meta-llama/Meta-Llama-3-70B (few-shot, val) |
70554 |
128 |
8317 |
True |
312 ± 55 / 177 ± 51 |
1.23 |
72.91 ± 3.24 / 68.06 ± 4.62 |
19.08 ± 3.37 / 42.04 ± 2.31 |
54.33 ± 3.49 / 75.54 ± 2.31 |
63.99 ± 2.07 / 77.63 ± 1.16 |
70.41 ± 0.97 / 25.41 ± 1.66 |
65.33 ± 1.92 / 73.98 ± 1.56 |
71.06 ± 2.82 / 78.16 ± 2.22 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
gpt-4-1106-preview (few-shot) |
unknown |
100 |
128000 |
True |
573 ± 185 / 87 ± 32 |
1.34 |
66.44 ± 2.18 / 56.97 ± 2.87 |
15.05 ± 1.85 / 35.62 ± 1.91 |
74.01 ± 1.29 / 86.71 ± 0.78 |
57.81 ± 1.23 / 74.51 ± 0.62 |
67.13 ± 0.50 / 17.61 ± 0.76 |
65.88 ± 1.81 / 74.14 ± 1.43 |
84.97 ± 0.86 / 88.61 ± 0.68 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
152334H/miqu-1-70b-sf (few-shot, val) |
68977 |
32 |
32889 |
True |
2,126 ± 676 / 319 ± 104 |
1.44 |
67.00 ± 3.69 / 56.41 ± 4.29 |
15.33 ± 4.14 / 36.14 ± 2.91 |
55.48 ± 4.37 / 77.55 ± 2.24 |
61.02 ± 1.67 / 76.87 ± 1.15 |
68.95 ± 0.75 / 21.31 ± 1.20 |
54.36 ± 1.61 / 65.70 ± 1.26 |
70.26 ± 3.64 / 77.62 ± 2.82 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
meta-llama/Meta-Llama-3-70B-Instruct (few-shot, val) |
70554 |
128 |
8317 |
True |
1,673 ± 583 / 275 ± 85 |
1.46 |
74.64 ± 3.67 / 71.84 ± 4.01 |
18.90 ± 2.04 / 41.93 ± 1.60 |
49.54 ± 4.22 / 74.03 ± 2.52 |
44.77 ± 1.67 / 71.44 ± 1.30 |
70.28 ± 0.65 / 22.72 ± 0.95 |
65.80 ± 3.16 / 74.38 ± 2.37 |
76.21 ± 1.36 / 82.15 ± 1.01 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
upstage/SOLAR-10.7B-v1.0 (few-shot) |
10732 |
32 |
4096 |
True |
3,780 ± 906 / 799 ± 261 |
1.87 |
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 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
Nexusflow/Starling-LM-7B-beta (few-shot) |
7242 |
32 |
8192 |
False |
5,876 ± 1,021 / 1,677 ± 546 |
1.93 |
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 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
gpt-3.5-turbo-0613 (few-shot, val) |
unknown |
100 |
4095 |
True |
921 ± 293 / 113 ± 37 |
1.94 |
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 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
meta-llama/Llama-2-70b-hf (few-shot, val) |
68977 |
32 |
4221 |
True |
1,892 ± 650 / 318 ± 105 |
2.02 |
66.50 ± 3.72 / 57.66 ± 3.78 |
7.82 ± 4.30 / 34.91 ± 2.53 |
49.55 ± 4.95 / 73.43 ± 3.38 |
65.26 ± 1.55 / 77.36 ± 1.41 |
67.28 ± 1.07 / 21.33 ± 1.39 |
49.41 ± 2.21 / 61.91 ± 1.74 |
54.50 ± 4.84 / 65.70 ± 3.64 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
mlabonne/NeuralBeagle14-7B (few-shot, val) |
7242 |
32 |
8192 |
False |
2,549 ± 472 / 784 ± 245 |
2.23 |
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 |
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 |
2.25 |
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 |
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-Instruct (few-shot) |
8030 |
128 |
8192 |
True |
4,909 ± 1,215 / 978 ± 319 |
2.30 |
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 |
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 |
2.32 |
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 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
mlabonne/AlphaMonarch-7B (few-shot, val) |
7242 |
32 |
8192 |
False |
5,340 ± 1,262 / 1,157 ± 375 |
2.36 |
64.71 ± 5.15 / 53.58 ± 3.82 |
11.14 ± 3.37 / 38.64 ± 2.36 |
25.22 ± 5.45 / 61.28 ± 2.51 |
46.34 ± 1.07 / 66.56 ± 1.49 |
67.71 ± 0.59 / 17.76 ± 0.71 |
38.49 ± 2.59 / 53.52 ± 2.03 |
47.66 ± 2.91 / 60.31 ± 2.30 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
robinsmits/Qwen1.5-7B-Dutch-Chat-Sft-Bf16 (few-shot) |
7719 |
152 |
32768 |
False |
2,413 ± 463 / 700 ± 220 |
2.45 |
56.83 ± 2.31 / 46.81 ± 2.87 |
14.79 ± 1.96 / 41.48 ± 1.53 |
23.58 ± 2.69 / 50.85 ± 3.74 |
55.90 ± 1.80 / 70.07 ± 0.77 |
65.06 ± 1.20 / 18.45 ± 1.09 |
33.73 ± 0.75 / 50.05 ± 0.57 |
29.29 ± 1.83 / 45.90 ± 1.77 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
robinsmits/Qwen1.5-7B-Dutch-Chat (few-shot) |
7719 |
152 |
32768 |
False |
4,686 ± 1,131 / 996 ± 326 |
2.49 |
57.81 ± 2.68 / 47.15 ± 2.77 |
14.62 ± 2.25 / 41.08 ± 1.81 |
25.34 ± 2.37 / 54.46 ± 3.43 |
56.81 ± 1.44 / 70.49 ± 0.68 |
60.51 ± 2.40 / 15.62 ± 1.65 |
34.78 ± 0.80 / 50.83 ± 0.58 |
30.29 ± 1.78 / 46.74 ± 1.68 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
ReBatch/Llama-3-8B-dutch (few-shot) |
8030 |
128 |
8317 |
False |
3,800 ± 1,275 / 566 ± 194 |
2.50 |
60.14 ± 2.00 / 44.91 ± 2.19 |
11.07 ± 1.98 / 34.77 ± 1.31 |
15.67 ± 3.75 / 40.14 ± 2.65 |
59.93 ± 1.17 / 71.20 ± 1.30 |
64.49 ± 1.40 / 18.40 ± 1.70 |
36.13 ± 1.24 / 51.76 ± 0.92 |
28.25 ± 2.23 / 44.23 ± 2.03 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
Rijgersberg/Mistral-7B-v0.1-chat-nl (few-shot) |
7242 |
32 |
32768 |
False |
5,907 ± 1,028 / 1,695 ± 549 |
2.59 |
56.73 ± 1.95 / 38.97 ± 1.84 |
11.08 ± 1.46 / 32.20 ± 1.43 |
19.41 ± 2.55 / 57.17 ± 2.38 |
58.91 ± 0.92 / 71.22 ± 0.72 |
68.05 ± 0.39 / 21.26 ± 0.65 |
31.39 ± 0.86 / 48.09 ± 0.72 |
16.49 ± 2.14 / 36.67 ± 1.72 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
mistralai/Mistral-7B-v0.1 (few-shot) |
7242 |
32 |
32768 |
True |
2,657 ± 524 / 880 ± 278 |
2.65 |
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 |
9.1.2 |
9.1.2 |
9.1.2 |
12.5.1 |
11.0.0 |
9.2.0 |
9.2.0 |
BramVanroy/GEITje-7B-ultra (few-shot) |
7242 |
32 |
8192 |
False |
2,475 ± 460 / 765 ± 238 |
2.67 |
42.25 ± 2.12 / 27.85 ± 1.09 |
12.78 ± 2.52 / 42.17 ± 1.91 |
18.23 ± 1.91 / 50.04 ± 2.54 |
53.41 ± 1.11 / 66.45 ± 0.46 |
68.30 ± 0.40 / 20.79 ± 0.63 |
26.92 ± 1.09 / 44.44 ± 0.85 |
25.72 ± 1.01 / 43.74 ± 0.69 |
9.3.2 |
9.3.2 |
9.3.2 |
12.4.0 |
12.4.0 |
10.0.1 |
10.0.1 |
alpindale/Mistral-7B-v0.2-hf (few-shot) |
7242 |
32 |
32768 |
True |
1,841 ± 297 / 651 ± 193 |
2.67 |
56.76 ± 1.52 / 42.03 ± 1.98 |
7.11 ± 1.17 / 26.36 ± 2.97 |
23.55 ± 2.76 / 59.14 ± 3.18 |
61.89 ± 1.10 / 72.41 ± 1.08 |
64.33 ± 0.72 / 17.66 ± 0.87 |
34.92 ± 1.07 / 51.02 ± 0.85 |
23.87 ± 1.80 / 42.03 ± 1.58 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
mistralai/Mistral-7B-Instruct-v0.2 (few-shot) |
7242 |
32 |
32768 |
False |
2,538 ± 415 / 821 ± 253 |
2.67 |
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 |
9.3.1 |
9.2.0 |
9.3.1 |
12.4.0 |
12.4.0 |
9.3.2 |
9.3.2 |
Rijgersberg/GEITje-7B-chat-v2 (few-shot) |
7242 |
32 |
32768 |
False |
5,908 ± 1,022 / 1,694 ± 551 |
2.78 |
42.12 ± 4.00 / 31.12 ± 1.86 |
11.06 ± 2.30 / 40.32 ± 1.64 |
19.71 ± 3.65 / 49.65 ± 4.28 |
59.19 ± 0.91 / 70.06 ± 0.82 |
65.55 ± 0.49 / 19.18 ± 0.67 |
27.71 ± 0.91 / 45.01 ± 0.71 |
18.03 ± 1.77 / 36.82 ± 1.76 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
RuterNorway/Llama-2-13b-chat-norwegian (few-shot) |
unknown |
32 |
4096 |
False |
7,778 ± 1,755 / 1,703 ± 552 |
2.80 |
57.66 ± 1.29 / 43.77 ± 2.78 |
8.41 ± 1.47 / 25.59 ± 1.30 |
16.93 ± 2.60 / 55.72 ± 3.35 |
56.29 ± 1.11 / 68.94 ± 0.81 |
66.22 ± 0.50 / 19.03 ± 0.51 |
25.70 ± 1.05 / 44.15 ± 0.82 |
17.92 ± 1.69 / 37.64 ± 1.43 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
occiglot/occiglot-7b-eu5-instruct (few-shot) |
7242 |
32 |
32768 |
False |
2,088 ± 352 / 706 ± 214 |
2.81 |
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 |
12.5.2 |
12.2.0 |
12.3.1 |
12.4.0 |
12.4.0 |
12.3.1 |
12.3.1 |
Rijgersberg/GEITje-7B-chat (few-shot) |
7242 |
32 |
32768 |
False |
5,920 ± 1,028 / 1,696 ± 550 |
2.88 |
50.69 ± 1.67 / 35.96 ± 2.63 |
8.16 ± 1.68 / 27.37 ± 1.95 |
20.45 ± 2.12 / 59.00 ± 1.21 |
54.48 ± 0.86 / 66.71 ± 0.59 |
66.92 ± 0.50 / 20.19 ± 0.69 |
24.89 ± 1.55 / 42.34 ± 1.14 |
9.84 ± 1.87 / 30.90 ± 1.58 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
Rijgersberg/GEITje-7B (few-shot) |
7242 |
32 |
32768 |
True |
10,401 ± 2,529 / 2,123 ± 690 |
2.91 |
47.53 ± 1.90 / 32.42 ± 1.99 |
4.36 ± 2.96 / 28.11 ± 4.71 |
30.67 ± 4.45 / 63.78 ± 2.80 |
56.55 ± 0.70 / 67.56 ± 0.60 |
67.58 ± 0.85 / 22.14 ± 1.21 |
28.12 ± 0.98 / 44.50 ± 0.93 |
11.70 ± 2.42 / 32.05 ± 1.90 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
occiglot/occiglot-7b-eu5 (few-shot) |
7242 |
32 |
32768 |
True |
2,219 ± 427 / 717 ± 224 |
2.91 |
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 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.2.0 |
12.2.0 |
Qwen/Qwen1.5-4B-Chat (few-shot) |
3950 |
152 |
32768 |
False |
4,347 ± 893 / 1,135 ± 365 |
2.93 |
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 |
12.5.2 |
10.0.1 |
12.1.0 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
mistralai/Mistral-7B-Instruct-v0.1 (few-shot) |
7242 |
32 |
32768 |
False |
5,443 ± 1,273 / 1,144 ± 364 |
2.95 |
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 |
9.3.1 |
9.3.1 |
9.3.1 |
12.4.0 |
12.4.0 |
9.3.1 |
9.3.1 |
meta-llama/Llama-2-7b-chat-hf (few-shot) |
6738 |
32 |
4096 |
False |
2,643 ± 455 / 800 ± 247 |
2.97 |
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 |
9.3.1 |
9.3.1 |
9.3.1 |
12.4.0 |
12.4.0 |
9.3.1 |
9.3.1 |
BramVanroy/GEITje-7B-ultra-sft (few-shot) |
7242 |
32 |
8192 |
False |
5,979 ± 1,044 / 1,724 ± 559 |
3.02 |
39.41 ± 2.93 / 30.59 ± 1.59 |
7.00 ± 3.04 / 35.01 ± 3.72 |
16.10 ± 2.34 / 52.05 ± 3.60 |
53.02 ± 0.97 / 65.63 ± 0.72 |
67.74 ± 0.43 / 20.32 ± 0.57 |
25.80 ± 0.75 / 42.85 ± 0.76 |
12.49 ± 2.15 / 33.04 ± 2.08 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
timpal0l/Mistral-7B-v0.1-flashback-v2 (few-shot) |
7242 |
32 |
32768 |
True |
5,054 ± 1,200 / 1,056 ± 339 |
3.04 |
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 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
01-ai/Yi-6B (few-shot) |
6061 |
64 |
4096 |
True |
2,786 ± 532 / 784 ± 250 |
3.09 |
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 |
9.3.2 |
10.0.0 |
10.0.0 |
12.5.1 |
12.0.0 |
10.0.1 |
10.0.1 |
meta-llama/Llama-2-7b-hf (few-shot) |
6738 |
32 |
4096 |
True |
2,648 ± 467 / 799 ± 250 |
3.15 |
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 |
9.2.0 |
9.2.0 |
9.2.0 |
12.5.1 |
11.0.0 |
9.2.0 |
9.2.0 |
Qwen/Qwen1.5-4B (few-shot) |
3950 |
152 |
32768 |
True |
3,248 ± 739 / 761 ± 252 |
3.22 |
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 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
AI-Sweden-Models/gpt-sw3-20b (few-shot) |
20918 |
64 |
2048 |
True |
4,880 ± 1,052 / 1,181 ± 380 |
3.26 |
35.30 ± 3.76 / 33.68 ± 1.80 |
15.67 ± 2.21 / 31.30 ± 4.51 |
1.76 ± 2.37 / 47.60 ± 1.68 |
45.05 ± 1.68 / 55.38 ± 1.66 |
59.15 ± 1.54 / 14.60 ± 0.72 |
6.24 ± 1.54 / 29.02 ± 1.30 |
0.47 ± 1.20 / 24.89 ± 0.59 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
AI-Sweden-Models/gpt-sw3-20b-instruct (few-shot) |
20918 |
64 |
2048 |
True |
4,572 ± 1,018 / 1,068 ± 331 |
3.48 |
24.44 ± 1.62 / 25.02 ± 1.72 |
18.40 ± 2.14 / 40.21 ± 2.51 |
4.85 ± 2.01 / 49.10 ± 2.56 |
39.83 ± 1.08 / 52.69 ± 1.15 |
54.89 ± 1.27 / 13.01 ± 0.47 |
4.38 ± 1.45 / 27.07 ± 1.30 |
1.95 ± 0.83 / 24.88 ± 0.71 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
RuterNorway/Llama-2-7b-chat-norwegian (few-shot) |
unknown |
32 |
4096 |
False |
10,890 ± 2,686 / 2,186 ± 750 |
3.49 |
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 |
9.3.1 |
9.3.1 |
9.3.1 |
12.5.2 |
9.3.1 |
9.3.1 |
9.3.1 |
google/gemma-2b-it (few-shot) |
2506 |
256 |
8192 |
False |
6,471 ± 1,142 / 1,961 ± 584 |
3.51 |
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 |
12.5.2 |
12.1.0 |
12.1.0 |
12.4.0 |
12.4.0 |
12.1.0 |
12.1.0 |
google/gemma-2b (few-shot) |
2506 |
256 |
8192 |
True |
6,087 ± 1,046 / 1,902 ± 563 |
3.63 |
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 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
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 |
3.71 |
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 |
12.5.2 |
11.0.0 |
12.1.0 |
12.5.0 |
12.5.0 |
12.1.0 |
12.1.0 |
LumiOpen/Viking-13B (few-shot) |
14030 |
131 |
4224 |
True |
3,480 ± 727 / 822 ± 274 |
3.85 |
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 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
Qwen/Qwen1.5-0.5B-Chat (few-shot) |
620 |
152 |
32768 |
False |
11,740 ± 3,000 / 2,209 ± 721 |
3.86 |
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 |
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 |
3.94 |
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 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
allenai/OLMo-7B (few-shot) |
6888 |
50 |
2176 |
True |
5,403 ± 1,133 / 1,294 ± 423 |
3.94 |
37.37 ± 2.22 / 30.45 ± 2.45 |
9.55 ± 1.82 / 23.90 ± 1.53 |
0.05 ± 1.35 / 35.78 ± 2.30 |
34.81 ± 1.54 / 46.37 ± 1.51 |
45.22 ± 0.39 / 8.61 ± 0.17 |
3.92 ± 1.04 / 27.22 ± 0.63 |
0.16 ± 0.55 / 25.29 ± 0.61 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
Qwen/Qwen1.5-0.5B (few-shot) |
620 |
152 |
32768 |
True |
11,371 ± 2,924 / 2,122 ± 692 |
4.04 |
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 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
allenai/OLMo-7B-Twin-2T (few-shot) |
6888 |
50 |
2176 |
True |
5,484 ± 1,125 / 1,317 ± 425 |
4.26 |
18.70 ± 5.76 / 19.58 ± 4.59 |
3.70 ± 1.69 / 17.91 ± 1.48 |
2.19 ± 2.08 / 45.43 ± 3.44 |
38.08 ± 1.07 / 48.44 ± 1.55 |
43.79 ± 0.51 / 7.59 ± 0.20 |
0.65 ± 1.39 / 25.05 ± 1.02 |
-0.02 ± 0.92 / 24.75 ± 0.66 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
allenai/OLMo-1B (few-shot) |
1177 |
50 |
2176 |
True |
8,536 ± 1,926 / 1,940 ± 619 |
4.54 |
22.58 ± 5.05 / 26.82 ± 3.69 |
4.92 ± 2.71 / 19.51 ± 4.22 |
-1.27 ± 1.85 / 41.38 ± 3.59 |
6.64 ± 1.96 / 11.74 ± 1.62 |
43.43 ± 0.37 / 7.83 ± 0.14 |
-0.56 ± 1.27 / 24.38 ± 0.98 |
0.29 ± 1.06 / 25.10 ± 0.83 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
12.1.0 |
RJuro/kanelsnegl-v0.1 (few-shot) |
7242 |
32 |
512 |
True |
9,757 ± 2,047 / 2,200 ± 705 |
4.63 |
0.00 ± 0.00 / 0.00 ± 0.00 |
0.95 ± 1.17 / 9.87 ± 0.86 |
0.00 ± 0.00 / 33.34 ± 0.31 |
0.00 ± 0.00 / 5.43 ± 0.58 |
60.14 ± 0.15 / 10.07 ± 0.16 |
0.11 ± 0.64 / 24.32 ± 0.78 |
-0.13 ± 0.82 / 23.60 ± 0.33 |
9.3.1 |
9.3.1 |
9.3.1 |
12.5.1 |
9.3.1 |
9.3.1 |
9.3.1 |
ai-forever/mGPT (few-shot) |
unknown |
100 |
1024 |
True |
13,551 ± 4,259 / 2,563 ± 838 |
5.15 |
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 |
9.3.1 |
10.0.1 |
11.0.0 |
12.5.1 |
12.0.0 |
11.0.0 |
11.0.0 |