4.0 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
12.4.0 |
12.4.0 |
12.10.8 |
12.1.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
9.3.1 |
9.3.1 |
9.3.1 |
12.4.0 |
12.4.0 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
12.4.0 |
12.4.0 |
9.3.1 |
9.3.1 |
meta-llama/Llama-3.2-3B (few-shot) |
3213 |
128 |
131073 |
True |
3,713 ± 877 / 836 ± 267 |
3.01 |
2.91 |
3.09 |
2.73 |
3.76 |
2.72 |
3.32 |
2.53 |
41.13 ± 2.85 / 27.15 ± 1.82 |
38.90 ± 1.93 / 44.34 ± 1.64 |
9.60 ± 2.51 / 44.34 ± 5.20 |
56.85 ± 1.27 / 62.25 ± 0.88 |
63.35 ± 0.50 / 15.11 ± 0.93 |
45.46 ± 1.79 / 57.79 ± 1.31 |
46.77 ± 2.98 / 64.61 ± 1.98 |
12.19 ± 0.97 / 33.27 ± 0.89 |
49.57 ± 2.20 / 37.13 ± 2.52 |
52.13 ± 3.94 / 38.26 ± 3.77 |
39.96 ± 2.25 / 58.34 ± 1.66 |
58.99 ± 1.85 / 11.04 ± 1.25 |
3.20 ± 3.84 / 37.62 ± 4.94 |
3.72 ± 3.66 / 38.51 ± 4.61 |
45.54 ± 3.50 / 68.67 ± 2.58 |
21.88 ± 1.21 / 40.31 ± 1.01 |
14.24 ± 1.99 / 33.82 ± 1.72 |
51.06 ± 2.85 / 31.63 ± 3.67 |
77.76 ± 1.09 / 67.88 ± 3.15 |
5.88 ± 3.89 / 38.51 ± 4.84 |
57.43 ± 1.04 / 62.93 ± 0.94 |
62.73 ± 0.74 / 17.61 ± 0.49 |
27.05 ± 1.14 / 44.68 ± 0.87 |
13.30 ± 1.20 / 33.89 ± 1.04 |
42.04 ± 3.53 / 25.31 ± 1.59 |
0.00 ± 0.00 / 32.97 ± 0.29 |
24.07 ± 4.63 / 49.31 ± 4.59 |
61.80 ± 2.80 / 14.50 ± 2.00 |
13.79 ± 1.55 / 35.23 ± 1.26 |
0.25 ± 2.45 / 48.10 ± 1.67 |
49.85 ± 1.96 / 41.04 ± 2.44 |
54.65 ± 1.58 / 65.94 ± 2.42 |
3.17 ± 5.20 / 36.54 ± 5.71 |
29.37 ± 3.48 / 58.09 ± 4.16 |
67.96 ± 1.38 / 25.30 ± 2.54 |
29.56 ± 0.63 / 46.21 ± 0.55 |
16.15 ± 1.34 / 35.40 ± 1.27 |
47.40 ± 3.29 / 33.11 ± 2.04 |
7.90 ± 1.98 / 30.71 ± 1.89 |
3.10 ± 1.93 / 34.24 ± 0.73 |
56.53 ± 1.48 / 68.47 ± 1.35 |
62.27 ± 2.04 / 16.54 ± 1.58 |
29.18 ± 0.87 / 46.04 ± 0.54 |
10.34 ± 1.08 / 32.08 ± 1.06 |
59.09 ± 1.44 / 52.03 ± 1.96 |
63.29 ± 1.29 / 67.82 ± 0.74 |
13.50 ± 4.14 / 50.33 ± 5.61 |
68.15 ± 2.21 / 81.12 ± 1.18 |
67.73 ± 0.51 / 22.02 ± 0.74 |
40.10 ± 0.68 / 54.53 ± 0.48 |
20.88 ± 2.25 / 39.75 ± 1.62 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
microsoft/Phi-3-mini-128k-instruct (few-shot) |
3821 |
32 |
131072 |
True |
7,312 ± 1,668 / 1,609 ± 525 |
3.02 |
3.30 |
3.25 |
3.22 |
4.07 |
2.17 |
3.08 |
2.07 |
4.51 ± 2.12 / 3.71 ± 1.76 |
40.85 ± 1.26 / 59.79 ± 1.32 |
5.43 ± 1.74 / 46.21 ± 4.13 |
51.76 ± 0.73 / 58.44 ± 0.54 |
64.64 ± 0.66 / 19.18 ± 0.74 |
37.45 ± 1.45 / 52.86 ± 1.15 |
36.39 ± 2.23 / 56.50 ± 1.51 |
17.42 ± 0.78 / 38.06 ± 0.55 |
52.18 ± 2.03 / 29.83 ± 3.23 |
50.53 ± 1.49 / 31.94 ± 4.20 |
33.30 ± 2.01 / 51.15 ± 2.93 |
60.69 ± 0.97 / 12.72 ± 0.74 |
2.63 ± 2.56 / 40.21 ± 3.98 |
4.00 ± 1.87 / 44.87 ± 3.17 |
37.08 ± 2.44 / 61.14 ± 2.01 |
17.34 ± 0.74 / 38.04 ± 0.55 |
17.43 ± 1.21 / 38.01 ± 0.91 |
42.36 ± 1.67 / 21.33 ± 2.90 |
51.53 ± 6.32 / 62.14 ± 3.43 |
3.11 ± 1.60 / 47.93 ± 2.93 |
51.11 ± 0.96 / 57.21 ± 0.95 |
59.28 ± 0.86 / 15.52 ± 0.64 |
22.99 ± 1.08 / 42.27 ± 0.81 |
20.19 ± 0.99 / 40.11 ± 0.71 |
27.22 ± 3.65 / 24.21 ± 2.67 |
1.31 ± 1.28 / 39.67 ± 4.39 |
17.24 ± 2.72 / 41.15 ± 1.57 |
62.00 ± 1.66 / 15.80 ± 1.12 |
1.85 ± 1.18 / 26.88 ± 0.86 |
1.06 ± 2.84 / 47.19 ± 2.14 |
55.36 ± 0.81 / 36.14 ± 1.96 |
53.05 ± 2.34 / 65.57 ± 1.92 |
23.08 ± 1.54 / 58.65 ± 2.04 |
31.55 ± 1.09 / 62.02 ± 2.17 |
67.33 ± 0.98 / 24.07 ± 2.44 |
39.57 ± 0.74 / 54.67 ± 0.56 |
51.26 ± 0.93 / 63.03 ± 0.69 |
44.27 ± 2.14 / 34.47 ± 2.48 |
12.84 ± 1.82 / 36.64 ± 1.13 |
10.44 ± 1.58 / 48.93 ± 3.41 |
56.40 ± 1.14 / 68.02 ± 0.79 |
62.60 ± 0.62 / 15.63 ± 0.45 |
28.63 ± 0.84 / 46.39 ± 0.61 |
22.58 ± 0.97 / 41.78 ± 0.71 |
64.09 ± 0.96 / 49.92 ± 2.47 |
46.77 ± 4.36 / 60.99 ± 2.15 |
31.62 ± 2.25 / 63.73 ± 1.79 |
71.25 ± 0.83 / 85.72 ± 0.57 |
69.54 ± 0.57 / 24.79 ± 0.89 |
57.66 ± 1.17 / 68.22 ± 0.88 |
72.26 ± 0.86 / 79.10 ± 0.64 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.10.0 |
12.10.0 |
12.10.0 |
12.9.1 |
12.9.1 |
12.9.1 |
12.10.0 |
12.9.1 |
12.9.1 |
12.9.1 |
12.10.0 |
12.10.0 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.10.0 |
12.10.0 |
12.10.0 |
12.9.1 |
12.9.1 |
12.9.1 |
12.10.0 |
12.10.8 |
12.10.0 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.10.0 |
12.10.0 |
12.10.0 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.10.0 |
12.10.0 |
12.10.0 |
12.9.1 |
12.9.1 |
12.9.1 |
12.9.1 |
12.10.0 |
12.10.0 |
12.10.0 |
ibm-granite/granite-8b-code-base-4k (few-shot) |
8055 |
49 |
4096 |
True |
2,313 ± 423 / 682 ± 210 |
3.05 |
3.05 |
3.13 |
2.98 |
3.96 |
2.72 |
3.04 |
2.46 |
48.44 ± 1.69 / 36.99 ± 1.77 |
39.07 ± 1.03 / 56.85 ± 1.91 |
9.72 ± 1.58 / 46.85 ± 3.66 |
51.18 ± 0.92 / 56.54 ± 0.69 |
63.93 ± 0.79 / 17.49 ± 0.73 |
33.11 ± 2.59 / 49.31 ± 2.03 |
18.96 ± 2.16 / 46.29 ± 1.39 |
9.03 ± 1.28 / 31.42 ± 1.04 |
68.40 ± 1.16 / 62.53 ± 1.69 |
65.15 ± 0.79 / 60.39 ± 2.11 |
42.00 ± 1.78 / 59.90 ± 1.22 |
61.27 ± 0.80 / 13.34 ± 0.66 |
5.20 ± 2.23 / 36.33 ± 1.30 |
3.32 ± 2.02 / 37.81 ± 3.26 |
37.51 ± 2.58 / 60.94 ± 3.06 |
12.42 ± 1.42 / 34.82 ± 0.98 |
8.32 ± 0.78 / 30.87 ± 0.75 |
59.77 ± 3.55 / 45.71 ± 4.91 |
74.45 ± 1.19 / 72.26 ± 0.89 |
3.97 ± 1.50 / 34.79 ± 0.80 |
50.18 ± 1.05 / 56.07 ± 0.89 |
62.61 ± 0.55 / 17.92 ± 0.33 |
14.34 ± 0.73 / 35.93 ± 0.55 |
7.40 ± 1.39 / 30.20 ± 1.23 |
50.89 ± 2.90 / 35.75 ± 4.67 |
0.50 ± 0.94 / 33.77 ± 0.30 |
17.43 ± 3.38 / 41.32 ± 3.18 |
59.94 ± 2.87 / 12.62 ± 1.91 |
5.52 ± 1.26 / 28.97 ± 0.97 |
1.73 ± 2.31 / 50.89 ± 3.35 |
59.07 ± 0.78 / 51.00 ± 2.06 |
49.75 ± 2.44 / 65.93 ± 1.66 |
14.71 ± 2.21 / 53.75 ± 3.07 |
29.45 ± 2.13 / 56.14 ± 2.53 |
67.78 ± 1.54 / 26.66 ± 3.40 |
16.39 ± 1.29 / 37.35 ± 0.95 |
10.68 ± 1.41 / 32.52 ± 1.35 |
63.29 ± 2.51 / 52.18 ± 4.31 |
13.81 ± 1.66 / 36.99 ± 2.58 |
8.16 ± 1.97 / 44.29 ± 4.25 |
56.64 ± 0.68 / 66.29 ± 0.71 |
63.08 ± 0.90 / 15.69 ± 0.65 |
16.86 ± 1.16 / 37.54 ± 0.93 |
6.24 ± 0.78 / 29.25 ± 0.61 |
72.76 ± 0.57 / 67.49 ± 0.90 |
62.35 ± 1.68 / 67.34 ± 0.77 |
21.57 ± 2.22 / 59.22 ± 1.69 |
69.80 ± 3.60 / 81.37 ± 2.26 |
67.73 ± 0.60 / 23.48 ± 0.91 |
25.63 ± 0.81 / 44.26 ± 0.63 |
16.44 ± 1.84 / 36.73 ± 1.54 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
meta-llama/Llama-2-7b-chat-hf (few-shot) |
6738 |
32 |
4096 |
False |
2,643 ± 455 / 800 ± 247 |
3.09 |
2.89 |
3.24 |
3.02 |
3.99 |
2.89 |
3.13 |
2.45 |
35.44 ± 3.00 / 24.63 ± 1.65 |
44.88 ± 1.45 / 62.35 ± 1.33 |
9.74 ± 1.96 / 47.42 ± 4.19 |
55.04 ± 0.79 / 61.34 ± 0.81 |
66.15 ± 0.67 / 19.69 ± 0.94 |
32.17 ± 2.28 / 46.67 ± 1.92 |
35.74 ± 2.46 / 55.18 ± 1.81 |
11.32 ± 0.41 / 32.24 ± 0.79 |
44.99 ± 2.49 / 38.59 ± 2.84 |
49.09 ± 1.90 / 39.09 ± 4.02 |
41.56 ± 3.37 / 57.09 ± 3.80 |
63.59 ± 0.40 / 14.15 ± 0.70 |
3.04 ± 2.84 / 36.81 ± 2.42 |
4.03 ± 2.49 / 40.55 ± 4.14 |
33.77 ± 2.11 / 61.99 ± 2.34 |
14.81 ± 0.79 / 34.79 ± 0.63 |
12.69 ± 0.77 / 31.84 ± 1.05 |
39.72 ± 2.82 / 29.85 ± 2.99 |
66.18 ± 3.25 / 72.00 ± 1.75 |
6.74 ± 1.66 / 45.55 ± 4.31 |
54.05 ± 0.84 / 60.90 ± 0.82 |
65.92 ± 0.05 / 18.51 ± 0.18 |
17.73 ± 0.98 / 37.55 ± 0.69 |
12.85 ± 0.93 / 33.37 ± 0.90 |
41.10 ± 3.35 / 40.54 ± 3.19 |
-1.07 ± 2.09 / 44.83 ± 2.20 |
16.13 ± 2.52 / 39.51 ± 1.98 |
62.30 ± 0.90 / 13.28 ± 1.36 |
3.16 ± 0.79 / 27.40 ± 0.79 |
1.84 ± 2.19 / 43.79 ± 0.73 |
50.09 ± 1.33 / 38.59 ± 1.66 |
46.52 ± 2.85 / 63.64 ± 2.10 |
15.23 ± 1.71 / 55.08 ± 1.88 |
25.54 ± 3.58 / 56.07 ± 3.76 |
67.62 ± 0.89 / 23.52 ± 2.43 |
20.12 ± 1.13 / 39.48 ± 1.02 |
13.98 ± 1.56 / 34.07 ± 1.30 |
50.23 ± 2.34 / 37.12 ± 3.30 |
10.07 ± 1.84 / 35.66 ± 2.24 |
14.73 ± 1.62 / 54.59 ± 2.24 |
53.42 ± 0.80 / 66.24 ± 0.84 |
67.59 ± 0.56 / 18.45 ± 0.65 |
20.19 ± 1.26 / 39.24 ± 1.03 |
11.42 ± 1.29 / 32.50 ± 1.10 |
62.53 ± 1.35 / 53.42 ± 2.04 |
62.23 ± 1.29 / 68.09 ± 1.34 |
22.71 ± 1.81 / 60.79 ± 1.08 |
64.45 ± 1.39 / 80.79 ± 0.79 |
69.95 ± 0.32 / 25.22 ± 0.33 |
30.47 ± 0.70 / 46.82 ± 0.55 |
30.18 ± 1.87 / 45.85 ± 1.98 |
9.3.1 |
9.3.1 |
9.3.1 |
12.4.0 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
12.4.0 |
9.3.1 |
9.3.1 |
12.4.0 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
12.4.0 |
12.4.0 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
12.4.0 |
12.4.0 |
12.10.8 |
12.1.0 |
12.9.0 |
12.9.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
9.3.1 |
9.3.1 |
9.3.1 |
12.4.0 |
12.4.0 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
12.4.0 |
12.4.0 |
9.3.1 |
9.3.1 |
google/gemma-7b-it (few-shot) |
8538 |
256 |
8192 |
False |
1,792 ± 249 / 668 ± 203 |
3.11 |
3.03 |
2.99 |
3.24 |
3.98 |
3.13 |
3.07 |
2.35 |
43.83 ± 1.93 / 34.03 ± 1.59 |
29.21 ± 1.92 / 52.86 ± 1.54 |
12.96 ± 1.67 / 55.83 ± 0.88 |
49.76 ± 0.59 / 56.52 ± 0.50 |
65.36 ± 1.08 / 19.65 ± 1.01 |
41.30 ± 1.79 / 54.09 ± 1.68 |
31.26 ± 2.75 / 52.68 ± 2.10 |
15.02 ± 1.01 / 34.38 ± 0.79 |
59.77 ± 2.77 / 56.12 ± 2.72 |
60.98 ± 2.01 / 57.99 ± 1.31 |
28.14 ± 1.90 / 49.76 ± 1.59 |
60.86 ± 1.60 / 13.66 ± 0.51 |
14.01 ± 2.15 / 56.43 ± 1.08 |
10.15 ± 1.06 / 54.56 ± 0.71 |
51.08 ± 2.83 / 74.34 ± 1.55 |
19.07 ± 1.42 / 37.82 ± 1.42 |
16.52 ± 1.25 / 35.24 ± 1.25 |
59.26 ± 2.00 / 52.73 ± 2.71 |
28.63 ± 1.24 / 50.95 ± 0.75 |
11.43 ± 1.88 / 53.31 ± 1.74 |
46.67 ± 1.97 / 53.24 ± 1.72 |
63.88 ± 0.30 / 18.58 ± 0.16 |
17.95 ± 1.18 / 36.41 ± 1.02 |
13.55 ± 1.32 / 33.39 ± 1.32 |
37.69 ± 3.97 / 34.52 ± 3.74 |
3.11 ± 1.49 / 48.48 ± 2.77 |
18.34 ± 2.07 / 43.26 ± 1.28 |
63.71 ± 1.04 / 16.63 ± 0.98 |
7.70 ± 1.44 / 28.98 ± 1.20 |
-5.17 ± 2.94 / 53.84 ± 1.87 |
54.20 ± 1.00 / 48.58 ± 1.53 |
15.43 ± 3.70 / 43.11 ± 2.77 |
17.49 ± 1.23 / 57.46 ± 1.12 |
28.68 ± 5.36 / 60.07 ± 4.46 |
64.87 ± 0.47 / 22.25 ± 1.89 |
22.10 ± 0.68 / 40.39 ± 0.63 |
18.58 ± 1.48 / 36.49 ± 1.24 |
53.93 ± 2.71 / 47.48 ± 2.09 |
12.83 ± 2.37 / 34.00 ± 2.26 |
6.58 ± 3.36 / 48.51 ± 3.35 |
53.45 ± 2.52 / 67.47 ± 0.88 |
65.89 ± 0.38 / 17.99 ± 0.46 |
19.58 ± 1.24 / 38.76 ± 1.06 |
13.68 ± 1.08 / 32.30 ± 0.99 |
66.70 ± 0.99 / 61.08 ± 1.16 |
55.62 ± 2.54 / 64.98 ± 2.03 |
31.36 ± 2.63 / 65.21 ± 1.16 |
72.58 ± 0.68 / 84.67 ± 0.91 |
67.24 ± 0.71 / 21.99 ± 0.99 |
35.27 ± 1.22 / 50.12 ± 0.94 |
32.54 ± 1.77 / 46.58 ± 1.66 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.8 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
Qwen/Qwen1.5-4B-Chat (few-shot) |
3950 |
152 |
32768 |
False |
4,347 ± 893 / 1,135 ± 365 |
3.12 |
2.96 |
3.27 |
3.07 |
4.18 |
2.92 |
3.13 |
2.32 |
35.96 ± 2.61 / 28.58 ± 2.58 |
42.04 ± 1.42 / 60.76 ± 1.41 |
8.65 ± 1.52 / 49.56 ± 3.60 |
53.68 ± 0.94 / 59.73 ± 0.86 |
63.22 ± 1.14 / 16.73 ± 1.50 |
37.79 ± 1.24 / 52.64 ± 0.99 |
29.62 ± 1.33 / 52.29 ± 1.02 |
16.87 ± 1.18 / 37.41 ± 0.90 |
44.83 ± 1.58 / 40.11 ± 2.00 |
46.29 ± 1.65 / 41.63 ± 3.45 |
32.70 ± 1.59 / 45.73 ± 2.82 |
60.53 ± 1.97 / 12.86 ± 1.03 |
3.57 ± 1.55 / 37.05 ± 2.34 |
1.61 ± 2.11 / 37.85 ± 3.99 |
42.55 ± 3.36 / 67.11 ± 2.50 |
17.00 ± 1.21 / 37.67 ± 0.96 |
16.18 ± 1.00 / 36.91 ± 0.64 |
40.19 ± 2.97 / 31.88 ± 4.51 |
64.08 ± 2.44 / 69.62 ± 1.29 |
5.43 ± 2.02 / 38.32 ± 2.54 |
53.21 ± 1.08 / 59.57 ± 0.97 |
61.90 ± 0.87 / 17.34 ± 0.52 |
20.95 ± 0.97 / 40.87 ± 0.76 |
16.59 ± 1.45 / 36.76 ± 1.20 |
25.65 ± 2.99 / 22.30 ± 2.30 |
-0.35 ± 2.01 / 44.36 ± 4.13 |
14.46 ± 2.66 / 32.31 ± 1.66 |
62.11 ± 2.22 / 14.98 ± 1.53 |
4.50 ± 1.47 / 28.86 ± 1.09 |
-1.89 ± 2.66 / 43.72 ± 0.92 |
42.08 ± 1.65 / 36.90 ± 2.00 |
41.52 ± 3.53 / 57.69 ± 3.35 |
12.78 ± 3.75 / 46.43 ± 5.48 |
29.35 ± 2.51 / 59.90 ± 2.80 |
65.56 ± 1.65 / 20.45 ± 2.68 |
23.76 ± 0.70 / 42.77 ± 0.56 |
20.92 ± 1.16 / 40.56 ± 0.86 |
42.52 ± 2.25 / 37.46 ± 3.08 |
14.68 ± 1.40 / 40.53 ± 1.64 |
4.07 ± 2.16 / 35.24 ± 1.77 |
55.18 ± 0.74 / 66.50 ± 0.80 |
62.75 ± 0.84 / 14.83 ± 0.70 |
24.25 ± 1.22 / 43.08 ± 0.87 |
16.21 ± 1.51 / 37.11 ± 1.16 |
58.56 ± 1.99 / 54.14 ± 2.01 |
59.62 ± 1.29 / 68.55 ± 0.56 |
28.55 ± 3.97 / 60.49 ± 4.25 |
70.04 ± 0.89 / 82.09 ± 0.84 |
67.27 ± 0.39 / 19.77 ± 0.31 |
38.68 ± 1.02 / 53.45 ± 0.74 |
47.47 ± 1.28 / 60.44 ± 1.02 |
12.5.2 |
10.0.1 |
12.1.0 |
12.5.2 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.5.2 |
10.0.1 |
12.1.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.1.0 |
12.5.2 |
12.1.0 |
12.10.8 |
12.1.0 |
12.5.2 |
10.0.1 |
12.1.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
10.0.1 |
12.1.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
10.0.1 |
12.1.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
meta-llama/Llama-2-7b-hf (few-shot) |
6738 |
32 |
4096 |
True |
930 ± 310 / 128 ± 43 |
3.14 |
3.01 |
3.23 |
2.88 |
4.08 |
2.84 |
3.35 |
2.60 |
31.77 ± 3.29 / 22.31 ± 2.29 |
43.91 ± 1.94 / 61.54 ± 2.33 |
0.31 ± 0.61 / 33.43 ± 0.23 |
58.44 ± 0.83 / 63.54 ± 0.66 |
65.50 ± 0.82 / 19.96 ± 0.95 |
20.18 ± 1.80 / 38.69 ± 1.57 |
35.69 ± 2.31 / 57.05 ± 1.60 |
7.93 ± 1.49 / 29.76 ± 0.92 |
42.13 ± 3.82 / 37.17 ± 3.44 |
43.80 ± 2.85 / 37.48 ± 4.00 |
41.74 ± 2.25 / 57.91 ± 2.82 |
62.30 ± 1.81 / 14.85 ± 1.88 |
0.00 ± 0.00 / 33.41 ± 0.30 |
0.02 ± 0.04 / 33.88 ± 0.35 |
44.19 ± 4.13 / 66.18 ± 4.05 |
14.48 ± 1.33 / 35.35 ± 0.94 |
6.49 ± 1.39 / 28.64 ± 0.96 |
44.11 ± 4.26 / 31.64 ± 4.48 |
79.05 ± 1.08 / 75.52 ± 2.66 |
7.34 ± 3.19 / 43.83 ± 5.31 |
57.49 ± 0.95 / 63.16 ± 0.77 |
64.63 ± 0.39 / 18.68 ± 0.39 |
15.65 ± 0.55 / 36.32 ± 0.55 |
8.74 ± 1.34 / 29.87 ± 1.40 |
32.71 ± 2.77 / 32.17 ± 2.13 |
0.66 ± 1.75 / 40.36 ± 4.19 |
18.04 ± 4.05 / 41.40 ± 3.27 |
60.73 ± 3.02 / 14.02 ± 1.57 |
3.65 ± 1.33 / 26.91 ± 1.00 |
-0.00 ± 2.41 / 44.93 ± 0.92 |
43.02 ± 1.93 / 32.69 ± 1.98 |
50.21 ± 2.43 / 65.81 ± 1.82 |
15.79 ± 2.35 / 53.25 ± 4.45 |
28.57 ± 5.09 / 55.54 ± 6.14 |
68.68 ± 0.96 / 26.95 ± 1.81 |
18.38 ± 1.36 / 38.12 ± 1.19 |
8.45 ± 1.86 / 30.07 ± 1.49 |
40.49 ± 4.32 / 30.86 ± 2.27 |
7.10 ± 1.85 / 27.42 ± 1.76 |
18.66 ± 2.39 / 55.25 ± 3.77 |
59.92 ± 0.61 / 70.24 ± 0.75 |
62.58 ± 1.13 / 16.33 ± 0.81 |
17.36 ± 1.12 / 37.44 ± 0.99 |
6.68 ± 1.82 / 29.30 ± 1.02 |
55.27 ± 2.79 / 50.25 ± 2.12 |
65.16 ± 1.21 / 66.86 ± 1.32 |
20.43 ± 3.69 / 55.98 ± 4.88 |
69.82 ± 2.49 / 81.43 ± 1.73 |
68.82 ± 0.54 / 23.58 ± 0.59 |
25.98 ± 0.90 / 42.52 ± 0.62 |
11.77 ± 1.81 / 31.25 ± 1.99 |
9.2.0 |
9.2.0 |
9.2.0 |
12.5.1 |
12.6.1 |
10.0.1 |
10.0.1 |
9.2.0 |
9.2.0 |
9.2.0 |
9.2.0 |
11.0.0 |
9.2.0 |
9.2.0 |
12.5.1 |
9.2.0 |
9.2.0 |
9.2.0 |
9.2.0 |
9.2.0 |
12.5.1 |
12.0.0 |
9.2.0 |
9.2.0 |
9.2.0 |
9.2.0 |
12.5.1 |
11.0.0 |
12.10.8 |
12.1.0 |
12.8.0 |
12.8.0 |
12.8.0 |
12.8.0 |
12.9.0 |
12.9.0 |
12.9.0 |
9.2.0 |
9.2.0 |
9.2.0 |
12.5.1 |
11.0.0 |
9.2.0 |
9.2.0 |
9.2.0 |
9.2.0 |
9.2.0 |
12.5.1 |
12.0.0 |
9.2.0 |
9.2.0 |
01-ai/Yi-6B (few-shot) |
6061 |
64 |
4096 |
True |
6,435 ± 1,316 / 1,632 ± 549 |
3.20 |
3.40 |
3.16 |
2.87 |
4.36 |
3.09 |
3.39 |
2.11 |
35.08 ± 2.24 / 25.02 ± 2.03 |
4.00 ± 2.43 / 18.67 ± 0.94 |
3.68 ± 2.25 / 35.69 ± 1.87 |
55.09 ± 0.79 / 60.88 ± 0.55 |
64.15 ± 1.03 / 18.95 ± 0.93 |
34.07 ± 2.13 / 50.17 ± 1.60 |
33.75 ± 2.28 / 54.22 ± 1.75 |
13.61 ± 1.51 / 34.38 ± 1.20 |
43.44 ± 1.89 / 33.41 ± 2.21 |
46.33 ± 3.12 / 34.05 ± 2.27 |
38.96 ± 2.34 / 56.27 ± 3.65 |
61.98 ± 1.45 / 14.38 ± 1.20 |
0.75 ± 1.07 / 33.42 ± 0.29 |
1.04 ± 1.93 / 33.14 ± 0.66 |
40.28 ± 3.58 / 62.78 ± 3.34 |
23.14 ± 0.98 / 41.88 ± 0.80 |
16.50 ± 1.60 / 36.98 ± 1.27 |
46.69 ± 2.39 / 32.97 ± 4.57 |
75.39 ± 1.06 / 71.95 ± 1.42 |
2.91 ± 2.80 / 35.26 ± 2.12 |
54.95 ± 0.86 / 60.77 ± 0.75 |
62.70 ± 0.76 / 17.52 ± 0.40 |
25.28 ± 0.72 / 43.71 ± 0.56 |
19.20 ± 1.18 / 38.76 ± 0.96 |
0.00 ± 0.00 / 0.00 ± 0.00 |
2.12 ± 1.40 / 38.45 ± 2.47 |
16.91 ± 2.57 / 40.63 ± 2.83 |
60.02 ± 3.15 / 14.22 ± 1.52 |
4.35 ± 1.25 / 28.94 ± 1.09 |
0.72 ± 2.33 / 52.54 ± 2.18 |
0.00 ± 0.00 / 0.00 ± 0.00 |
52.66 ± 2.45 / 67.63 ± 1.87 |
7.33 ± 2.53 / 37.69 ± 2.51 |
30.05 ± 1.59 / 57.13 ± 2.48 |
66.09 ± 1.28 / 23.20 ± 2.54 |
30.33 ± 0.78 / 47.68 ± 0.54 |
22.89 ± 1.14 / 41.15 ± 1.08 |
46.34 ± 2.00 / 33.30 ± 1.78 |
8.96 ± 1.44 / 18.10 ± 2.39 |
0.88 ± 1.23 / 33.53 ± 0.48 |
55.33 ± 1.28 / 66.50 ± 0.94 |
58.35 ± 1.57 / 14.29 ± 0.85 |
29.33 ± 0.91 / 46.94 ± 0.68 |
20.27 ± 1.38 / 39.32 ± 1.12 |
52.70 ± 2.29 / 48.83 ± 2.24 |
68.66 ± 0.92 / 58.34 ± 0.37 |
25.29 ± 4.29 / 54.31 ± 5.45 |
75.89 ± 1.84 / 85.86 ± 1.03 |
64.51 ± 0.30 / 18.84 ± 0.32 |
50.89 ± 0.77 / 63.01 ± 0.60 |
68.29 ± 0.74 / 75.90 ± 0.62 |
9.3.2 |
10.0.0 |
10.0.0 |
12.5.1 |
12.6.1 |
10.0.1 |
10.0.1 |
10.0.1 |
9.3.2 |
9.3.2 |
10.0.0 |
12.0.0 |
10.0.0 |
10.0.0 |
12.5.1 |
10.0.1 |
10.0.1 |
9.3.2 |
10.0.0 |
10.0.0 |
12.5.1 |
12.0.0 |
10.0.1 |
10.0.1 |
9.3.2 |
10.0.0 |
12.5.1 |
12.0.0 |
12.10.8 |
12.1.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
9.3.2 |
10.0.0 |
10.0.0 |
12.5.1 |
12.0.0 |
10.0.1 |
10.0.1 |
9.3.2 |
10.0.0 |
10.0.0 |
12.5.1 |
12.0.0 |
10.0.1 |
10.0.1 |
allenai/OLMo-1.7-7B-hf (few-shot) |
6888 |
50 |
4096 |
True |
3,371 ± 876 / 561 ± 184 |
3.29 |
3.24 |
3.40 |
3.01 |
4.14 |
2.95 |
3.64 |
2.62 |
33.80 ± 2.66 / 25.32 ± 3.06 |
31.57 ± 2.65 / 46.48 ± 3.84 |
2.76 ± 1.76 / 44.96 ± 3.93 |
54.20 ± 1.63 / 59.50 ± 1.54 |
64.19 ± 1.01 / 17.67 ± 1.44 |
17.75 ± 1.41 / 35.70 ± 1.27 |
28.24 ± 2.88 / 52.50 ± 1.77 |
4.50 ± 0.85 / 27.33 ± 0.64 |
42.78 ± 1.09 / 37.34 ± 1.81 |
42.85 ± 1.93 / 37.34 ± 3.04 |
36.68 ± 2.11 / 46.78 ± 2.71 |
59.58 ± 1.88 / 12.71 ± 1.18 |
2.39 ± 1.54 / 43.99 ± 3.66 |
1.91 ± 1.37 / 44.20 ± 4.28 |
39.16 ± 2.56 / 62.28 ± 2.34 |
13.41 ± 0.92 / 33.01 ± 0.94 |
7.83 ± 1.64 / 29.50 ± 1.51 |
41.25 ± 2.07 / 32.87 ± 2.49 |
76.60 ± 0.98 / 64.63 ± 2.41 |
6.37 ± 2.08 / 49.55 ± 3.34 |
54.87 ± 0.64 / 61.35 ± 0.68 |
62.90 ± 0.52 / 17.15 ± 0.51 |
16.18 ± 0.78 / 34.88 ± 0.66 |
8.52 ± 1.90 / 29.96 ± 1.75 |
27.44 ± 3.28 / 23.50 ± 3.29 |
1.46 ± 1.18 / 41.20 ± 3.25 |
17.26 ± 3.80 / 39.06 ± 3.00 |
58.30 ± 4.50 / 14.03 ± 2.00 |
2.14 ± 1.25 / 25.83 ± 1.11 |
2.43 ± 2.93 / 55.15 ± 1.40 |
39.41 ± 2.30 / 36.17 ± 2.32 |
49.42 ± 4.33 / 61.57 ± 5.43 |
6.02 ± 2.53 / 46.41 ± 4.35 |
27.69 ± 4.39 / 54.92 ± 5.38 |
66.75 ± 0.68 / 23.16 ± 0.88 |
20.77 ± 0.92 / 39.29 ± 0.91 |
10.47 ± 1.51 / 31.09 ± 1.36 |
46.95 ± 2.32 / 36.13 ± 1.88 |
4.34 ± 2.10 / 19.37 ± 2.08 |
3.46 ± 1.91 / 41.32 ± 3.08 |
57.07 ± 0.89 / 68.14 ± 0.65 |
61.31 ± 0.64 / 17.24 ± 0.72 |
18.21 ± 0.70 / 37.51 ± 0.63 |
9.03 ± 1.04 / 29.35 ± 0.77 |
41.02 ± 3.86 / 40.03 ± 2.56 |
66.43 ± 0.78 / 57.25 ± 0.33 |
5.17 ± 1.55 / 37.03 ± 2.40 |
76.04 ± 0.97 / 85.31 ± 0.82 |
70.28 ± 0.06 / 28.85 ± 0.17 |
34.92 ± 0.75 / 50.82 ± 0.73 |
18.73 ± 1.32 / 34.76 ± 0.91 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.8 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.4 |
12.10.4 |
Qwen/Qwen1.5-4B (few-shot) |
3950 |
152 |
32768 |
True |
3,248 ± 739 / 761 ± 252 |
3.34 |
3.07 |
3.40 |
3.65 |
4.43 |
3.12 |
3.47 |
2.23 |
32.28 ± 3.16 / 23.24 ± 3.51 |
39.62 ± 2.39 / 56.09 ± 2.89 |
5.38 ± 2.18 / 36.31 ± 1.96 |
54.16 ± 0.89 / 60.63 ± 0.75 |
62.74 ± 1.62 / 16.48 ± 1.77 |
37.49 ± 1.84 / 51.62 ± 1.43 |
29.21 ± 3.46 / 52.40 ± 2.50 |
15.58 ± 1.48 / 36.33 ± 1.08 |
32.12 ± 5.17 / 32.01 ± 2.80 |
36.86 ± 3.53 / 35.46 ± 3.07 |
36.97 ± 1.94 / 55.08 ± 2.30 |
57.64 ± 2.16 / 11.53 ± 1.29 |
5.27 ± 3.31 / 40.91 ± 5.24 |
1.40 ± 1.87 / 33.64 ± 0.74 |
40.00 ± 2.26 / 62.87 ± 1.60 |
16.50 ± 1.40 / 36.63 ± 1.17 |
13.27 ± 2.02 / 34.42 ± 1.54 |
37.26 ± 4.28 / 29.89 ± 5.96 |
5.20 ± 7.35 / 30.65 ± 4.97 |
1.85 ± 1.54 / 33.71 ± 0.46 |
54.15 ± 0.58 / 60.15 ± 0.59 |
58.24 ± 1.76 / 16.02 ± 0.88 |
22.04 ± 0.60 / 41.36 ± 0.54 |
14.76 ± 1.28 / 35.27 ± 1.32 |
15.66 ± 5.89 / 15.78 ± 3.95 |
-0.55 ± 1.06 / 39.57 ± 3.61 |
14.11 ± 3.08 / 34.56 ± 2.38 |
57.17 ± 3.07 / 11.73 ± 1.00 |
5.46 ± 1.45 / 29.23 ± 1.11 |
-1.71 ± 3.79 / 50.88 ± 1.29 |
31.52 ± 2.96 / 29.20 ± 1.88 |
39.91 ± 3.29 / 53.66 ± 3.20 |
3.27 ± 2.51 / 34.30 ± 1.29 |
27.55 ± 3.12 / 57.60 ± 3.34 |
65.88 ± 1.25 / 21.37 ± 1.87 |
21.32 ± 1.14 / 40.66 ± 0.96 |
21.35 ± 0.89 / 40.77 ± 0.65 |
35.74 ± 3.22 / 31.74 ± 2.24 |
12.55 ± 1.39 / 39.80 ± 1.38 |
0.23 ± 0.44 / 33.35 ± 0.31 |
51.30 ± 1.63 / 64.17 ± 0.87 |
58.90 ± 1.59 / 14.17 ± 0.80 |
22.20 ± 1.53 / 41.49 ± 1.08 |
13.11 ± 1.85 / 33.86 ± 1.69 |
55.45 ± 1.61 / 49.72 ± 1.27 |
60.55 ± 1.54 / 68.53 ± 0.71 |
28.60 ± 3.36 / 60.31 ± 4.06 |
70.49 ± 0.74 / 82.68 ± 0.52 |
68.67 ± 0.11 / 21.65 ± 0.21 |
39.82 ± 0.76 / 54.62 ± 0.57 |
51.82 ± 1.03 / 63.79 ± 0.79 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
9.3.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.10.8 |
12.1.0 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
google/gemma-2-2b (few-shot) |
2614 |
256 |
8193 |
True |
5,235 ± 1,226 / 1,154 ± 366 |
3.35 |
3.15 |
3.49 |
3.08 |
4.21 |
3.03 |
3.62 |
2.89 |
17.29 ± 2.84 / 13.87 ± 2.03 |
34.94 ± 2.71 / 42.58 ± 3.24 |
6.39 ± 2.41 / 45.03 ± 4.32 |
54.94 ± 1.00 / 59.95 ± 1.03 |
64.82 ± 1.05 / 20.37 ± 1.06 |
48.07 ± 1.24 / 60.50 ± 0.88 |
45.03 ± 1.84 / 63.40 ± 1.23 |
9.10 ± 1.03 / 30.51 ± 1.01 |
20.47 ± 4.02 / 21.28 ± 2.58 |
24.18 ± 4.24 / 24.41 ± 3.40 |
32.61 ± 1.86 / 47.91 ± 2.11 |
60.17 ± 2.18 / 13.48 ± 1.53 |
3.22 ± 1.55 / 36.61 ± 2.49 |
3.91 ± 2.50 / 45.37 ± 4.56 |
41.16 ± 3.73 / 63.31 ± 3.73 |
19.03 ± 1.65 / 38.84 ± 1.33 |
7.35 ± 1.61 / 28.89 ± 1.54 |
30.45 ± 3.49 / 23.98 ± 3.18 |
76.36 ± 1.10 / 65.98 ± 2.36 |
6.06 ± 2.07 / 49.80 ± 2.71 |
55.19 ± 0.71 / 60.59 ± 0.61 |
63.12 ± 0.69 / 17.92 ± 0.39 |
20.80 ± 0.90 / 40.36 ± 0.78 |
6.24 ± 1.13 / 28.87 ± 1.03 |
10.67 ± 5.23 / 13.01 ± 3.26 |
-0.21 ± 0.99 / 33.71 ± 0.28 |
20.22 ± 3.01 / 43.48 ± 2.32 |
59.97 ± 2.49 / 13.32 ± 2.03 |
10.08 ± 1.82 / 32.08 ± 1.37 |
1.16 ± 2.48 / 51.00 ± 1.70 |
19.69 ± 4.71 / 19.53 ± 3.13 |
50.36 ± 2.83 / 60.36 ± 3.45 |
9.07 ± 2.41 / 44.45 ± 4.37 |
27.06 ± 4.74 / 53.36 ± 6.20 |
68.52 ± 1.47 / 26.96 ± 3.01 |
26.50 ± 0.89 / 44.19 ± 0.75 |
9.36 ± 1.35 / 30.60 ± 1.18 |
22.63 ± 4.98 / 22.71 ± 2.86 |
8.11 ± 1.55 / 28.07 ± 1.80 |
8.04 ± 1.79 / 48.95 ± 2.97 |
52.39 ± 2.14 / 65.22 ± 1.11 |
61.90 ± 1.04 / 17.09 ± 0.93 |
22.76 ± 0.76 / 41.67 ± 0.80 |
8.50 ± 1.32 / 30.16 ± 1.11 |
30.82 ± 4.46 / 27.49 ± 3.87 |
66.28 ± 0.84 / 65.60 ± 1.23 |
10.09 ± 2.52 / 48.92 ± 3.34 |
64.96 ± 3.77 / 78.21 ± 2.16 |
67.13 ± 0.54 / 21.94 ± 0.39 |
35.14 ± 1.07 / 51.22 ± 0.84 |
11.26 ± 1.35 / 31.40 ± 1.40 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
meta-llama/Llama-3.2-1B-Instruct (few-shot) |
1236 |
128 |
131073 |
False |
7,436 ± 1,846 / 1,508 ± 479 |
3.58 |
3.43 |
3.77 |
3.42 |
4.16 |
3.43 |
3.76 |
3.08 |
35.45 ± 2.41 / 30.39 ± 1.72 |
36.94 ± 1.08 / 49.24 ± 1.41 |
1.12 ± 2.21 / 44.63 ± 2.92 |
44.61 ± 0.84 / 53.34 ± 0.63 |
61.33 ± 1.47 / 15.38 ± 1.23 |
27.14 ± 1.18 / 43.89 ± 1.09 |
18.57 ± 1.82 / 46.35 ± 1.18 |
3.16 ± 0.85 / 26.86 ± 0.87 |
44.66 ± 0.68 / 41.13 ± 2.11 |
47.78 ± 1.22 / 44.30 ± 1.57 |
27.43 ± 1.89 / 42.83 ± 3.08 |
57.67 ± 1.45 / 10.42 ± 1.07 |
0.07 ± 1.51 / 34.07 ± 0.78 |
1.14 ± 1.23 / 33.17 ± 0.47 |
18.00 ± 3.56 / 39.37 ± 4.69 |
11.67 ± 1.20 / 33.08 ± 0.94 |
3.53 ± 1.01 / 26.63 ± 0.86 |
41.60 ± 2.74 / 37.22 ± 3.26 |
71.86 ± 2.01 / 71.15 ± 2.16 |
3.72 ± 1.40 / 48.04 ± 1.96 |
43.57 ± 1.35 / 52.90 ± 1.42 |
56.69 ± 0.79 / 13.27 ± 0.37 |
14.64 ± 0.91 / 35.56 ± 0.80 |
3.10 ± 0.87 / 26.60 ± 0.68 |
33.76 ± 3.44 / 32.21 ± 2.82 |
-0.13 ± 1.34 / 42.66 ± 3.62 |
12.43 ± 2.62 / 33.38 ± 1.39 |
59.46 ± 2.42 / 13.23 ± 1.87 |
2.09 ± 1.34 / 25.68 ± 0.67 |
3.56 ± 2.07 / 56.72 ± 0.99 |
42.51 ± 1.31 / 37.05 ± 1.59 |
38.26 ± 2.34 / 55.52 ± 2.66 |
5.48 ± 1.36 / 48.23 ± 2.44 |
19.43 ± 3.10 / 41.82 ± 3.29 |
60.81 ± 1.75 / 13.79 ± 2.22 |
16.06 ± 1.35 / 36.96 ± 0.92 |
6.64 ± 0.55 / 29.12 ± 0.60 |
42.01 ± 2.06 / 37.16 ± 1.98 |
9.15 ± 1.70 / 32.55 ± 2.69 |
1.11 ± 2.15 / 36.71 ± 3.89 |
40.04 ± 1.61 / 53.75 ± 1.10 |
58.72 ± 1.05 / 12.47 ± 0.62 |
17.71 ± 0.69 / 38.01 ± 0.61 |
6.98 ± 1.11 / 28.05 ± 1.00 |
56.41 ± 1.79 / 52.05 ± 1.57 |
59.46 ± 1.16 / 65.61 ± 1.08 |
8.36 ± 0.71 / 49.50 ± 2.90 |
47.26 ± 3.09 / 67.95 ± 2.10 |
66.61 ± 0.54 / 21.06 ± 1.04 |
25.59 ± 0.93 / 43.75 ± 0.65 |
18.56 ± 1.15 / 38.13 ± 0.88 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
google/gemma-2b (few-shot) |
2506 |
256 |
8192 |
True |
6,087 ± 1,046 / 1,902 ± 563 |
3.65 |
3.40 |
3.76 |
3.45 |
4.35 |
3.52 |
3.84 |
3.24 |
19.97 ± 3.91 / 16.51 ± 3.20 |
40.21 ± 1.00 / 46.73 ± 1.82 |
2.27 ± 2.39 / 38.71 ± 4.03 |
50.55 ± 1.22 / 56.27 ± 1.09 |
63.07 ± 1.07 / 16.98 ± 0.98 |
15.04 ± 1.21 / 35.51 ± 0.80 |
30.63 ± 3.36 / 50.02 ± 2.13 |
4.90 ± 0.95 / 28.18 ± 0.88 |
15.53 ± 5.69 / 15.49 ± 5.08 |
19.78 ± 4.54 / 18.86 ± 4.22 |
32.89 ± 1.65 / 42.58 ± 3.16 |
57.65 ± 2.16 / 10.13 ± 1.30 |
1.18 ± 1.00 / 33.34 ± 0.26 |
0.00 ± 0.00 / 32.79 ± 0.34 |
33.33 ± 3.73 / 53.15 ± 4.42 |
11.27 ± 1.41 / 32.73 ± 1.25 |
5.10 ± 1.44 / 28.63 ± 1.05 |
14.67 ± 4.71 / 14.85 ± 3.77 |
75.45 ± 1.10 / 64.08 ± 1.47 |
3.82 ± 1.23 / 44.81 ± 3.55 |
51.73 ± 0.88 / 57.35 ± 0.82 |
59.72 ± 1.46 / 15.26 ± 0.64 |
10.98 ± 0.98 / 31.92 ± 0.80 |
4.24 ± 0.47 / 27.53 ± 0.44 |
8.83 ± 5.85 / 9.93 ± 4.70 |
0.31 ± 1.95 / 45.42 ± 3.51 |
16.08 ± 2.91 / 37.41 ± 2.44 |
60.00 ± 2.62 / 13.07 ± 1.31 |
2.52 ± 1.20 / 26.23 ± 1.40 |
0.00 ± 2.53 / 56.42 ± 0.98 |
16.95 ± 2.96 / 15.80 ± 2.16 |
44.96 ± 3.30 / 61.27 ± 2.88 |
0.77 ± 1.22 / 33.68 ± 0.59 |
17.92 ± 4.72 / 40.68 ± 6.34 |
66.80 ± 0.96 / 22.24 ± 1.37 |
12.11 ± 0.94 / 33.12 ± 0.90 |
7.32 ± 1.40 / 30.11 ± 1.16 |
16.90 ± 4.91 / 17.38 ± 4.30 |
9.95 ± 0.78 / 27.94 ± 1.43 |
0.41 ± 1.03 / 33.54 ± 0.32 |
49.15 ± 1.55 / 59.16 ± 1.44 |
58.61 ± 2.22 / 13.67 ± 1.15 |
10.94 ± 0.50 / 31.87 ± 0.76 |
3.29 ± 0.95 / 26.85 ± 0.49 |
19.65 ± 5.96 / 18.64 ± 5.49 |
62.14 ± 1.16 / 67.81 ± 0.65 |
8.30 ± 1.63 / 45.01 ± 3.82 |
66.30 ± 1.42 / 77.75 ± 0.63 |
66.51 ± 0.85 / 21.76 ± 0.84 |
20.38 ± 0.82 / 38.44 ± 0.70 |
7.41 ± 1.01 / 29.08 ± 0.61 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.10.8 |
12.1.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
ibm-granite/granite-3b-code-base-2k (few-shot) |
3483 |
49 |
2048 |
True |
2,732 ± 868 / 662 ± 238 |
3.67 |
3.37 |
3.99 |
3.66 |
4.22 |
3.79 |
3.61 |
3.05 |
38.62 ± 3.40 / 27.71 ± 3.01 |
35.47 ± 1.35 / 52.70 ± 2.05 |
5.07 ± 1.76 / 43.91 ± 4.86 |
45.21 ± 0.84 / 50.96 ± 0.94 |
62.50 ± 0.59 / 15.45 ± 0.50 |
13.46 ± 2.03 / 33.24 ± 1.59 |
15.31 ± 3.62 / 43.65 ± 2.19 |
6.00 ± 1.15 / 29.24 ± 0.76 |
53.93 ± 3.93 / 48.95 ± 4.17 |
54.04 ± 1.83 / 49.74 ± 2.48 |
23.83 ± 3.47 / 45.39 ± 3.46 |
50.59 ± 3.68 / 7.28 ± 1.97 |
3.91 ± 1.46 / 42.54 ± 4.53 |
1.55 ± 2.39 / 40.63 ± 4.26 |
2.37 ± 0.20 / 12.14 ± 1.07 |
8.68 ± 1.17 / 31.15 ± 0.84 |
6.19 ± 0.85 / 29.29 ± 0.77 |
51.76 ± 4.53 / 41.73 ± 6.65 |
70.61 ± 1.12 / 60.47 ± 1.13 |
6.24 ± 3.11 / 46.34 ± 5.43 |
44.67 ± 1.34 / 50.56 ± 1.33 |
41.31 ± 2.13 / 7.20 ± 1.44 |
7.41 ± 0.75 / 30.14 ± 0.39 |
5.42 ± 0.79 / 29.15 ± 0.59 |
38.52 ± 3.25 / 28.84 ± 5.49 |
0.00 ± 0.00 / 33.69 ± 0.28 |
12.94 ± 2.60 / 36.06 ± 2.17 |
58.58 ± 4.00 / 12.91 ± 2.09 |
2.11 ± 1.02 / 27.80 ± 1.02 |
-4.75 ± 2.84 / 50.40 ± 4.21 |
49.38 ± 2.20 / 42.66 ± 3.24 |
41.72 ± 4.07 / 60.45 ± 3.07 |
7.67 ± 1.52 / 46.66 ± 3.23 |
13.70 ± 2.43 / 30.21 ± 3.80 |
45.88 ± 3.36 / 8.30 ± 1.98 |
8.73 ± 1.03 / 31.46 ± 0.70 |
6.18 ± 1.33 / 29.78 ± 1.02 |
50.88 ± 3.41 / 39.51 ± 3.29 |
12.39 ± 1.50 / 30.05 ± 1.80 |
3.31 ± 1.19 / 37.97 ± 4.40 |
48.44 ± 1.06 / 58.85 ± 0.75 |
52.50 ± 2.95 / 10.11 ± 2.12 |
9.22 ± 0.79 / 31.06 ± 0.75 |
4.45 ± 1.38 / 28.26 ± 1.08 |
60.64 ± 2.11 / 55.14 ± 2.01 |
61.20 ± 1.16 / 61.92 ± 1.68 |
7.63 ± 2.79 / 46.39 ± 3.79 |
69.83 ± 2.12 / 80.15 ± 1.27 |
56.62 ± 3.70 / 13.80 ± 2.77 |
16.29 ± 0.76 / 36.25 ± 0.61 |
10.37 ± 1.17 / 32.60 ± 0.89 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
LumiOpen/Viking-13B (few-shot) |
14030 |
131 |
4097 |
True |
840 ± 79 / 400 ± 124 |
3.68 |
3.34 |
3.79 |
3.35 |
3.97 |
3.74 |
4.22 |
3.37 |
28.60 ± 4.69 / 20.29 ± 3.37 |
48.71 ± 1.27 / 60.90 ± 2.95 |
2.30 ± 1.34 / 37.21 ± 2.50 |
53.85 ± 1.73 / 58.96 ± 1.67 |
64.05 ± 0.93 / 16.99 ± 1.44 |
0.55 ± 0.59 / 24.15 ± 0.73 |
0.00 ± 2.29 / 35.66 ± 1.43 |
0.36 ± 1.09 / 25.24 ± 0.60 |
26.76 ± 6.99 / 23.69 ± 3.73 |
35.38 ± 5.87 / 27.52 ± 3.45 |
29.22 ± 2.89 / 39.25 ± 1.86 |
56.69 ± 2.08 / 8.56 ± 1.22 |
2.58 ± 2.68 / 36.11 ± 2.42 |
2.79 ± 1.44 / 36.17 ± 1.51 |
34.41 ± 3.68 / 53.61 ± 4.28 |
-0.56 ± 0.87 / 21.99 ± 0.62 |
-0.43 ± 1.02 / 24.54 ± 0.89 |
31.55 ± 4.67 / 18.37 ± 2.73 |
78.66 ± 1.03 / 78.34 ± 1.13 |
5.69 ± 2.24 / 44.98 ± 3.55 |
52.93 ± 1.30 / 57.87 ± 1.27 |
60.05 ± 1.20 / 13.94 ± 0.43 |
1.32 ± 1.02 / 23.28 ± 0.65 |
0.35 ± 0.66 / 25.33 ± 0.66 |
26.28 ± 5.09 / 22.73 ± 3.35 |
2.17 ± 1.98 / 48.03 ± 2.64 |
22.65 ± 3.50 / 45.48 ± 2.99 |
62.07 ± 1.73 / 11.04 ± 1.91 |
-0.07 ± 0.85 / 23.51 ± 0.95 |
-2.92 ± 4.86 / 53.55 ± 3.32 |
34.53 ± 1.24 / 29.89 ± 1.96 |
42.90 ± 2.66 / 56.64 ± 4.71 |
1.51 ± 1.64 / 43.36 ± 4.05 |
15.83 ± 1.42 / 29.77 ± 2.54 |
61.40 ± 3.15 / 14.84 ± 2.07 |
-1.84 ± 1.09 / 23.98 ± 0.66 |
-0.12 ± 1.30 / 24.41 ± 0.96 |
36.74 ± 3.36 / 32.36 ± 1.39 |
8.57 ± 2.44 / 34.17 ± 2.59 |
3.01 ± 1.94 / 46.03 ± 4.19 |
32.32 ± 1.55 / 40.73 ± 1.64 |
51.76 ± 1.36 / 10.67 ± 0.56 |
0.67 ± 1.15 / 24.89 ± 0.79 |
-0.30 ± 1.01 / 23.52 ± 0.38 |
42.78 ± 4.24 / 40.64 ± 2.84 |
59.90 ± 4.98 / 54.05 ± 2.70 |
5.68 ± 1.91 / 50.82 ± 2.18 |
58.52 ± 1.88 / 68.97 ± 1.86 |
64.83 ± 0.95 / 18.37 ± 0.46 |
1.63 ± 0.89 / 23.51 ± 0.83 |
0.54 ± 1.01 / 24.93 ± 0.46 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.4 |
12.10.5 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.4 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.8 |
12.10.5 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
google/gemma-2b-it (few-shot) |
2506 |
256 |
8192 |
False |
6,471 ± 1,142 / 1,961 ± 584 |
3.80 |
3.62 |
3.76 |
4.14 |
4.42 |
3.55 |
3.85 |
3.27 |
24.44 ± 2.59 / 17.37 ± 2.03 |
34.03 ± 2.50 / 52.42 ± 2.16 |
2.25 ± 1.28 / 42.33 ± 3.11 |
42.12 ± 1.18 / 49.76 ± 1.22 |
62.41 ± 1.21 / 17.66 ± 0.54 |
15.16 ± 1.35 / 31.61 ± 1.92 |
12.67 ± 1.89 / 41.99 ± 1.17 |
2.67 ± 1.17 / 26.82 ± 0.69 |
39.78 ± 2.67 / 31.15 ± 2.70 |
43.58 ± 2.49 / 36.60 ± 2.76 |
22.01 ± 3.00 / 40.48 ± 2.81 |
55.43 ± 4.07 / 11.54 ± 0.87 |
2.76 ± 1.35 / 44.34 ± 3.05 |
1.45 ± 1.35 / 39.55 ± 3.53 |
32.42 ± 1.72 / 56.65 ± 0.92 |
7.68 ± 0.87 / 29.15 ± 0.61 |
1.06 ± 1.38 / 25.48 ± 1.00 |
33.51 ± 2.12 / 23.48 ± 2.69 |
43.97 ± 1.64 / 57.41 ± 1.18 |
0.53 ± 1.09 / 39.60 ± 1.99 |
39.39 ± 1.04 / 47.28 ± 1.02 |
40.55 ± 6.41 / 11.10 ± 1.63 |
11.06 ± 0.98 / 31.69 ± 0.81 |
1.03 ± 0.85 / 25.55 ± 0.60 |
20.49 ± 2.30 / 18.33 ± 1.40 |
-0.01 ± 2.13 / 46.02 ± 2.71 |
10.95 ± 2.39 / 37.64 ± 0.75 |
59.16 ± 0.96 / 9.92 ± 1.05 |
0.45 ± 1.44 / 22.94 ± 0.76 |
0.62 ± 1.42 / 56.02 ± 0.95 |
36.62 ± 1.56 / 28.22 ± 1.66 |
28.54 ± 2.70 / 50.10 ± 1.65 |
1.15 ± 1.66 / 38.16 ± 2.78 |
23.39 ± 1.00 / 51.61 ± 1.04 |
63.02 ± 2.00 / 19.54 ± 1.33 |
12.27 ± 1.33 / 33.40 ± 1.08 |
6.57 ± 0.74 / 28.60 ± 0.70 |
38.85 ± 3.77 / 32.18 ± 2.49 |
11.25 ± 1.90 / 28.36 ± 1.81 |
-2.27 ± 1.37 / 37.91 ± 2.26 |
45.95 ± 1.11 / 56.54 ± 0.95 |
51.99 ± 8.25 / 12.75 ± 2.04 |
10.97 ± 0.92 / 32.28 ± 0.76 |
1.45 ± 1.15 / 24.79 ± 0.52 |
40.05 ± 2.56 / 33.77 ± 1.94 |
48.83 ± 1.00 / 60.88 ± 0.70 |
5.83 ± 1.52 / 50.74 ± 1.73 |
63.77 ± 1.40 / 76.59 ± 0.77 |
67.28 ± 0.27 / 22.84 ± 0.41 |
18.21 ± 0.70 / 37.61 ± 0.55 |
10.84 ± 1.23 / 31.84 ± 1.00 |
12.5.2 |
12.1.0 |
12.1.0 |
12.4.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.5.2 |
12.1.0 |
12.4.0 |
12.1.0 |
12.1.0 |
12.4.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.4.0 |
12.4.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.1.0 |
12.4.0 |
12.4.0 |
12.10.8 |
12.1.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.4.0 |
12.4.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.4.0 |
12.4.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.4.0 |
12.4.0 |
12.1.0 |
12.1.0 |
Qwen/Qwen1.5-1.8B-Chat (few-shot) |
1837 |
152 |
32768 |
False |
8,304 ± 1,846 / 1,933 ± 617 |
3.85 |
3.88 |
4.07 |
3.70 |
4.56 |
3.70 |
4.05 |
3.01 |
18.00 ± 2.52 / 14.88 ± 1.68 |
26.58 ± 2.81 / 45.88 ± 3.40 |
0.63 ± 1.48 / 33.42 ± 0.28 |
41.66 ± 1.48 / 49.40 ± 1.53 |
57.19 ± 1.18 / 11.87 ± 0.68 |
22.17 ± 1.31 / 39.97 ± 1.18 |
12.85 ± 3.11 / 42.13 ± 2.09 |
7.01 ± 0.62 / 30.16 ± 0.46 |
26.99 ± 3.92 / 24.61 ± 2.74 |
25.74 ± 3.76 / 24.51 ± 2.96 |
19.85 ± 1.97 / 35.75 ± 1.74 |
55.08 ± 0.83 / 8.11 ± 0.35 |
1.96 ± 1.33 / 44.22 ± 2.93 |
-0.01 ± 1.39 / 39.57 ± 2.97 |
16.33 ± 2.17 / 31.16 ± 3.40 |
7.79 ± 0.78 / 29.50 ± 0.61 |
5.61 ± 1.32 / 28.45 ± 1.02 |
20.94 ± 3.73 / 18.26 ± 2.84 |
52.54 ± 3.33 / 60.44 ± 3.13 |
0.34 ± 1.22 / 36.61 ± 1.57 |
43.55 ± 1.14 / 50.53 ± 1.40 |
61.19 ± 0.69 / 15.92 ± 0.24 |
10.74 ± 0.92 / 32.65 ± 0.68 |
4.83 ± 0.62 / 28.76 ± 0.55 |
14.15 ± 1.92 / 14.96 ± 2.11 |
0.78 ± 1.70 / 44.74 ± 3.57 |
7.80 ± 1.32 / 23.47 ± 1.64 |
57.27 ± 1.42 / 10.43 ± 0.97 |
1.62 ± 1.18 / 25.09 ± 1.06 |
1.92 ± 2.32 / 50.07 ± 2.68 |
28.04 ± 2.71 / 24.08 ± 1.58 |
36.21 ± 3.42 / 54.82 ± 3.32 |
3.12 ± 1.42 / 46.21 ± 2.93 |
16.33 ± 3.22 / 41.91 ± 4.34 |
61.47 ± 1.67 / 12.62 ± 1.40 |
13.44 ± 1.22 / 34.26 ± 0.98 |
8.31 ± 1.08 / 31.05 ± 0.84 |
23.44 ± 5.09 / 25.00 ± 2.33 |
6.82 ± 1.82 / 30.97 ± 2.65 |
4.11 ± 1.73 / 43.70 ± 3.47 |
33.16 ± 1.61 / 46.66 ± 1.27 |
60.91 ± 0.99 / 12.65 ± 0.41 |
12.11 ± 0.90 / 33.62 ± 0.61 |
6.41 ± 1.13 / 29.73 ± 0.82 |
40.89 ± 2.63 / 37.44 ± 2.39 |
55.33 ± 1.77 / 64.53 ± 0.70 |
11.23 ± 1.81 / 52.85 ± 2.65 |
60.69 ± 1.44 / 74.24 ± 0.82 |
67.23 ± 0.14 / 18.87 ± 0.43 |
26.84 ± 0.41 / 44.86 ± 0.31 |
23.89 ± 1.20 / 42.78 ± 0.95 |
12.5.2 |
11.0.0 |
12.1.0 |
12.5.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.5.2 |
11.0.0 |
12.5.0 |
12.1.0 |
12.1.0 |
12.5.0 |
12.1.0 |
12.1.0 |
12.5.2 |
11.0.0 |
12.1.0 |
12.5.0 |
12.5.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.1.0 |
12.5.0 |
12.5.0 |
12.10.8 |
12.1.0 |
12.5.2 |
11.0.0 |
12.1.0 |
12.5.0 |
12.5.0 |
12.1.0 |
12.1.0 |
12.5.2 |
11.0.0 |
12.1.0 |
12.5.0 |
12.5.0 |
12.1.0 |
12.1.0 |
12.5.2 |
11.0.0 |
12.1.0 |
12.5.0 |
12.5.0 |
12.1.0 |
12.1.0 |
Qwen/Qwen1.5-1.8B (few-shot) |
1837 |
152 |
32768 |
True |
5,666 ± 1,328 / 1,256 ± 408 |
3.90 |
3.91 |
4.08 |
3.78 |
4.58 |
3.84 |
4.32 |
2.81 |
9.83 ± 3.50 / 8.97 ± 2.64 |
29.03 ± 2.48 / 46.75 ± 3.69 |
0.56 ± 0.87 / 33.34 ± 0.23 |
46.43 ± 0.74 / 53.20 ± 0.47 |
56.43 ± 1.74 / 11.67 ± 1.17 |
14.86 ± 1.85 / 33.52 ± 1.63 |
17.56 ± 2.63 / 45.31 ± 1.78 |
4.78 ± 1.48 / 27.73 ± 1.32 |
12.10 ± 5.58 / 12.85 ± 4.80 |
13.42 ± 6.02 / 13.82 ± 5.16 |
22.82 ± 3.11 / 43.88 ± 3.10 |
54.48 ± 1.91 / 8.22 ± 0.70 |
2.70 ± 2.16 / 47.68 ± 3.18 |
2.21 ± 1.46 / 42.80 ± 4.36 |
16.31 ± 2.22 / 30.78 ± 3.64 |
9.57 ± 1.11 / 30.18 ± 0.83 |
6.02 ± 0.84 / 28.58 ± 1.13 |
18.01 ± 6.41 / 18.55 ± 4.65 |
51.91 ± 4.78 / 59.44 ± 4.65 |
1.49 ± 1.95 / 40.76 ± 4.07 |
44.83 ± 0.63 / 51.87 ± 0.72 |
54.82 ± 1.62 / 14.43 ± 0.68 |
11.54 ± 0.73 / 32.55 ± 0.60 |
7.19 ± 1.40 / 29.76 ± 1.22 |
12.26 ± 4.13 / 12.77 ± 3.60 |
0.94 ± 1.34 / 40.66 ± 3.73 |
6.31 ± 1.01 / 20.24 ± 2.02 |
55.32 ± 3.49 / 8.91 ± 1.05 |
3.65 ± 1.45 / 26.36 ± 0.92 |
1.13 ± 3.74 / 52.30 ± 2.26 |
9.23 ± 4.86 / 10.43 ± 3.83 |
38.30 ± 2.90 / 56.94 ± 2.83 |
0.39 ± 1.17 / 33.47 ± 0.34 |
16.67 ± 3.02 / 41.61 ± 3.00 |
61.74 ± 1.58 / 14.71 ± 1.12 |
13.65 ± 1.17 / 33.35 ± 0.91 |
8.86 ± 0.99 / 30.21 ± 0.77 |
11.66 ± 6.46 / 15.15 ± 4.38 |
5.20 ± 1.78 / 35.43 ± 2.14 |
2.89 ± 1.91 / 41.36 ± 4.63 |
34.60 ± 2.17 / 48.83 ± 1.05 |
55.00 ± 1.73 / 11.21 ± 0.64 |
13.56 ± 0.64 / 34.17 ± 0.48 |
5.89 ± 0.82 / 29.17 ± 0.66 |
37.22 ± 3.24 / 34.07 ± 3.11 |
64.34 ± 1.18 / 62.90 ± 1.36 |
15.30 ± 1.17 / 55.67 ± 1.16 |
64.41 ± 1.29 / 75.79 ± 0.97 |
68.15 ± 0.13 / 22.11 ± 0.19 |
27.24 ± 1.14 / 44.95 ± 0.84 |
22.84 ± 1.16 / 41.75 ± 0.99 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.10.8 |
12.1.0 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
meta-llama/Llama-3.2-1B (few-shot) |
1236 |
128 |
131073 |
True |
7,577 ± 1,884 / 1,555 ± 492 |
3.95 |
3.76 |
4.01 |
3.66 |
4.51 |
3.72 |
4.44 |
3.53 |
19.82 ± 4.70 / 17.20 ± 3.57 |
35.97 ± 3.00 / 49.88 ± 3.80 |
2.14 ± 2.61 / 44.16 ± 4.48 |
46.59 ± 5.44 / 51.92 ± 6.14 |
58.65 ± 1.07 / 11.57 ± 0.77 |
2.65 ± 1.26 / 25.17 ± 1.16 |
9.51 ± 2.67 / 40.41 ± 1.62 |
-0.88 ± 1.13 / 24.79 ± 0.98 |
30.54 ± 3.75 / 29.88 ± 3.25 |
31.34 ± 4.72 / 30.46 ± 4.56 |
29.50 ± 4.18 / 49.19 ± 4.59 |
53.31 ± 0.98 / 7.37 ± 0.54 |
-0.13 ± 1.28 / 37.46 ± 3.25 |
0.02 ± 1.75 / 39.49 ± 4.41 |
19.59 ± 5.61 / 34.02 ± 8.33 |
2.49 ± 1.09 / 25.63 ± 0.78 |
2.53 ± 1.16 / 26.30 ± 0.82 |
29.89 ± 7.13 / 27.65 ± 6.45 |
74.33 ± 1.07 / 73.73 ± 1.77 |
1.06 ± 1.79 / 43.95 ± 3.08 |
46.89 ± 2.72 / 52.70 ± 3.39 |
52.06 ± 2.11 / 12.53 ± 0.81 |
0.93 ± 1.44 / 26.10 ± 1.04 |
0.09 ± 1.37 / 24.84 ± 0.69 |
17.77 ± 6.81 / 16.42 ± 6.19 |
-0.35 ± 1.50 / 34.29 ± 1.64 |
8.15 ± 2.21 / 30.75 ± 2.05 |
54.21 ± 3.27 / 11.06 ± 1.56 |
0.71 ± 1.34 / 25.40 ± 0.83 |
2.88 ± 1.84 / 54.45 ± 2.60 |
24.79 ± 6.48 / 22.92 ± 5.74 |
47.65 ± 2.85 / 63.11 ± 2.17 |
2.39 ± 1.46 / 39.92 ± 4.38 |
13.39 ± 4.13 / 33.76 ± 5.50 |
61.07 ± 4.19 / 16.72 ± 4.33 |
3.94 ± 1.35 / 27.78 ± 1.07 |
0.90 ± 0.98 / 25.40 ± 0.65 |
22.03 ± 4.43 / 19.22 ± 3.92 |
4.25 ± 2.95 / 26.57 ± 3.31 |
1.46 ± 1.83 / 42.29 ± 4.01 |
41.76 ± 1.92 / 52.60 ± 1.99 |
51.56 ± 1.45 / 10.34 ± 0.52 |
5.46 ± 1.05 / 28.09 ± 0.78 |
-0.58 ± 0.81 / 23.58 ± 0.50 |
35.08 ± 5.88 / 32.44 ± 4.89 |
54.40 ± 2.92 / 64.38 ± 2.10 |
2.97 ± 0.84 / 45.05 ± 4.18 |
58.30 ± 2.84 / 71.04 ± 1.83 |
62.19 ± 1.70 / 16.53 ± 1.13 |
7.91 ± 0.72 / 29.30 ± 0.46 |
1.60 ± 1.21 / 26.25 ± 0.85 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
Qwen/Qwen1.5-0.5B (few-shot) |
620 |
152 |
32768 |
True |
11,371 ± 2,924 / 2,122 ± 692 |
4.22 |
4.30 |
4.44 |
4.17 |
4.63 |
4.16 |
4.36 |
3.51 |
19.01 ± 1.91 / 17.08 ± 1.83 |
8.88 ± 1.86 / 24.27 ± 2.45 |
0.66 ± 1.41 / 37.98 ± 4.14 |
32.78 ± 2.33 / 38.31 ± 2.81 |
55.57 ± 1.04 / 8.04 ± 0.82 |
7.21 ± 1.78 / 29.73 ± 1.08 |
16.56 ± 3.13 / 42.30 ± 1.26 |
0.62 ± 1.30 / 25.65 ± 0.72 |
34.46 ± 2.01 / 33.09 ± 2.32 |
33.41 ± 2.21 / 33.91 ± 2.33 |
6.31 ± 3.46 / 20.67 ± 2.69 |
49.88 ± 3.11 / 5.75 ± 0.88 |
-1.59 ± 1.08 / 36.27 ± 3.71 |
0.61 ± 1.41 / 38.84 ± 5.10 |
5.95 ± 1.53 / 16.20 ± 1.93 |
2.81 ± 1.18 / 25.21 ± 0.98 |
2.92 ± 0.88 / 26.67 ± 0.60 |
28.96 ± 2.39 / 26.49 ± 3.14 |
26.58 ± 5.12 / 28.64 ± 5.35 |
-1.88 ± 1.46 / 35.45 ± 2.92 |
34.59 ± 1.06 / 40.95 ± 1.11 |
53.36 ± 1.44 / 12.82 ± 0.58 |
6.52 ± 1.02 / 28.83 ± 0.78 |
1.91 ± 1.30 / 26.10 ± 0.65 |
16.20 ± 1.52 / 16.96 ± 1.71 |
-0.57 ± 1.20 / 41.25 ± 3.51 |
3.31 ± 0.82 / 16.86 ± 2.98 |
56.00 ± 3.13 / 10.05 ± 0.73 |
1.96 ± 1.72 / 25.55 ± 1.37 |
0.85 ± 1.91 / 52.12 ± 2.92 |
27.34 ± 1.95 / 24.46 ± 1.25 |
10.64 ± 5.31 / 26.79 ± 4.73 |
0.33 ± 1.20 / 35.20 ± 2.45 |
11.81 ± 2.10 / 27.38 ± 2.49 |
59.71 ± 2.14 / 12.23 ± 1.08 |
6.34 ± 1.10 / 29.19 ± 0.75 |
2.94 ± 0.65 / 27.16 ± 0.61 |
28.30 ± 3.90 / 28.67 ± 3.15 |
4.54 ± 2.76 / 26.53 ± 3.74 |
-0.42 ± 2.41 / 37.60 ± 3.89 |
20.81 ± 2.21 / 29.05 ± 2.31 |
58.40 ± 2.03 / 10.34 ± 0.54 |
7.44 ± 0.51 / 29.86 ± 0.35 |
1.70 ± 1.42 / 26.04 ± 0.91 |
37.51 ± 1.56 / 33.24 ± 2.24 |
57.15 ± 2.35 / 52.82 ± 1.40 |
2.94 ± 2.00 / 44.53 ± 3.65 |
42.57 ± 1.97 / 55.17 ± 1.29 |
65.22 ± 0.29 / 19.22 ± 0.18 |
18.24 ± 1.14 / 37.15 ± 0.82 |
10.89 ± 1.01 / 32.65 ± 0.85 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.10.8 |
12.1.0 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
RuterNorway/Llama-2-7b-chat-norwegian (few-shot) |
unknown |
32 |
4096 |
False |
10,890 ± 2,686 / 2,186 ± 750 |
4.26 |
4.50 |
4.22 |
4.10 |
4.82 |
3.85 |
3.76 |
4.54 |
10.12 ± 1.24 / 9.84 ± 1.12 |
10.65 ± 3.65 / 28.33 ± 5.27 |
-0.66 ± 1.24 / 33.61 ± 0.26 |
26.08 ± 3.96 / 28.87 ± 4.21 |
56.92 ± 0.98 / 8.57 ± 0.76 |
0.10 ± 1.50 / 26.50 ± 1.00 |
4.29 ± 5.87 / 35.00 ± 1.75 |
-0.88 ± 1.17 / 24.43 ± 0.74 |
21.04 ± 2.63 / 20.44 ± 2.47 |
18.71 ± 2.67 / 19.91 ± 2.89 |
12.22 ± 1.17 / 23.50 ± 3.03 |
53.49 ± 5.64 / 9.38 ± 1.34 |
-1.18 ± 1.40 / 35.70 ± 2.67 |
0.36 ± 1.28 / 37.66 ± 4.07 |
26.86 ± 1.65 / 50.11 ± 1.80 |
0.21 ± 0.83 / 26.88 ± 1.44 |
-0.30 ± 1.13 / 24.48 ± 0.70 |
22.38 ± 3.00 / 22.09 ± 2.85 |
31.11 ± 12.17 / 36.84 ± 11.52 |
0.09 ± 0.67 / 33.42 ± 0.30 |
44.36 ± 1.34 / 50.14 ± 1.15 |
55.44 ± 0.79 / 12.95 ± 0.51 |
1.12 ± 0.42 / 25.27 ± 0.68 |
-0.91 ± 0.96 / 24.26 ± 0.64 |
9.48 ± 1.48 / 10.10 ± 1.44 |
0.07 ± 1.06 / 43.54 ± 3.63 |
1.04 ± 0.96 / 7.35 ± 3.52 |
55.16 ± 1.26 / 10.52 ± 1.13 |
-0.80 ± 2.00 / 23.89 ± 0.86 |
-0.16 ± 0.86 / 32.02 ± 2.77 |
27.22 ± 1.38 / 24.48 ± 1.76 |
33.61 ± 5.06 / 49.68 ± 5.74 |
0.45 ± 0.91 / 35.24 ± 3.71 |
20.44 ± 3.29 / 45.50 ± 3.33 |
60.50 ± 0.63 / 13.71 ± 0.75 |
-0.10 ± 0.93 / 25.16 ± 1.17 |
-1.00 ± 1.03 / 24.94 ± 1.00 |
35.49 ± 3.10 / 29.35 ± 2.75 |
11.36 ± 1.56 / 30.66 ± 3.68 |
2.52 ± 2.14 / 42.60 ± 4.80 |
37.49 ± 1.37 / 47.34 ± 1.53 |
62.24 ± 0.86 / 15.62 ± 0.60 |
5.41 ± 1.15 / 27.75 ± 0.75 |
0.15 ± 0.98 / 25.59 ± 0.57 |
18.69 ± 7.23 / 18.50 ± 6.51 |
21.95 ± 6.30 / 33.38 ± 4.79 |
0.01 ± 1.91 / 39.40 ± 3.94 |
36.51 ± 2.07 / 50.66 ± 1.90 |
60.11 ± 1.39 / 16.29 ± 0.69 |
3.71 ± 0.75 / 28.35 ± 0.99 |
0.62 ± 0.99 / 24.68 ± 0.55 |
9.3.1 |
9.3.1 |
9.3.1 |
12.5.2 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
11.0.0 |
9.3.1 |
9.3.1 |
12.5.2 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
12.5.2 |
11.0.0 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
12.5.2 |
12.4.0 |
12.10.8 |
12.1.0 |
9.3.1 |
12.10.0 |
9.3.1 |
12.5.2 |
12.4.0 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
12.5.2 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
12.5.2 |
9.3.1 |
9.3.1 |
9.3.1 |
Qwen/Qwen1.5-0.5B-Chat (few-shot) |
620 |
152 |
32768 |
False |
11,740 ± 3,000 / 2,209 ± 721 |
4.29 |
4.21 |
5.05 |
4.27 |
4.60 |
4.17 |
4.21 |
3.49 |
17.38 ± 2.04 / 15.74 ± 1.99 |
10.72 ± 3.35 / 25.21 ± 3.80 |
1.32 ± 1.08 / 42.05 ± 3.69 |
34.58 ± 0.97 / 40.37 ± 1.02 |
55.87 ± 5.22 / 11.87 ± 1.03 |
4.56 ± 1.88 / 25.87 ± 1.72 |
22.41 ± 3.16 / 42.73 ± 0.96 |
1.71 ± 0.99 / 25.84 ± 0.79 |
29.52 ± 1.48 / 29.79 ± 1.62 |
31.27 ± 1.30 / 31.91 ± 1.31 |
11.49 ± 1.38 / 27.12 ± 1.98 |
9.92 ± 8.37 / 1.42 ± 1.14 |
0.29 ± 1.58 / 40.21 ± 4.22 |
-0.12 ± 1.48 / 39.92 ± 3.90 |
7.80 ± 1.19 / 17.09 ± 2.72 |
0.29 ± 1.08 / 24.63 ± 0.79 |
0.49 ± 1.19 / 24.95 ± 0.86 |
18.57 ± 4.62 / 17.69 ± 4.61 |
40.23 ± 5.86 / 49.01 ± 4.77 |
0.21 ± 1.06 / 39.60 ± 3.61 |
29.49 ± 2.47 / 35.01 ± 2.72 |
53.29 ± 6.52 / 13.04 ± 1.68 |
2.59 ± 0.72 / 26.87 ± 0.72 |
-0.84 ± 1.01 / 24.44 ± 0.61 |
9.50 ± 3.17 / 9.41 ± 3.40 |
1.76 ± 1.62 / 38.51 ± 3.72 |
3.14 ± 0.71 / 17.84 ± 2.26 |
58.92 ± 1.57 / 10.09 ± 1.41 |
-1.28 ± 1.48 / 24.82 ± 0.92 |
1.48 ± 3.56 / 53.95 ± 2.45 |
24.67 ± 0.99 / 23.98 ± 0.73 |
9.31 ± 2.97 / 21.50 ± 2.70 |
1.11 ± 1.69 / 37.88 ± 4.05 |
13.60 ± 1.60 / 29.10 ± 1.94 |
56.42 ± 7.64 / 11.68 ± 1.75 |
2.75 ± 0.91 / 27.17 ± 0.72 |
3.41 ± 1.30 / 27.45 ± 0.79 |
18.66 ± 4.43 / 17.56 ± 4.28 |
8.59 ± 3.20 / 29.65 ± 5.10 |
0.34 ± 2.02 / 43.92 ± 3.15 |
26.74 ± 1.57 / 35.03 ± 2.14 |
62.36 ± 0.81 / 11.72 ± 0.73 |
2.09 ± 1.13 / 25.90 ± 0.60 |
1.44 ± 1.12 / 26.50 ± 0.68 |
33.86 ± 2.16 / 32.80 ± 2.21 |
55.41 ± 2.17 / 54.48 ± 1.65 |
1.15 ± 1.81 / 34.47 ± 1.12 |
53.34 ± 1.21 / 64.09 ± 1.26 |
65.81 ± 1.90 / 20.88 ± 0.66 |
11.66 ± 1.13 / 32.84 ± 0.97 |
5.22 ± 1.17 / 27.95 ± 1.10 |
12.5.2 |
11.0.0 |
12.1.0 |
12.4.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.5.2 |
11.0.0 |
12.5.0 |
12.1.0 |
12.1.0 |
12.4.0 |
12.1.0 |
12.1.0 |
12.5.2 |
11.0.0 |
12.1.0 |
12.4.0 |
12.5.0 |
12.1.0 |
12.1.0 |
12.5.2 |
12.1.0 |
12.5.0 |
12.5.0 |
12.10.8 |
12.1.0 |
12.5.2 |
11.0.0 |
12.1.0 |
12.5.0 |
12.5.0 |
12.1.0 |
12.1.0 |
12.5.2 |
11.0.0 |
12.1.0 |
12.5.0 |
12.5.0 |
12.1.0 |
12.1.0 |
12.5.2 |
11.0.0 |
12.1.0 |
12.5.0 |
12.5.0 |
12.1.0 |
12.1.0 |
ai-forever/mGPT (few-shot) |
unknown |
100 |
1024 |
True |
11,734 ± 3,124 / 2,174 ± 720 |
5.62 |
5.66 |
5.10 |
5.57 |
5.80 |
5.56 |
5.59 |
6.03 |
0.65 ± 0.68 / 0.59 ± 0.63 |
2.61 ± 2.75 / 20.51 ± 2.48 |
-0.73 ± 1.72 / 41.15 ± 3.71 |
1.99 ± 1.69 / 2.68 ± 1.87 |
35.64 ± 4.11 / 4.70 ± 2.01 |
-0.61 ± 0.54 / 24.71 ± 1.18 |
6.94 ± 3.67 / 38.18 ± 1.72 |
-1.12 ± 0.87 / 24.71 ± 0.88 |
0.08 ± 0.16 / 0.07 ± 0.14 |
0.00 ± 0.00 / 0.00 ± 0.00 |
4.76 ± 1.84 / 16.95 ± 5.07 |
31.66 ± 0.51 / 0.93 ± 0.29 |
0.67 ± 1.94 / 40.42 ± 4.43 |
-0.88 ± 1.89 / 40.70 ± 4.30 |
0.00 ± 0.00 / 0.74 ± 0.05 |
0.72 ± 0.81 / 22.86 ± 0.63 |
-0.20 ± 1.06 / 24.94 ± 0.69 |
0.00 ± 0.00 / 0.00 ± 0.00 |
0.00 ± 0.00 / 19.32 ± 0.16 |
0.49 ± 1.29 / 39.12 ± 3.92 |
6.24 ± 3.13 / 7.85 ± 3.67 |
31.89 ± 0.27 / 2.03 ± 0.10 |
-0.37 ± 1.08 / 22.43 ± 0.55 |
0.36 ± 0.83 / 25.08 ± 0.77 |
0.00 ± 0.00 / 0.00 ± 0.00 |
0.00 ± 0.00 / 33.69 ± 0.28 |
0.00 ± 0.00 / 0.05 ± 0.03 |
17.11 ± 1.37 / 0.96 ± 0.09 |
-0.02 ± 1.16 / 22.75 ± 0.50 |
0.47 ± 4.14 / 46.93 ± 3.13 |
0.00 ± 0.00 / 0.00 ± 0.00 |
0.19 ± 1.24 / 17.20 ± 1.22 |
-0.12 ± 0.91 / 36.65 ± 3.92 |
0.00 ± 0.00 / 1.29 ± 0.49 |
29.43 ± 1.80 / 2.35 ± 0.59 |
-0.69 ± 0.79 / 22.79 ± 0.51 |
0.15 ± 0.35 / 24.25 ± 0.59 |
0.11 ± 0.21 / 0.27 ± 0.53 |
-0.67 ± 1.33 / 8.96 ± 0.37 |
-0.97 ± 1.56 / 34.83 ± 1.94 |
0.29 ± 0.21 / 1.56 ± 0.19 |
30.20 ± 0.68 / 2.14 ± 0.04 |
1.45 ± 0.84 / 24.91 ± 0.60 |
-0.56 ± 0.80 / 23.53 ± 0.49 |
1.55 ± 1.98 / 1.45 ± 1.82 |
3.71 ± 3.16 / 22.09 ± 2.08 |
-0.42 ± 1.56 / 40.58 ± 3.74 |
5.58 ± 3.10 / 11.12 ± 4.66 |
34.62 ± 0.17 / 2.18 ± 0.04 |
0.37 ± 0.93 / 24.18 ± 0.90 |
-0.17 ± 0.50 / 24.82 ± 0.41 |
9.3.1 |
10.0.1 |
11.0.0 |
12.5.1 |
12.6.1 |
11.0.0 |
11.0.0 |
11.0.0 |
9.3.1 |
9.3.1 |
10.0.1 |
12.0.0 |
11.0.0 |
11.0.0 |
12.5.1 |
11.0.0 |
11.0.0 |
9.3.1 |
10.0.1 |
11.0.0 |
12.5.1 |
12.0.0 |
11.0.0 |
11.0.0 |
9.3.1 |
11.0.0 |
12.5.1 |
12.0.0 |
12.10.8 |
12.1.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
9.3.1 |
10.0.1 |
11.0.0 |
12.5.1 |
12.0.0 |
11.0.0 |
11.0.0 |
9.3.1 |
10.0.1 |
11.0.0 |
12.5.1 |
12.0.0 |
11.0.0 |
11.0.0 |