gpt-4-0613 (few-shot, val) |
unknown |
100 |
8191 |
True |
597 ± 197 / 93 ± 33 |
1.13 |
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 |
12.2.0 |
12.1.0 |
12.2.0 |
12.2.0 |
12.5.2 |
12.5.2 |
12.5.2 |
meta-llama/Meta-Llama-3-70B (few-shot, val) |
70554 |
128 |
8192 |
True |
312 ± 55 / 177 ± 51 |
1.25 |
79.06 ± 2.34 / 74.41 ± 2.24 |
65.53 ± 2.61 / 68.71 ± 2.08 |
46.28 ± 4.01 / 72.38 ± 2.33 |
75.20 ± 1.68 / 86.90 ± 1.14 |
69.10 ± 0.33 / 21.34 ± 0.43 |
72.64 ± 1.98 / 79.49 ± 1.48 |
77.49 ± 4.78 / 82.50 ± 3.93 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
VAGOsolutions/SauerkrautLM-7b-LaserChat (few-shot) |
7242 |
32 |
8192 |
False |
2,387 ± 456 / 717 ± 226 |
1.37 |
71.91 ± 1.16 / 62.61 ± 2.72 |
69.68 ± 0.91 / 69.92 ± 0.73 |
46.89 ± 2.30 / 72.87 ± 1.01 |
76.21 ± 1.03 / 89.02 ± 0.61 |
70.19 ± 0.35 / 27.05 ± 0.41 |
50.39 ± 1.26 / 62.73 ± 0.94 |
83.53 ± 0.67 / 87.62 ± 0.50 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
upstage/SOLAR-10.7B-v1.0 (few-shot) |
10732 |
32 |
4096 |
True |
3,780 ± 906 / 799 ± 261 |
1.38 |
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 |
Nexusflow/Starling-LM-7B-beta (few-shot) |
7242 |
32 |
8192 |
False |
5,876 ± 1,021 / 1,677 ± 546 |
1.40 |
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 |
meta-llama/Llama-2-70b-hf (few-shot, val) |
68977 |
32 |
4349 |
True |
1,892 ± 650 / 318 ± 105 |
1.47 |
72.38 ± 1.28 / 66.44 ± 1.74 |
60.98 ± 2.19 / 68.64 ± 2.17 |
43.12 ± 5.21 / 70.12 ± 2.87 |
74.50 ± 3.41 / 86.22 ± 1.70 |
71.63 ± 0.35 / 26.83 ± 0.78 |
54.29 ± 1.91 / 65.78 ± 1.33 |
74.35 ± 4.59 / 80.47 ± 3.64 |
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 |
8192 |
True |
1,673 ± 583 / 275 ± 85 |
1.47 |
81.30 ± 1.35 / 76.64 ± 1.77 |
66.18 ± 2.04 / 72.85 ± 1.27 |
38.10 ± 2.32 / 68.58 ± 1.40 |
53.31 ± 3.61 / 77.76 ± 1.59 |
70.35 ± 0.46 / 26.71 ± 0.65 |
72.39 ± 1.41 / 79.30 ± 1.05 |
83.86 ± 2.24 / 87.81 ± 1.71 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
152334H/miqu-1-70b-sf (few-shot, val) |
68977 |
32 |
33017 |
True |
2,126 ± 676 / 319 ± 104 |
1.51 |
71.83 ± 1.48 / 65.37 ± 1.62 |
62.99 ± 3.04 / 69.81 ± 1.86 |
39.97 ± 3.89 / 69.38 ± 1.87 |
64.42 ± 3.17 / 80.97 ± 1.54 |
71.27 ± 0.50 / 25.32 ± 0.64 |
64.27 ± 3.04 / 73.20 ± 2.27 |
77.60 ± 4.02 / 82.85 ± 3.10 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
VAGOsolutions/FC-SauerkrautLM-7b-beta (few-shot) |
unknown |
32 |
8192 |
False |
2,160 ± 514 / 668 ± 256 |
1.51 |
70.15 ± 0.85 / 60.29 ± 2.28 |
69.36 ± 0.87 / 67.37 ± 0.89 |
37.09 ± 2.04 / 68.05 ± 1.30 |
77.39 ± 1.14 / 89.74 ± 0.41 |
69.72 ± 0.17 / 25.82 ± 0.35 |
50.10 ± 1.05 / 62.63 ± 0.79 |
77.27 ± 0.64 / 82.91 ± 0.49 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
gpt-3.5-turbo-0613 (few-shot, val) |
unknown |
100 |
4095 |
True |
921 ± 293 / 113 ± 37 |
1.64 |
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 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
0.0.0 |
VAGOsolutions/SauerkrautLM-7b-HerO (few-shot, val) |
7242 |
32 |
32768 |
False |
2,477 ± 467 / 744 ± 232 |
1.75 |
69.26 ± 2.17 / 57.48 ± 2.92 |
68.63 ± 2.65 / 73.31 ± 1.74 |
29.87 ± 3.02 / 63.64 ± 1.60 |
60.92 ± 2.44 / 80.40 ± 1.26 |
70.20 ± 0.33 / 26.15 ± 0.51 |
49.51 ± 2.34 / 61.84 ± 1.70 |
71.47 ± 2.32 / 78.36 ± 1.73 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
meta-llama/Llama-2-70b-chat-hf (few-shot, val) |
68977 |
32 |
4096 |
True |
1,979 ± 621 / 320 ± 105 |
1.80 |
72.80 ± 1.65 / 64.88 ± 3.12 |
63.76 ± 2.53 / 71.14 ± 1.90 |
28.37 ± 4.76 / 62.85 ± 3.04 |
64.70 ± 2.69 / 81.80 ± 1.41 |
71.04 ± 0.42 / 25.68 ± 0.52 |
47.00 ± 2.21 / 60.12 ± 1.58 |
61.56 ± 2.97 / 70.27 ± 2.27 |
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-3-8B-Instruct (few-shot) |
8030 |
128 |
8192 |
True |
4,909 ± 1,215 / 978 ± 319 |
1.82 |
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 |
cstr/Spaetzle-v8-7b (few-shot, val) |
7242 |
32 |
32768 |
False |
5,980 ± 1,031 / 1,714 ± 552 |
1.83 |
69.40 ± 1.47 / 54.63 ± 3.27 |
65.39 ± 2.32 / 73.11 ± 1.62 |
26.69 ± 3.88 / 62.82 ± 2.19 |
49.74 ± 2.61 / 75.27 ± 0.99 |
71.02 ± 0.71 / 25.90 ± 1.04 |
52.23 ± 1.23 / 63.71 ± 0.98 |
74.61 ± 2.55 / 80.66 ± 1.88 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
mlabonne/NeuralBeagle14-7B (few-shot, val) |
7242 |
32 |
8192 |
False |
2,549 ± 472 / 784 ± 245 |
1.83 |
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 |
9.3.2 |
9.3.2 |
9.3.2 |
robinsmits/Qwen1.5-7B-Dutch-Chat-Sft-Bf16 (few-shot) |
7719 |
152 |
32768 |
False |
2,413 ± 463 / 700 ± 220 |
1.84 |
67.52 ± 1.19 / 59.09 ± 2.64 |
63.10 ± 1.92 / 70.11 ± 0.80 |
37.75 ± 2.52 / 67.53 ± 1.75 |
64.88 ± 1.60 / 82.23 ± 0.72 |
68.45 ± 0.22 / 21.67 ± 0.52 |
47.66 ± 0.96 / 60.75 ± 0.72 |
63.35 ± 1.62 / 72.16 ± 1.31 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
senseable/WestLake-7B-v2 (few-shot) |
7242 |
32 |
32768 |
False |
5,993 ± 1,028 / 1,742 ± 561 |
1.87 |
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 |
meta-llama/Meta-Llama-3-8B (few-shot) |
8030 |
128 |
8192 |
True |
4,687 ± 1,121 / 967 ± 313 |
1.89 |
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 |
mistralai/Mistral-7B-v0.1 (few-shot) |
7242 |
32 |
32768 |
True |
2,657 ± 524 / 880 ± 278 |
1.89 |
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 |
9.1.2 |
9.1.2 |
9.1.2 |
12.5.1 |
11.0.0 |
9.2.0 |
9.2.0 |
alpindale/Mistral-7B-v0.2-hf (few-shot) |
7242 |
32 |
32768 |
True |
1,841 ± 297 / 651 ± 193 |
1.92 |
61.02 ± 2.70 / 55.57 ± 2.50 |
67.10 ± 0.81 / 70.66 ± 0.76 |
29.82 ± 5.18 / 62.86 ± 4.72 |
73.50 ± 1.67 / 84.26 ± 1.30 |
69.02 ± 0.55 / 23.87 ± 0.72 |
47.13 ± 1.24 / 60.08 ± 0.92 |
35.88 ± 4.42 / 49.95 ± 3.87 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
01-ai/Yi-6B (few-shot) |
6061 |
64 |
4096 |
True |
2,786 ± 532 / 784 ± 250 |
1.93 |
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 |
12.0.0 |
10.0.1 |
10.0.1 |
occiglot/occiglot-7b-de-en-instruct (few-shot) |
7242 |
32 |
32768 |
False |
1,584 ± 217 / 635 ± 178 |
1.98 |
60.90 ± 3.17 / 53.69 ± 2.67 |
66.54 ± 1.42 / 69.26 ± 0.83 |
23.60 ± 3.72 / 57.65 ± 4.08 |
75.14 ± 1.51 / 87.25 ± 0.61 |
68.96 ± 0.53 / 25.60 ± 0.80 |
42.53 ± 0.85 / 56.25 ± 0.72 |
41.79 ± 3.18 / 54.82 ± 2.83 |
12.5.2 |
12.3.1 |
12.3.1 |
12.4.0 |
12.4.0 |
12.3.1 |
12.3.1 |
mlabonne/AlphaMonarch-7B (few-shot, val) |
7242 |
32 |
8192 |
False |
5,340 ± 1,262 / 1,157 ± 375 |
1.99 |
69.19 ± 2.03 / 55.64 ± 3.53 |
63.77 ± 2.55 / 71.13 ± 1.83 |
28.43 ± 3.97 / 62.28 ± 1.86 |
44.39 ± 2.68 / 71.79 ± 1.25 |
69.77 ± 0.76 / 24.60 ± 1.13 |
46.53 ± 2.54 / 59.53 ± 1.87 |
71.36 ± 3.95 / 78.36 ± 2.91 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
Qwen/Qwen1.5-4B (few-shot) |
3950 |
152 |
32768 |
True |
3,248 ± 739 / 761 ± 252 |
2.08 |
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 |
12.1.0 |
12.1.0 |
12.1.0 |
occiglot/occiglot-7b-de-en (few-shot) |
7242 |
32 |
32768 |
True |
1,992 ± 319 / 706 ± 211 |
2.08 |
56.07 ± 4.01 / 51.66 ± 3.99 |
65.29 ± 1.43 / 69.38 ± 0.73 |
25.78 ± 2.57 / 61.50 ± 2.24 |
73.13 ± 4.05 / 83.85 ± 2.69 |
68.76 ± 0.54 / 23.14 ± 0.51 |
41.47 ± 0.94 / 55.81 ± 0.77 |
32.75 ± 3.47 / 48.17 ± 2.83 |
12.3.2 |
12.3.1 |
12.3.1 |
12.3.1 |
12.3.1 |
12.3.1 |
12.3.1 |
timpal0l/Mistral-7B-v0.1-flashback-v2 (few-shot) |
7242 |
32 |
32768 |
True |
5,054 ± 1,200 / 1,056 ± 339 |
2.08 |
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 |
12.5.3 |
12.5.3 |
12.5.3 |
mistralai/Mistral-7B-Instruct-v0.1 (few-shot) |
7242 |
32 |
32768 |
False |
5,443 ± 1,273 / 1,144 ± 364 |
2.09 |
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 |
12.4.0 |
9.3.1 |
9.3.1 |
Qwen/Qwen1.5-4B-Chat (few-shot) |
3950 |
152 |
32768 |
False |
4,347 ± 893 / 1,135 ± 365 |
2.11 |
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 |
12.1.0 |
12.1.0 |
12.1.0 |
RuterNorway/Llama-2-13b-chat-norwegian (few-shot) |
unknown |
32 |
4096 |
False |
7,778 ± 1,755 / 1,703 ± 552 |
2.12 |
64.93 ± 2.24 / 57.95 ± 1.24 |
64.14 ± 1.61 / 68.00 ± 1.67 |
28.08 ± 3.86 / 62.71 ± 2.98 |
62.09 ± 1.68 / 79.57 ± 0.96 |
68.84 ± 0.52 / 24.99 ± 0.80 |
36.49 ± 0.82 / 52.02 ± 0.62 |
38.09 ± 2.61 / 52.60 ± 2.19 |
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 |
2.17 |
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 |
12.4.0 |
12.3.1 |
12.3.1 |
danish-foundation-models/munin-7b-v0.1dev0 (few-shot) |
7242 |
32 |
8192 |
True |
6,113 ± 1,044 / 1,790 ± 579 |
2.18 |
56.38 ± 2.95 / 50.80 ± 2.82 |
66.04 ± 1.68 / 65.21 ± 1.48 |
22.15 ± 3.57 / 57.71 ± 4.24 |
71.32 ± 1.41 / 83.70 ± 0.93 |
68.13 ± 0.68 / 23.08 ± 0.59 |
35.47 ± 1.23 / 50.47 ± 0.94 |
29.25 ± 3.05 / 44.01 ± 2.75 |
12.5.2 |
12.5.0 |
12.5.0 |
12.5.0 |
12.5.0 |
12.5.0 |
12.5.0 |
mistralai/Mistral-7B-Instruct-v0.2 (few-shot) |
7242 |
32 |
32768 |
False |
2,538 ± 415 / 821 ± 253 |
2.19 |
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 |
9.3.1 |
9.2.0 |
9.3.1 |
12.4.0 |
12.4.0 |
9.3.2 |
9.3.2 |
meta-llama/Llama-2-7b-chat-hf (few-shot) |
6738 |
32 |
4096 |
False |
2,643 ± 455 / 800 ± 247 |
2.27 |
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 |
12.4.0 |
9.3.1 |
9.3.1 |
occiglot/occiglot-7b-eu5 (few-shot) |
7242 |
32 |
32768 |
True |
2,219 ± 427 / 717 ± 224 |
2.32 |
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 |
12.1.0 |
12.2.0 |
12.2.0 |
microsoft/phi-2 (few-shot) |
2780 |
51 |
2048 |
True |
3,472 ± 885 / 728 ± 239 |
2.36 |
49.16 ± 3.09 / 43.10 ± 2.58 |
62.41 ± 1.51 / 67.24 ± 1.18 |
12.31 ± 2.96 / 48.73 ± 5.08 |
75.79 ± 1.88 / 86.40 ± 1.10 |
67.79 ± 0.51 / 23.29 ± 0.89 |
40.15 ± 1.11 / 54.65 ± 0.86 |
23.21 ± 2.87 / 39.96 ± 2.45 |
12.5.2 |
12.2.0 |
12.0.0 |
12.0.0 |
12.0.0 |
12.0.0 |
12.0.0 |
meta-llama/Llama-2-7b-hf (few-shot) |
6738 |
32 |
4096 |
True |
2,648 ± 467 / 799 ± 250 |
2.40 |
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 |
12.0.0 |
9.2.0 |
9.2.0 |
Rijgersberg/GEITje-7B (few-shot) |
7242 |
32 |
32768 |
True |
10,401 ± 2,529 / 2,123 ± 690 |
2.48 |
53.39 ± 2.97 / 47.76 ± 2.67 |
65.21 ± 1.35 / 65.73 ± 1.61 |
12.63 ± 2.60 / 50.10 ± 3.87 |
65.74 ± 2.31 / 77.95 ± 1.84 |
68.05 ± 0.54 / 24.11 ± 0.59 |
31.65 ± 1.00 / 47.19 ± 0.83 |
17.69 ± 2.71 / 35.94 ± 2.08 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
Qwen/Qwen1.5-1.8B (few-shot) |
1837 |
152 |
32768 |
True |
5,666 ± 1,328 / 1,256 ± 408 |
2.61 |
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 |
12.1.0 |
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 |
2.75 |
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 |
12.5.0 |
12.1.0 |
12.1.0 |
AI-Sweden-Models/gpt-sw3-20b-instruct (few-shot) |
20918 |
64 |
2048 |
True |
1,831 ± 587 / 268 ± 90 |
2.77 |
39.21 ± 1.52 / 34.08 ± 1.88 |
65.58 ± 1.59 / 57.86 ± 1.13 |
7.82 ± 1.43 / 51.19 ± 1.75 |
72.25 ± 2.19 / 83.08 ± 1.30 |
64.07 ± 0.60 / 19.27 ± 0.54 |
14.98 ± 0.77 / 36.11 ± 0.75 |
13.55 ± 1.51 / 34.03 ± 1.55 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
google/gemma-2b (few-shot) |
2506 |
256 |
8192 |
True |
6,087 ± 1,046 / 1,902 ± 563 |
2.90 |
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 |
12.1.0 |
12.1.0 |
12.1.0 |
VAGOsolutions/SauerkrautLM-Gemma-2b (few-shot) |
2506 |
256 |
8192 |
False |
3,607 ± 565 / 1,212 ± 349 |
2.92 |
23.28 ± 6.45 / 21.81 ± 5.61 |
61.91 ± 2.08 / 67.80 ± 1.12 |
6.92 ± 2.36 / 44.29 ± 3.87 |
64.68 ± 1.06 / 76.60 ± 0.51 |
65.15 ± 0.86 / 20.15 ± 0.50 |
22.65 ± 0.87 / 41.40 ± 0.67 |
14.54 ± 1.87 / 34.39 ± 1.49 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
google/gemma-2b-it (few-shot) |
2506 |
256 |
8192 |
False |
6,471 ± 1,142 / 1,961 ± 584 |
2.99 |
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 |
12.4.0 |
12.1.0 |
12.1.0 |
Qwen/Qwen1.5-0.5B-Chat (few-shot) |
620 |
152 |
32768 |
False |
11,740 ± 3,000 / 2,209 ± 721 |
3.17 |
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 |
12.5.0 |
12.5.0 |
12.1.0 |
12.1.0 |
Qwen/Qwen1.5-0.5B (few-shot) |
620 |
152 |
32768 |
True |
11,371 ± 2,924 / 2,122 ± 692 |
3.19 |
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 |
12.1.0 |
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 |
3.24 |
45.86 ± 3.18 / 40.23 ± 2.41 |
62.08 ± 3.29 / 55.11 ± 1.68 |
6.62 ± 2.43 / 48.79 ± 3.77 |
65.29 ± 1.81 / 77.71 ± 0.98 |
43.45 ± 7.12 / 15.14 ± 2.47 |
9.10 ± 1.33 / 30.31 ± 0.94 |
8.35 ± 0.79 / 29.79 ± 0.76 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
LumiOpen/Viking-13B (few-shot) |
14030 |
131 |
4352 |
True |
3,480 ± 727 / 822 ± 274 |
3.28 |
47.70 ± 2.71 / 44.98 ± 2.69 |
51.87 ± 6.35 / 49.40 ± 3.66 |
0.14 ± 1.67 / 46.80 ± 2.63 |
50.83 ± 1.05 / 61.39 ± 1.03 |
63.14 ± 1.28 / 16.86 ± 0.76 |
2.16 ± 1.01 / 24.58 ± 0.54 |
0.17 ± 0.73 / 25.05 ± 0.35 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
allenai/OLMo-7B (few-shot) |
6888 |
50 |
2304 |
True |
5,403 ± 1,133 / 1,294 ± 423 |
3.40 |
38.23 ± 3.10 / 36.38 ± 2.60 |
60.70 ± 1.80 / 66.82 ± 1.12 |
-0.19 ± 2.28 / 38.77 ± 3.32 |
61.93 ± 1.98 / 73.71 ± 1.57 |
51.32 ± 0.91 / 11.96 ± 0.57 |
5.00 ± 1.53 / 27.59 ± 1.14 |
1.10 ± 1.02 / 25.71 ± 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-7B-Twin-2T (few-shot) |
6888 |
50 |
2304 |
True |
5,484 ± 1,125 / 1,317 ± 425 |
3.60 |
25.36 ± 8.05 / 24.05 ± 7.34 |
56.91 ± 2.41 / 66.15 ± 1.54 |
7.10 ± 2.89 / 49.36 ± 4.03 |
58.60 ± 5.37 / 70.37 ± 4.71 |
46.16 ± 1.28 / 11.33 ± 0.70 |
0.71 ± 0.85 / 24.97 ± 0.62 |
0.82 ± 1.01 / 25.62 ± 0.74 |
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 |
2304 |
True |
8,536 ± 1,926 / 1,940 ± 619 |
3.79 |
26.47 ± 6.25 / 28.27 ± 5.35 |
60.05 ± 3.94 / 56.18 ± 1.90 |
0.72 ± 1.90 / 42.84 ± 3.50 |
43.87 ± 2.49 / 55.59 ± 2.44 |
46.18 ± 1.20 / 10.06 ± 0.67 |
-0.87 ± 0.99 / 23.08 ± 0.63 |
0.20 ± 1.12 / 24.94 ± 0.86 |
12.5.2 |
12.1.0 |
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 |
3.97 |
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 |
9.3.1 |
9.3.1 |
9.3.1 |
RJuro/kanelsnegl-v0.1 (few-shot) |
7242 |
32 |
512 |
True |
9,757 ± 2,047 / 2,200 ± 705 |
4.75 |
0.00 ± 0.00 / 0.00 ± 0.00 |
0.00 ± 0.00 / 19.61 ± 0.22 |
0.41 ± 0.55 / 33.46 ± 0.37 |
0.00 ± 0.00 / 3.68 ± 0.43 |
61.26 ± 0.09 / 6.73 ± 0.06 |
0.00 ± 0.00 / 22.69 ± 0.63 |
0.36 ± 0.47 / 24.60 ± 0.43 |
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 |
5.17 |
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 |
12.0.0 |
11.0.0 |
11.0.0 |