gpt-4-0613 (few-shot, val) |
unknown |
100 |
8191 |
True |
597 ± 197 / 93 ± 33 |
1.18 |
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 |
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 |
gpt-4-1106-preview (few-shot, val) |
unknown |
100 |
128000 |
True |
576 ± 221 / 81 ± 28 |
1.31 |
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 |
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 |
gpt-4o-2024-05-13 (few-shot, val) |
unknown |
200 |
128000 |
True |
916 ± 329 / 114 ± 38 |
1.34 |
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 |
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 |
meta-llama/Meta-Llama-3-70B (few-shot, val) |
70554 |
128 |
8192 |
True |
312 ± 55 / 177 ± 51 |
1.44 |
75.31 ± 3.84 / 64.90 ± 4.05 |
75.94 ± 4.62 / 62.81 ± 5.25 |
66.74 ± 4.50 / 74.89 ± 3.69 |
65.78 ± 1.11 / 20.46 ± 1.79 |
59.82 ± 3.52 / 79.17 ± 2.10 |
47.56 ± 3.52 / 71.91 ± 1.79 |
60.87 ± 4.82 / 82.30 ± 2.52 |
62.45 ± 1.70 / 71.60 ± 1.37 |
65.29 ± 3.59 / 72.50 ± 3.24 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
google/gemma-2-27b-it (few-shot) |
27227 |
256 |
8193 |
False |
1,516 ± 257 / 480 ± 148 |
1.60 |
67.35 ± 2.33 / 56.75 ± 3.04 |
66.61 ± 1.81 / 57.24 ± 4.35 |
67.14 ± 1.22 / 78.63 ± 0.96 |
66.24 ± 0.95 / 20.99 ± 0.81 |
64.66 ± 1.38 / 81.94 ± 0.79 |
52.49 ± 2.01 / 75.95 ± 1.15 |
44.85 ± 2.17 / 73.41 ± 1.61 |
58.34 ± 1.14 / 68.54 ± 0.88 |
70.87 ± 2.22 / 77.92 ± 1.72 |
13.0.0 |
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-3-70B-Instruct (few-shot, val) |
70554 |
128 |
8192 |
True |
1,673 ± 583 / 275 ± 85 |
1.86 |
80.50 ± 2.85 / 76.71 ± 2.48 |
76.47 ± 3.13 / 73.94 ± 2.95 |
59.29 ± 5.92 / 69.99 ± 4.80 |
65.70 ± 0.63 / 19.36 ± 0.99 |
47.28 ± 3.57 / 69.23 ± 3.04 |
32.76 ± 3.80 / 60.66 ± 3.10 |
39.71 ± 2.59 / 71.60 ± 1.57 |
63.58 ± 1.91 / 72.58 ± 1.42 |
63.41 ± 2.52 / 71.91 ± 1.89 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
abhishek/autotrain-llama3-oh-sft-v0-2 (few-shot) |
70554 |
128 |
8192 |
False |
2,668 ± 802 / 411 ± 135 |
1.87 |
80.97 ± 1.73 / 74.56 ± 3.82 |
79.69 ± 0.64 / 75.12 ± 2.70 |
63.91 ± 1.74 / 75.51 ± 1.63 |
65.47 ± 0.63 / 18.47 ± 1.15 |
39.82 ± 3.91 / 60.91 ± 4.26 |
26.86 ± 2.91 / 53.05 ± 3.88 |
47.06 ± 3.13 / 75.80 ± 2.01 |
60.88 ± 0.68 / 70.60 ± 0.54 |
57.46 ± 3.09 / 66.74 ± 2.82 |
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 |
google/gemma-2-9b-it (few-shot) |
9242 |
256 |
8193 |
False |
2,062 ± 397 / 589 ± 178 |
1.87 |
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 |
13.0.0 |
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-2-27b (few-shot) |
27227 |
256 |
8193 |
True |
1,531 ± 264 / 489 ± 149 |
1.92 |
42.58 ± 1.77 / 43.06 ± 1.89 |
40.43 ± 0.91 / 40.42 ± 1.46 |
64.15 ± 2.03 / 76.14 ± 1.68 |
66.84 ± 1.04 / 22.18 ± 1.49 |
51.59 ± 5.86 / 72.57 ± 4.90 |
42.41 ± 3.62 / 68.76 ± 3.06 |
58.55 ± 6.45 / 80.21 ± 4.49 |
57.29 ± 0.87 / 67.76 ± 0.69 |
53.73 ± 5.15 / 63.55 ± 4.76 |
13.0.0 |
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 |
4095 |
True |
921 ± 293 / 113 ± 37 |
2.00 |
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 |
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 |
google/gemma-2-9b (few-shot) |
9242 |
256 |
8193 |
True |
2,038 ± 406 / 566 ± 172 |
2.01 |
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 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
152334H/miqu-1-70b-sf (few-shot, val) |
68977 |
32 |
32764 |
True |
2,126 ± 676 / 319 ± 104 |
2.13 |
66.75 ± 2.07 / 58.61 ± 3.33 |
66.81 ± 2.57 / 57.71 ± 3.04 |
60.58 ± 4.96 / 70.33 ± 4.12 |
64.64 ± 0.63 / 16.59 ± 1.15 |
47.53 ± 4.07 / 72.24 ± 2.31 |
17.14 ± 4.72 / 51.14 ± 4.36 |
41.92 ± 3.36 / 72.51 ± 1.91 |
51.01 ± 2.61 / 63.20 ± 1.96 |
58.23 ± 5.79 / 67.46 ± 4.92 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
gpt-4o-mini-2024-07-18 (few-shot) |
unknown |
200 |
128000 |
True |
1,171 ± 378 / 120 ± 39 |
2.18 |
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 |
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 |
meta-llama/Llama-2-70b-hf (few-shot, val) |
68977 |
32 |
4096 |
True |
1,892 ± 650 / 318 ± 105 |
2.22 |
62.46 ± 4.62 / 60.77 ± 4.36 |
64.68 ± 3.04 / 61.69 ± 2.31 |
59.68 ± 3.30 / 70.62 ± 3.08 |
66.09 ± 1.05 / 21.12 ± 1.52 |
27.34 ± 12.20 / 50.42 ± 9.24 |
3.95 ± 4.66 / 36.08 ± 3.27 |
57.44 ± 4.59 / 78.69 ± 3.09 |
43.88 ± 3.11 / 57.62 ± 2.27 |
53.85 ± 3.43 / 64.34 ± 2.65 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
timpal0l/sol (few-shot) |
10732 |
32 |
4096 |
False |
3,701 ± 876 / 771 ± 247 |
2.22 |
65.14 ± 1.62 / 52.85 ± 3.03 |
65.88 ± 1.53 / 52.89 ± 2.29 |
57.06 ± 1.54 / 71.09 ± 1.17 |
66.21 ± 0.76 / 20.29 ± 1.10 |
26.41 ± 3.80 / 51.92 ± 5.30 |
19.58 ± 1.29 / 53.93 ± 2.90 |
51.60 ± 1.97 / 77.87 ± 1.44 |
36.06 ± 0.69 / 51.47 ± 0.52 |
64.97 ± 1.25 / 73.41 ± 1.01 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
mistralai/Mistral-Nemo-Instruct-2407 (few-shot) |
12248 |
131 |
1024001 |
True |
7,095 ± 2,193 / 1,063 ± 344 |
2.26 |
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 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
upstage/SOLAR-10.7B-v1.0 (few-shot) |
10732 |
32 |
4096 |
True |
3,780 ± 906 / 799 ± 261 |
2.37 |
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 |
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 |
Nexusflow/Starling-LM-7B-beta (few-shot) |
7242 |
32 |
8192 |
False |
5,876 ± 1,021 / 1,677 ± 546 |
2.43 |
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 |
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 |
AI-Sweden-Models/Llama-3-8B-instruct (few-shot) |
8030 |
128 |
8192 |
False |
4,314 ± 1,202 / 776 ± 245 |
2.49 |
85.07 ± 0.60 / 84.47 ± 0.48 |
81.43 ± 0.59 / 79.70 ± 0.68 |
38.52 ± 2.49 / 53.36 ± 2.80 |
65.02 ± 0.45 / 16.74 ± 0.52 |
0.00 ± 0.00 / 33.41 ± 0.30 |
0.00 ± 0.00 / 33.86 ± 0.33 |
40.52 ± 2.89 / 66.67 ± 3.21 |
41.57 ± 0.66 / 55.57 ± 0.53 |
72.25 ± 0.79 / 78.88 ± 0.64 |
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 |
bineric/NorskGPT-Llama3-8b (few-shot) |
8030 |
128 |
8192 |
False |
3,695 ± 1,277 / 532 ± 183 |
2.49 |
66.94 ± 2.67 / 60.25 ± 3.14 |
67.69 ± 1.87 / 61.57 ± 2.05 |
48.40 ± 3.28 / 61.42 ± 3.56 |
65.84 ± 0.40 / 19.08 ± 0.78 |
24.26 ± 2.68 / 57.31 ± 2.64 |
18.43 ± 1.34 / 52.28 ± 2.63 |
46.80 ± 2.74 / 74.57 ± 2.20 |
33.55 ± 1.06 / 49.43 ± 0.76 |
47.32 ± 2.75 / 59.11 ± 2.44 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
meta-llama/Meta-Llama-3.1-8B-Instruct (few-shot) |
8030 |
128 |
131073 |
True |
2,411 ± 465 / 686 ± 215 |
2.50 |
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 |
13.0.0 |
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 |
2.50 |
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 |
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 |
abhishek/autotrain-llama3-orpo-v2 (few-shot) |
8030 |
128 |
8192 |
False |
8,532 ± 2,749 / 1,177 ± 399 |
2.51 |
74.62 ± 1.74 / 66.51 ± 2.71 |
74.22 ± 1.16 / 67.02 ± 2.57 |
51.30 ± 3.11 / 66.17 ± 3.21 |
63.93 ± 0.56 / 14.84 ± 0.94 |
26.03 ± 2.08 / 61.04 ± 2.00 |
19.90 ± 1.99 / 58.22 ± 1.98 |
45.31 ± 3.83 / 71.62 ± 3.39 |
33.28 ± 0.73 / 48.46 ± 0.57 |
30.60 ± 2.00 / 45.31 ± 2.06 |
12.8.0 |
12.8.0 |
12.8.0 |
12.8.0 |
12.8.0 |
12.8.0 |
12.8.0 |
12.8.0 |
12.8.0 |
birgermoell/Munin-NeuralBeagle-NorskGPT (few-shot, val) |
7242 |
32 |
32768 |
False |
2,903 ± 407 / 1,157 ± 350 |
2.51 |
63.33 ± 2.69 / 53.24 ± 3.41 |
68.84 ± 1.87 / 53.85 ± 3.78 |
58.28 ± 3.11 / 69.79 ± 2.39 |
65.94 ± 0.22 / 19.92 ± 0.44 |
18.65 ± 3.84 / 45.34 ± 2.61 |
10.72 ± 5.52 / 43.91 ± 3.48 |
44.39 ± 3.95 / 70.76 ± 3.10 |
26.61 ± 3.10 / 44.80 ± 2.38 |
46.64 ± 2.03 / 59.84 ± 1.50 |
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 |
birgermoell/WestLake-Munin-Cat-NorskGPT (few-shot, val) |
7242 |
32 |
32768 |
False |
2,856 ± 391 / 1,142 ± 342 |
2.51 |
63.33 ± 2.69 / 53.24 ± 3.41 |
68.84 ± 1.87 / 53.85 ± 3.78 |
58.28 ± 3.11 / 69.79 ± 2.39 |
65.94 ± 0.22 / 19.92 ± 0.44 |
18.65 ± 3.84 / 45.34 ± 2.61 |
10.72 ± 5.52 / 43.91 ± 3.48 |
44.39 ± 3.95 / 70.76 ± 3.10 |
26.61 ± 3.10 / 44.80 ± 2.38 |
46.64 ± 2.03 / 59.84 ± 1.50 |
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 |
bineric/NorskGPT-Mistral-7b (few-shot) |
7242 |
32 |
32768 |
False |
2,443 ± 451 / 761 ± 237 |
2.52 |
63.28 ± 1.99 / 47.72 ± 3.74 |
61.25 ± 1.05 / 45.04 ± 2.92 |
56.90 ± 1.49 / 70.81 ± 1.30 |
65.72 ± 0.39 / 19.24 ± 0.78 |
13.86 ± 1.95 / 44.84 ± 2.31 |
10.17 ± 1.89 / 46.48 ± 2.46 |
49.03 ± 4.22 / 74.38 ± 3.92 |
32.37 ± 1.15 / 49.00 ± 0.91 |
47.62 ± 1.62 / 60.59 ± 1.18 |
9.3.1 |
9.3.1 |
9.3.1 |
11.0.0 |
9.3.1 |
9.3.1 |
12.5.1 |
9.3.1 |
9.3.1 |
meta-llama/Meta-Llama-3-8B-Instruct (few-shot) |
8030 |
128 |
8192 |
True |
4,909 ± 1,215 / 978 ± 319 |
2.58 |
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 |
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 |
RJuro/munin-neuralbeagle-7b (few-shot, val) |
7242 |
32 |
32768 |
False |
2,493 ± 466 / 773 ± 243 |
2.62 |
61.18 ± 2.76 / 56.36 ± 3.30 |
65.16 ± 3.97 / 55.74 ± 4.71 |
55.61 ± 4.02 / 68.27 ± 3.49 |
65.99 ± 0.31 / 19.46 ± 0.47 |
20.84 ± 5.41 / 49.36 ± 4.98 |
9.12 ± 3.51 / 43.06 ± 3.74 |
42.92 ± 3.08 / 69.13 ± 2.85 |
27.77 ± 2.86 / 45.43 ± 2.04 |
39.67 ± 4.37 / 54.26 ± 3.37 |
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 |
four-two-labs/orpo-llama-3-swe (few-shot) |
8030 |
128 |
8192 |
False |
4,974 ± 1,208 / 1,032 ± 342 |
2.62 |
61.63 ± 1.64 / 48.09 ± 2.89 |
61.30 ± 1.94 / 50.08 ± 2.60 |
48.85 ± 2.22 / 64.93 ± 2.00 |
63.67 ± 1.11 / 16.08 ± 1.70 |
24.15 ± 6.12 / 56.29 ± 6.81 |
21.33 ± 3.03 / 58.05 ± 2.59 |
53.66 ± 4.34 / 75.19 ± 3.59 |
33.52 ± 1.36 / 49.78 ± 1.04 |
26.04 ± 2.54 / 43.74 ± 2.07 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
meta-llama/Meta-Llama-3-8B (few-shot) |
8030 |
128 |
8192 |
True |
4,687 ± 1,121 / 967 ± 313 |
2.62 |
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 |
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 |
timpal0l/BeagleCatMunin2 (few-shot, val) |
7242 |
32 |
32768 |
False |
2,477 ± 459 / 767 ± 241 |
2.62 |
61.17 ± 3.56 / 54.24 ± 3.45 |
65.44 ± 2.83 / 54.34 ± 3.95 |
58.69 ± 3.28 / 70.83 ± 2.49 |
66.08 ± 0.32 / 20.15 ± 0.64 |
15.03 ± 2.70 / 40.22 ± 1.66 |
5.95 ± 4.55 / 39.18 ± 2.91 |
42.42 ± 2.92 / 69.53 ± 3.17 |
27.31 ± 2.26 / 45.04 ± 1.66 |
41.63 ± 2.84 / 56.02 ± 2.19 |
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 |
meta-llama/Llama-2-70b-chat-hf (few-shot, val) |
68977 |
32 |
3843 |
True |
1,979 ± 621 / 320 ± 105 |
2.70 |
60.21 ± 1.86 / 47.06 ± 3.08 |
62.99 ± 2.66 / 48.82 ± 5.49 |
55.12 ± 5.10 / 66.55 ± 5.07 |
65.11 ± 0.66 / 17.82 ± 1.21 |
27.12 ± 4.90 / 54.26 ± 6.80 |
6.82 ± 5.06 / 46.18 ± 4.14 |
38.50 ± 3.93 / 69.99 ± 2.23 |
32.30 ± 3.42 / 48.32 ± 2.61 |
34.43 ± 2.91 / 49.65 ± 2.23 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
timpal0l/dolphin-2.9-llama3-8b-flashback (few-shot, val) |
8030 |
128 |
8192 |
False |
5,018 ± 1,216 / 996 ± 324 |
2.70 |
64.51 ± 3.28 / 51.06 ± 4.78 |
65.66 ± 3.82 / 53.90 ± 4.32 |
52.90 ± 4.31 / 65.38 ± 3.73 |
64.12 ± 0.39 / 15.41 ± 0.84 |
29.34 ± 4.34 / 59.36 ± 4.64 |
17.42 ± 4.38 / 52.01 ± 3.50 |
38.49 ± 4.41 / 67.16 ± 3.41 |
25.77 ± 3.46 / 43.40 ± 2.66 |
31.80 ± 2.89 / 46.80 ± 2.26 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
mlabonne/NeuralBeagle14-7B (few-shot, val) |
7242 |
32 |
8192 |
False |
2,549 ± 472 / 784 ± 245 |
2.74 |
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 |
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 |
senseable/WestLake-7B-v2 (few-shot) |
7242 |
32 |
32768 |
False |
5,993 ± 1,028 / 1,742 ± 561 |
2.74 |
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 |
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 |
birgermoell/BeagleCatMunin-Flashback-Bellman (few-shot, val) |
7242 |
32 |
32768 |
False |
2,890 ± 401 / 1,155 ± 348 |
2.77 |
53.96 ± 3.37 / 49.84 ± 3.30 |
63.45 ± 2.27 / 53.13 ± 3.43 |
52.70 ± 4.58 / 66.82 ± 3.41 |
65.23 ± 0.55 / 18.64 ± 0.86 |
14.87 ± 3.37 / 40.83 ± 1.91 |
2.48 ± 3.31 / 35.61 ± 1.83 |
41.43 ± 3.34 / 67.26 ± 2.73 |
27.42 ± 2.13 / 45.20 ± 1.58 |
36.05 ± 3.95 / 51.68 ± 2.96 |
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 |
google/gemma-7b (few-shot) |
8538 |
256 |
8067 |
True |
1,378 ± 260 / 387 ± 119 |
2.77 |
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 |
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 |
Mabeck/Heidrun-Mistral-7B-chat (few-shot) |
7242 |
32 |
32768 |
False |
5,822 ± 1,283 / 1,336 ± 430 |
2.78 |
61.41 ± 1.71 / 52.32 ± 2.63 |
59.49 ± 1.26 / 49.45 ± 3.31 |
49.19 ± 1.64 / 63.36 ± 1.52 |
64.22 ± 0.52 / 16.72 ± 0.66 |
15.17 ± 2.64 / 50.25 ± 4.51 |
10.78 ± 1.99 / 50.08 ± 4.20 |
48.99 ± 2.91 / 73.08 ± 2.26 |
27.64 ± 1.39 / 45.78 ± 1.03 |
25.74 ± 1.87 / 43.95 ± 1.58 |
10.0.1 |
10.0.1 |
10.0.1 |
12.5.0 |
10.0.1 |
10.0.1 |
12.5.0 |
10.0.1 |
10.0.1 |
timpal0l/BeagleCatMunin (few-shot, val) |
7242 |
32 |
32768 |
False |
2,495 ± 458 / 775 ± 244 |
2.80 |
54.04 ± 2.86 / 48.50 ± 2.85 |
62.21 ± 3.31 / 50.38 ± 4.32 |
54.74 ± 3.71 / 67.81 ± 2.80 |
65.60 ± 0.49 / 19.07 ± 0.70 |
14.51 ± 1.97 / 40.94 ± 1.63 |
5.38 ± 4.69 / 37.62 ± 2.92 |
42.83 ± 3.31 / 69.15 ± 2.50 |
25.82 ± 1.66 / 43.75 ± 1.18 |
32.01 ± 3.74 / 48.40 ± 2.69 |
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 |
mlabonne/AlphaMonarch-7B (few-shot, val) |
7242 |
32 |
8192 |
False |
5,340 ± 1,262 / 1,157 ± 375 |
2.82 |
61.90 ± 2.57 / 57.16 ± 2.81 |
66.92 ± 2.52 / 57.81 ± 3.54 |
48.80 ± 4.56 / 63.38 ± 3.06 |
64.72 ± 0.39 / 17.40 ± 0.60 |
19.53 ± 5.49 / 51.96 ± 4.90 |
9.83 ± 4.57 / 47.95 ± 2.22 |
30.27 ± 2.28 / 62.04 ± 2.19 |
28.18 ± 1.89 / 45.23 ± 1.44 |
36.20 ± 3.97 / 50.74 ± 3.38 |
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 |
birgermoell/Rapid-Cycling (few-shot, val) |
7242 |
32 |
32768 |
False |
2,346 ± 450 / 666 ± 249 |
2.83 |
55.93 ± 2.70 / 50.51 ± 3.15 |
63.85 ± 2.45 / 53.11 ± 4.11 |
50.41 ± 5.49 / 64.49 ± 4.37 |
65.10 ± 0.51 / 18.12 ± 0.74 |
15.74 ± 4.15 / 41.16 ± 2.21 |
2.23 ± 4.69 / 34.70 ± 1.39 |
39.81 ± 2.81 / 65.65 ± 2.64 |
26.34 ± 1.48 / 44.69 ± 1.13 |
34.85 ± 4.33 / 50.23 ± 3.39 |
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 |
birgermoell/Flashback-Bellman (few-shot, val) |
7242 |
32 |
32768 |
False |
2,887 ± 403 / 1,144 ± 345 |
2.85 |
56.44 ± 3.14 / 50.10 ± 4.61 |
66.56 ± 2.40 / 54.48 ± 4.93 |
53.24 ± 4.75 / 67.94 ± 3.75 |
64.96 ± 0.56 / 17.92 ± 0.82 |
11.96 ± 2.46 / 37.26 ± 1.15 |
2.50 ± 4.21 / 35.26 ± 1.79 |
39.21 ± 3.48 / 64.09 ± 3.49 |
26.64 ± 1.95 / 44.88 ± 1.41 |
31.14 ± 2.64 / 48.01 ± 2.14 |
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 |
danish-foundation-models/munin-7b-v0.1dev0 (few-shot) |
7242 |
32 |
8192 |
True |
6,113 ± 1,044 / 1,790 ± 579 |
2.85 |
50.43 ± 2.27 / 42.19 ± 3.03 |
54.20 ± 1.81 / 43.92 ± 2.94 |
39.21 ± 5.64 / 56.54 ± 6.43 |
65.46 ± 0.77 / 19.21 ± 1.10 |
20.51 ± 4.43 / 52.48 ± 5.96 |
11.66 ± 4.10 / 48.13 ± 6.13 |
51.57 ± 3.87 / 73.95 ± 3.51 |
28.97 ± 1.40 / 45.70 ± 1.02 |
25.41 ± 3.81 / 42.75 ± 3.44 |
12.5.2 |
12.5.2 |
12.4.0 |
12.4.0 |
12.4.0 |
12.4.0 |
12.4.0 |
12.4.0 |
12.4.0 |
timpal0l/njord-alpha (few-shot) |
7242 |
32 |
32768 |
True |
5,431 ± 1,267 / 1,139 ± 365 |
2.85 |
50.47 ± 2.96 / 43.31 ± 2.54 |
51.97 ± 3.83 / 42.66 ± 5.03 |
48.03 ± 1.71 / 65.89 ± 1.68 |
65.48 ± 1.22 / 19.57 ± 1.57 |
22.65 ± 3.80 / 51.83 ± 5.03 |
17.10 ± 4.78 / 49.03 ± 6.45 |
44.72 ± 4.47 / 68.08 ± 4.22 |
25.82 ± 0.84 / 42.08 ± 0.80 |
21.35 ± 3.32 / 37.35 ± 3.07 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
birgermoell/NeuralBeagle-Flashback (few-shot, val) |
7242 |
32 |
32768 |
False |
2,904 ± 405 / 1,155 ± 349 |
2.86 |
51.78 ± 2.90 / 47.69 ± 3.44 |
61.22 ± 3.73 / 50.00 ± 4.37 |
53.06 ± 4.92 / 67.05 ± 4.22 |
65.11 ± 0.51 / 18.04 ± 0.81 |
10.27 ± 5.84 / 43.06 ± 3.15 |
8.06 ± 3.56 / 41.59 ± 3.99 |
40.64 ± 2.58 / 66.46 ± 2.62 |
25.61 ± 2.74 / 44.49 ± 2.07 |
27.67 ± 4.55 / 44.18 ± 3.63 |
9.3.0 |
9.3.0 |
9.3.0 |
9.3.0 |
9.3.0 |
9.3.0 |
12.5.2 |
9.3.0 |
9.3.0 |
merge-crew/da-sv-dare-ties-density-0.9 (few-shot, val) |
7242 |
32 |
32768 |
True |
2,443 ± 458 / 750 ± 240 |
2.86 |
48.24 ± 3.18 / 42.53 ± 3.52 |
61.50 ± 1.54 / 50.90 ± 4.58 |
49.40 ± 3.40 / 60.71 ± 3.33 |
64.56 ± 0.80 / 17.62 ± 1.06 |
24.12 ± 3.24 / 59.38 ± 2.25 |
13.20 ± 3.16 / 54.42 ± 3.04 |
47.93 ± 3.46 / 69.52 ± 3.06 |
26.21 ± 2.32 / 42.54 ± 1.71 |
17.00 ± 2.59 / 33.52 ± 2.18 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
AI-Sweden-Models/Llama-3-8B (few-shot) |
8030 |
128 |
8192 |
True |
4,141 ± 994 / 905 ± 299 |
2.87 |
44.53 ± 2.58 / 36.59 ± 1.71 |
47.02 ± 2.08 / 39.99 ± 2.76 |
41.84 ± 2.46 / 56.79 ± 2.95 |
65.29 ± 1.50 / 19.34 ± 1.91 |
19.97 ± 3.99 / 47.40 ± 4.84 |
15.61 ± 4.20 / 43.40 ± 4.90 |
50.91 ± 4.42 / 73.43 ± 3.55 |
30.85 ± 1.15 / 46.02 ± 0.92 |
18.61 ± 3.08 / 36.62 ± 2.86 |
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 |
RJuro/munin-neuralbeagle-SkoleGPTOpenOrca-7b (few-shot, val) |
7242 |
32 |
32768 |
False |
3,008 ± 429 / 991 ± 323 |
2.87 |
53.68 ± 2.01 / 49.22 ± 2.67 |
61.92 ± 4.06 / 49.03 ± 3.97 |
47.78 ± 3.19 / 57.76 ± 2.55 |
64.23 ± 0.75 / 16.90 ± 0.94 |
0.91 ± 1.78 / 33.51 ± 0.85 |
1.24 ± 1.66 / 33.71 ± 0.94 |
47.76 ± 2.93 / 70.99 ± 2.39 |
28.59 ± 2.31 / 46.48 ± 1.80 |
42.57 ± 2.86 / 56.64 ± 2.17 |
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 |
KennethEnevoldsen/munin_mistral-7b (few-shot, val) |
7242 |
32 |
32768 |
False |
2,543 ± 466 / 787 ± 247 |
2.88 |
51.82 ± 4.16 / 44.64 ± 4.66 |
62.55 ± 3.84 / 49.66 ± 5.87 |
56.37 ± 4.27 / 69.55 ± 4.52 |
63.74 ± 1.20 / 16.64 ± 1.53 |
6.04 ± 5.92 / 36.34 ± 3.96 |
-0.02 ± 0.04 / 33.47 ± 0.88 |
48.85 ± 4.11 / 70.75 ± 3.73 |
28.43 ± 2.75 / 45.94 ± 2.14 |
20.49 ± 3.69 / 40.00 ± 2.80 |
12.5.2 |
12.5.2 |
12.3.1 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
merge-crew/da-sv-slerp (few-shot, val) |
7242 |
32 |
32768 |
True |
2,467 ± 469 / 762 ± 244 |
2.89 |
49.67 ± 3.12 / 43.26 ± 3.03 |
61.11 ± 1.93 / 50.15 ± 4.14 |
56.07 ± 5.22 / 68.93 ± 4.07 |
64.97 ± 0.59 / 18.14 ± 1.03 |
3.81 ± 3.09 / 34.47 ± 1.22 |
-1.29 ± 2.53 / 33.32 ± 0.91 |
44.98 ± 4.12 / 68.18 ± 3.39 |
28.63 ± 2.26 / 45.94 ± 1.79 |
25.43 ± 4.85 / 43.48 ± 3.71 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
merge-crew/da-sv-task-arithmetic (few-shot, val) |
7242 |
32 |
32768 |
True |
2,500 ± 469 / 762 ± 238 |
2.90 |
49.69 ± 2.90 / 43.57 ± 2.90 |
61.78 ± 2.03 / 49.91 ± 4.24 |
55.87 ± 5.21 / 68.97 ± 3.95 |
64.94 ± 0.66 / 18.09 ± 1.08 |
2.99 ± 3.04 / 34.16 ± 1.10 |
-1.29 ± 2.53 / 33.32 ± 0.91 |
44.62 ± 4.06 / 68.17 ± 3.48 |
28.26 ± 2.85 / 45.78 ± 2.14 |
25.83 ± 5.55 / 43.63 ± 4.29 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
bineric/NorskGPT-Llama-13B-v0.1 (few-shot) |
13016 |
32 |
4096 |
False |
2,856 ± 645 / 709 ± 243 |
2.91 |
56.72 ± 1.90 / 43.75 ± 2.72 |
57.62 ± 1.35 / 43.81 ± 2.43 |
48.86 ± 2.54 / 64.32 ± 2.46 |
64.86 ± 0.32 / 16.84 ± 0.69 |
9.87 ± 1.78 / 44.29 ± 3.62 |
6.90 ± 1.65 / 48.96 ± 3.09 |
41.27 ± 3.42 / 69.36 ± 3.54 |
24.51 ± 1.23 / 42.96 ± 0.98 |
31.41 ± 1.81 / 47.68 ± 1.36 |
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 |
merge-crew/da-sv-ties (few-shot, val) |
7242 |
32 |
32768 |
True |
2,457 ± 451 / 757 ± 237 |
2.94 |
47.61 ± 2.50 / 42.16 ± 2.82 |
60.57 ± 2.02 / 48.89 ± 4.48 |
44.46 ± 4.10 / 52.31 ± 4.53 |
64.59 ± 0.86 / 17.61 ± 1.09 |
23.99 ± 5.54 / 60.60 ± 2.74 |
11.60 ± 3.18 / 53.40 ± 2.75 |
47.02 ± 3.37 / 69.07 ± 2.64 |
27.13 ± 1.80 / 42.23 ± 1.12 |
15.65 ± 2.90 / 31.76 ± 2.07 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
AI-Sweden-Models/tyr (few-shot, val) |
7242 |
32 |
32768 |
False |
6,079 ± 1,051 / 1,760 ± 570 |
2.99 |
58.60 ± 4.42 / 52.72 ± 4.93 |
63.15 ± 2.29 / 54.03 ± 4.33 |
51.85 ± 3.51 / 64.28 ± 2.54 |
64.57 ± 0.59 / 17.58 ± 0.98 |
0.66 ± 1.29 / 33.42 ± 0.80 |
0.53 ± 1.05 / 33.42 ± 0.73 |
43.22 ± 2.24 / 68.55 ± 2.42 |
26.09 ± 2.24 / 44.41 ± 1.68 |
23.43 ± 2.86 / 42.30 ± 2.29 |
12.5.2 |
12.5.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
bineric/NorskGPT-Llama-7B-v0.1 (few-shot) |
6738 |
32 |
4096 |
False |
5,384 ± 879 / 1,746 ± 553 |
3.00 |
56.18 ± 3.05 / 49.39 ± 2.78 |
56.96 ± 1.64 / 48.30 ± 5.46 |
50.94 ± 1.41 / 66.55 ± 1.06 |
64.21 ± 0.23 / 15.54 ± 0.49 |
8.19 ± 1.95 / 45.17 ± 3.69 |
5.55 ± 1.71 / 48.92 ± 2.94 |
41.35 ± 2.33 / 69.72 ± 2.52 |
21.27 ± 1.03 / 40.69 ± 0.82 |
26.81 ± 1.72 / 44.27 ± 1.46 |
12.5.2 |
12.5.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
merge-crew/da-sv-dare-ties-density-0.6 (few-shot, val) |
7242 |
32 |
32768 |
True |
2,515 ± 465 / 785 ± 247 |
3.00 |
47.26 ± 3.76 / 40.22 ± 3.43 |
59.35 ± 2.82 / 45.26 ± 3.91 |
54.93 ± 3.49 / 68.45 ± 2.61 |
64.25 ± 0.86 / 16.92 ± 1.27 |
9.00 ± 2.87 / 37.53 ± 2.91 |
5.26 ± 3.15 / 39.01 ± 3.54 |
45.95 ± 3.12 / 68.00 ± 3.07 |
21.89 ± 2.60 / 39.61 ± 2.11 |
15.32 ± 3.65 / 34.57 ± 2.40 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
timpal0l/Llama-3-8B-flashback-v1 (few-shot) |
8030 |
128 |
8192 |
True |
4,807 ± 1,152 / 979 ± 319 |
3.01 |
59.09 ± 1.89 / 52.82 ± 2.60 |
60.02 ± 1.44 / 52.04 ± 2.63 |
47.58 ± 1.91 / 64.35 ± 1.95 |
58.88 ± 1.42 / 10.65 ± 1.13 |
10.52 ± 4.67 / 46.13 ± 6.95 |
6.67 ± 4.53 / 40.61 ± 5.40 |
49.89 ± 4.89 / 71.90 ± 4.09 |
29.17 ± 1.09 / 46.02 ± 0.72 |
17.46 ± 1.74 / 36.36 ± 1.79 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
timpal0l/Mistral-7B-v0.1-flashback-v2 (few-shot) |
7242 |
32 |
32768 |
True |
5,054 ± 1,200 / 1,056 ± 339 |
3.01 |
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 |
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 |
ThatsGroes/munin-SkoleGPTOpenOrca-7b-16bit (few-shot) |
7242 |
32 |
32768 |
False |
3,006 ± 479 / 1,053 ± 319 |
3.02 |
51.99 ± 1.85 / 37.40 ± 2.95 |
52.74 ± 1.13 / 36.83 ± 1.95 |
50.39 ± 1.38 / 66.42 ± 1.20 |
64.20 ± 0.44 / 16.28 ± 0.55 |
0.99 ± 1.03 / 33.56 ± 0.25 |
1.27 ± 1.30 / 34.04 ± 0.45 |
47.95 ± 3.19 / 72.60 ± 2.57 |
25.74 ± 0.98 / 43.89 ± 0.69 |
26.36 ± 1.73 / 44.31 ± 1.40 |
11.0.0 |
11.0.0 |
11.0.0 |
12.4.0 |
11.0.0 |
11.0.0 |
12.4.0 |
11.0.0 |
11.0.0 |
mhenrichsen/hestenettetLM (few-shot) |
7242 |
32 |
32768 |
True |
5,160 ± 804 / 1,654 ± 516 |
3.02 |
52.52 ± 1.85 / 43.46 ± 2.21 |
55.60 ± 3.22 / 45.25 ± 4.20 |
48.23 ± 3.31 / 65.51 ± 3.01 |
63.53 ± 1.47 / 16.54 ± 1.59 |
8.53 ± 3.72 / 38.61 ± 3.22 |
6.65 ± 1.40 / 39.32 ± 2.51 |
46.89 ± 3.29 / 70.96 ± 2.84 |
27.67 ± 0.91 / 45.77 ± 0.66 |
14.20 ± 3.45 / 34.89 ± 2.57 |
12.5.2 |
12.5.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
mistralai/Mistral-7B-v0.1 (few-shot) |
7242 |
32 |
32768 |
True |
2,657 ± 524 / 880 ± 278 |
3.04 |
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 |
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 |
meta-llama/Llama-2-13b-chat-hf (few-shot) |
13016 |
32 |
4096 |
True |
2,849 ± 622 / 723 ± 229 |
3.05 |
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 |
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 |
alpindale/Mistral-7B-v0.2-hf (few-shot) |
7242 |
32 |
32768 |
True |
1,841 ± 297 / 651 ± 193 |
3.06 |
50.63 ± 2.12 / 44.59 ± 1.80 |
52.69 ± 2.30 / 46.51 ± 3.63 |
44.05 ± 2.51 / 61.80 ± 2.28 |
63.11 ± 1.66 / 16.14 ± 1.73 |
11.60 ± 4.10 / 43.01 ± 5.07 |
9.26 ± 1.14 / 46.28 ± 3.60 |
45.23 ± 3.73 / 68.68 ± 3.29 |
28.19 ± 0.84 / 45.83 ± 0.68 |
13.65 ± 2.51 / 34.00 ± 1.87 |
12.5.2 |
12.5.2 |
12.5.1 |
12.5.1 |
12.5.1 |
12.5.1 |
12.5.1 |
12.5.1 |
12.5.1 |
mistralai/Mistral-7B-v0.3 (few-shot) |
7248 |
33 |
32768 |
True |
4,120 ± 976 / 926 ± 306 |
3.06 |
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 |
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 |
RuterNorway/Llama-2-13b-chat-norwegian (few-shot) |
unknown |
32 |
4096 |
False |
3,254 ± 1,068 / 484 ± 173 |
3.07 |
58.61 ± 1.58 / 47.74 ± 2.83 |
60.40 ± 1.25 / 47.53 ± 2.68 |
41.36 ± 3.50 / 58.47 ± 3.79 |
65.33 ± 0.44 / 18.70 ± 0.55 |
6.52 ± 2.11 / 38.10 ± 2.56 |
3.95 ± 2.52 / 42.37 ± 4.20 |
38.93 ± 2.43 / 65.76 ± 3.07 |
23.32 ± 0.89 / 42.01 ± 0.76 |
22.30 ± 1.43 / 41.29 ± 1.19 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
google/gemma-2-2b-it (few-shot) |
2614 |
256 |
8193 |
False |
6,789 ± 2,167 / 981 ± 327 |
3.12 |
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 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
Mabeck/Heidrun-Mistral-7B-base (few-shot) |
7242 |
32 |
32768 |
True |
3,823 ± 967 / 860 ± 280 |
3.14 |
50.10 ± 2.16 / 41.80 ± 2.77 |
54.81 ± 1.88 / 45.95 ± 3.21 |
48.64 ± 2.14 / 66.06 ± 1.47 |
62.29 ± 1.37 / 14.65 ± 1.36 |
10.31 ± 3.46 / 43.68 ± 5.10 |
1.11 ± 2.48 / 36.52 ± 2.31 |
42.20 ± 3.02 / 65.18 ± 2.86 |
27.39 ± 0.85 / 45.60 ± 0.64 |
11.76 ± 2.46 / 32.87 ± 2.13 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
mistralai/Mistral-7B-Instruct-v0.2 (few-shot) |
7242 |
32 |
32768 |
False |
634 ± 179 / 110 ± 35 |
3.14 |
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 |
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 |
google/gemma-7b-it (few-shot) |
8538 |
256 |
8192 |
False |
1,792 ± 249 / 668 ± 203 |
3.17 |
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 |
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 |
occiglot/occiglot-7b-eu5-instruct (few-shot) |
7242 |
32 |
32768 |
False |
2,088 ± 352 / 706 ± 214 |
3.17 |
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 |
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 |
meta-llama/Llama-2-13b-hf (few-shot) |
13016 |
32 |
4096 |
True |
2,898 ± 637 / 736 ± 236 |
3.19 |
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 |
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 |
mistralai/Mistral-7B-Instruct-v0.1 (few-shot) |
7242 |
32 |
32768 |
False |
634 ± 179 / 110 ± 35 |
3.20 |
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 |
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 |
occiglot/occiglot-7b-eu5 (few-shot) |
7242 |
32 |
32768 |
True |
2,219 ± 427 / 717 ± 224 |
3.26 |
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 |
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 |
danish-foundation-models/munin-7b-alpha (few-shot) |
7242 |
32 |
32768 |
True |
6,116 ± 1,049 / 1,784 ± 577 |
3.28 |
48.89 ± 3.42 / 35.46 ± 2.58 |
51.95 ± 1.59 / 36.45 ± 2.57 |
20.54 ± 6.01 / 36.30 ± 6.77 |
63.67 ± 1.16 / 15.98 ± 1.26 |
4.39 ± 3.94 / 35.23 ± 2.81 |
1.20 ± 1.64 / 34.54 ± 1.31 |
47.16 ± 4.15 / 70.08 ± 3.96 |
29.07 ± 1.15 / 46.18 ± 0.96 |
19.15 ± 4.16 / 38.37 ± 3.10 |
12.5.2 |
12.5.2 |
12.4.0 |
12.4.0 |
12.4.0 |
12.4.0 |
12.4.0 |
12.4.0 |
12.4.0 |
meta-llama/Llama-3.2-3B (few-shot) |
3213 |
128 |
131073 |
True |
3,713 ± 877 / 836 ± 267 |
3.28 |
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 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
ibm-granite/granite-8b-code-base-4k (few-shot) |
8055 |
49 |
4096 |
True |
2,313 ± 423 / 682 ± 210 |
3.29 |
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 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
01-ai/Yi-1.5-6B (few-shot) |
6061 |
64 |
4097 |
True |
2,867 ± 550 / 793 ± 253 |
3.32 |
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 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
01-ai/Yi-6B (few-shot) |
6061 |
64 |
4096 |
True |
6,435 ± 1,316 / 1,632 ± 549 |
3.32 |
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 |
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 |
meta-llama/Llama-3.2-3B-Instruct (few-shot) |
3213 |
128 |
131073 |
False |
3,602 ± 855 / 779 ± 245 |
3.33 |
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 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
neph1/bellman-7b-mistral-instruct-v0.2 (few-shot) |
7242 |
32 |
32768 |
False |
2,518 ± 463 / 779 ± 243 |
3.33 |
57.01 ± 1.93 / 44.65 ± 2.87 |
56.77 ± 0.98 / 41.67 ± 3.53 |
38.81 ± 2.67 / 56.39 ± 3.13 |
62.13 ± 0.30 / 12.18 ± 0.45 |
14.16 ± 2.24 / 54.43 ± 2.61 |
9.29 ± 2.65 / 50.59 ± 3.99 |
32.75 ± 1.68 / 59.21 ± 2.11 |
17.08 ± 1.29 / 37.00 ± 1.04 |
10.52 ± 2.25 / 31.85 ± 1.79 |
9.2.0 |
9.2.0 |
9.2.0 |
12.4.0 |
9.2.0 |
9.2.0 |
12.4.0 |
9.2.0 |
9.2.0 |
meta-llama/Llama-2-7b-chat-hf (few-shot) |
6738 |
32 |
4096 |
False |
2,643 ± 455 / 800 ± 247 |
3.37 |
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 |
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 |
microsoft/Phi-3-mini-4k-instruct (few-shot) |
3821 |
32 |
4096 |
True |
5,224 ± 1,371 / 1,063 ± 358 |
3.40 |
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 |
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 |
emillykkejensen/Phi-3-mini-4k-instruct-dansk (few-shot) |
3821 |
32 |
4096 |
False |
1,360 ± 179 / 566 ± 190 |
3.41 |
56.41 ± 2.05 / 37.55 ± 3.57 |
53.95 ± 1.23 / 38.44 ± 4.85 |
42.27 ± 1.52 / 56.76 ± 2.10 |
60.58 ± 0.98 / 12.77 ± 0.70 |
0.00 ± 0.00 / 33.41 ± 0.30 |
0.21 ± 1.00 / 34.08 ± 0.56 |
29.35 ± 1.40 / 53.48 ± 2.01 |
18.57 ± 0.90 / 39.13 ± 0.69 |
13.36 ± 1.66 / 34.70 ± 1.32 |
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 |
meta-llama/Llama-2-7b-hf (few-shot) |
6738 |
32 |
4096 |
True |
930 ± 310 / 128 ± 43 |
3.41 |
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 |
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 |
microsoft/Phi-3-mini-128k-instruct (few-shot) |
3821 |
32 |
130819 |
True |
7,312 ± 1,668 / 1,609 ± 525 |
3.41 |
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 |
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 |
AI-Sweden-Models/gpt-sw3-20b-instruct (few-shot) |
20918 |
64 |
2048 |
True |
1,831 ± 587 / 268 ± 90 |
3.42 |
23.95 ± 1.93 / 21.43 ± 1.89 |
26.55 ± 1.50 / 25.06 ± 1.61 |
40.89 ± 3.60 / 59.86 ± 3.59 |
65.90 ± 0.33 / 19.68 ± 0.55 |
9.45 ± 1.58 / 44.62 ± 3.29 |
8.32 ± 1.89 / 42.30 ± 2.78 |
43.19 ± 1.82 / 67.93 ± 1.55 |
7.24 ± 0.98 / 29.40 ± 0.69 |
11.76 ± 1.46 / 32.09 ± 1.66 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
Qwen/Qwen1.5-4B-Chat (few-shot) |
3950 |
152 |
32768 |
False |
4,347 ± 893 / 1,135 ± 365 |
3.42 |
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 |
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 |
NorwAI/NorwAI-Mistral-7B (few-shot) |
7537 |
68 |
4096 |
True |
3,035 ± 503 / 911 ± 300 |
3.44 |
21.09 ± 6.44 / 20.45 ± 2.65 |
26.31 ± 4.64 / 26.42 ± 2.98 |
49.00 ± 3.88 / 65.98 ± 2.95 |
63.87 ± 1.60 / 17.88 ± 1.49 |
7.15 ± 2.14 / 40.83 ± 3.95 |
7.98 ± 2.64 / 45.21 ± 4.95 |
47.70 ± 5.32 / 68.04 ± 5.37 |
5.83 ± 1.04 / 27.83 ± 1.08 |
5.39 ± 1.69 / 27.82 ± 1.56 |
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 |
merge-crew/da-sv-dare-ties-density-0.3 (few-shot, val) |
7242 |
32 |
32768 |
True |
2,461 ± 476 / 773 ± 248 |
3.49 |
35.98 ± 3.79 / 27.51 ± 2.13 |
47.39 ± 2.31 / 36.42 ± 2.87 |
38.98 ± 5.51 / 58.23 ± 4.01 |
61.99 ± 0.85 / 14.07 ± 0.75 |
11.54 ± 5.04 / 49.91 ± 3.96 |
5.20 ± 3.47 / 46.19 ± 5.23 |
37.54 ± 3.00 / 56.56 ± 2.96 |
10.40 ± 2.03 / 29.84 ± 1.34 |
2.52 ± 1.76 / 24.84 ± 1.48 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
AI-Sweden-Models/gpt-sw3-20b (few-shot) |
20918 |
64 |
2048 |
True |
1,875 ± 673 / 261 ± 91 |
3.50 |
30.82 ± 5.81 / 25.27 ± 3.92 |
39.56 ± 4.73 / 32.12 ± 4.06 |
34.50 ± 1.29 / 42.21 ± 1.39 |
63.10 ± 1.12 / 16.05 ± 1.50 |
15.17 ± 1.41 / 49.46 ± 2.90 |
12.46 ± 3.29 / 48.89 ± 5.19 |
42.81 ± 3.10 / 66.15 ± 3.21 |
4.51 ± 1.00 / 27.45 ± 0.78 |
5.27 ± 1.29 / 28.47 ± 1.11 |
9.3.1 |
9.3.1 |
12.10.0 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
norallm/normistral-7b-warm-instruct (few-shot) |
7248 |
33 |
2048 |
True |
6,194 ± 949 / 1,967 ± 619 |
3.50 |
46.49 ± 2.30 / 31.87 ± 1.92 |
51.46 ± 2.36 / 35.87 ± 2.14 |
37.98 ± 1.72 / 43.91 ± 2.51 |
64.52 ± 0.50 / 17.03 ± 1.00 |
7.86 ± 2.74 / 47.20 ± 2.71 |
7.23 ± 1.97 / 46.62 ± 3.92 |
33.31 ± 1.03 / 59.27 ± 1.53 |
5.22 ± 0.78 / 25.35 ± 0.57 |
9.32 ± 1.67 / 29.64 ± 1.49 |
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 |
tollefj/nordavind-7b-instruct-warm (few-shot) |
7248 |
33 |
2048 |
False |
6,450 ± 961 / 2,082 ± 658 |
3.52 |
38.82 ± 5.36 / 30.48 ± 1.91 |
43.28 ± 3.13 / 33.87 ± 3.30 |
38.05 ± 1.85 / 47.06 ± 3.97 |
64.04 ± 1.06 / 17.41 ± 1.19 |
8.45 ± 2.47 / 46.75 ± 3.97 |
7.50 ± 1.65 / 48.14 ± 4.65 |
40.47 ± 2.77 / 64.21 ± 2.94 |
2.60 ± 1.14 / 25.13 ± 0.64 |
3.83 ± 0.86 / 26.37 ± 0.88 |
12.5.2 |
12.5.2 |
12.3.2 |
12.4.0 |
12.3.2 |
12.3.2 |
12.4.0 |
12.3.2 |
12.3.2 |
NorwAI/NorwAI-Llama2-7B (few-shot) |
7033 |
68 |
4096 |
True |
4,438 ± 1,128 / 1,028 ± 346 |
3.54 |
31.45 ± 1.64 / 31.64 ± 1.89 |
33.85 ± 1.95 / 34.29 ± 1.91 |
36.06 ± 3.96 / 52.59 ± 4.67 |
63.06 ± 2.34 / 17.34 ± 1.88 |
8.34 ± 2.97 / 45.11 ± 4.57 |
6.84 ± 3.88 / 45.28 ± 5.45 |
48.31 ± 4.22 / 69.39 ± 4.10 |
3.28 ± 1.19 / 25.97 ± 1.25 |
1.87 ± 1.03 / 26.44 ± 0.71 |
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 |
Qwen/Qwen1.5-4B (few-shot) |
3950 |
152 |
32768 |
True |
3,248 ± 739 / 761 ± 252 |
3.55 |
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 |
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 |
allenai/OLMo-1.7-7B-hf (few-shot) |
6888 |
50 |
4096 |
True |
3,371 ± 876 / 561 ± 184 |
3.56 |
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 |
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 |
AI-Sweden-Models/gpt-sw3-6.7b-v2 (few-shot) |
7111 |
64 |
2048 |
True |
2,351 ± 448 / 707 ± 216 |
3.57 |
29.62 ± 4.17 / 24.40 ± 2.42 |
32.30 ± 5.27 / 29.23 ± 3.22 |
34.67 ± 5.23 / 54.62 ± 5.71 |
61.61 ± 2.04 / 14.34 ± 1.84 |
8.37 ± 1.71 / 48.94 ± 2.72 |
7.76 ± 2.86 / 46.16 ± 4.77 |
44.62 ± 3.31 / 67.57 ± 3.03 |
3.03 ± 1.30 / 25.60 ± 0.86 |
5.57 ± 1.19 / 27.61 ± 0.93 |
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 |
AI-Sweden-Models/gpt-sw3-40b (few-shot) |
39927 |
64 |
1795 |
True |
409 ± 53 / 182 ± 54 |
3.58 |
24.07 ± 5.59 / 19.09 ± 2.55 |
26.67 ± 6.24 / 21.18 ± 2.80 |
31.05 ± 7.03 / 45.69 ± 8.29 |
61.58 ± 2.25 / 15.13 ± 2.44 |
10.80 ± 1.96 / 52.29 ± 2.55 |
8.89 ± 2.52 / 47.62 ± 4.31 |
48.78 ± 3.64 / 71.66 ± 3.34 |
6.67 ± 1.51 / 28.84 ± 1.19 |
6.25 ± 1.29 / 29.00 ± 1.15 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.1 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.1 |
12.9.1 |
AI-Sweden-Models/gpt-sw3-6.7b-v2-instruct (few-shot) |
7111 |
64 |
2048 |
True |
2,383 ± 451 / 718 ± 221 |
3.59 |
24.67 ± 1.69 / 24.58 ± 1.95 |
29.03 ± 2.12 / 29.83 ± 2.15 |
34.39 ± 5.34 / 50.45 ± 6.08 |
64.07 ± 0.86 / 17.41 ± 0.90 |
2.42 ± 1.83 / 35.49 ± 2.63 |
5.11 ± 2.68 / 38.37 ± 3.31 |
42.52 ± 2.05 / 68.98 ± 2.23 |
6.89 ± 1.56 / 27.44 ± 1.06 |
12.81 ± 0.66 / 32.38 ± 0.61 |
9.2.0 |
9.2.0 |
9.2.0 |
12.4.0 |
9.2.0 |
9.2.0 |
12.4.0 |
9.2.0 |
9.3.1 |
google/gemma-2-2b (few-shot) |
2614 |
256 |
8193 |
True |
5,235 ± 1,226 / 1,154 ± 366 |
3.60 |
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 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
timpal0l/Mistral-7B-v0.1-flashback-v2-instruct (few-shot) |
7242 |
32 |
32768 |
False |
5,172 ± 813 / 1,647 ± 518 |
3.64 |
50.34 ± 3.17 / 45.09 ± 2.65 |
52.06 ± 2.41 / 46.88 ± 2.39 |
32.19 ± 2.52 / 43.19 ± 4.63 |
58.71 ± 4.08 / 11.81 ± 0.96 |
-0.22 ± 0.43 / 33.41 ± 0.30 |
0.00 ± 0.00 / 33.86 ± 0.33 |
20.57 ± 0.64 / 40.19 ± 1.13 |
22.27 ± 1.22 / 41.36 ± 0.93 |
11.71 ± 1.56 / 32.80 ± 1.22 |
12.5.2 |
12.5.2 |
12.3.2 |
12.4.0 |
12.3.2 |
12.3.2 |
12.4.0 |
12.3.2 |
12.3.2 |
LumiOpen/Viking-33B@1000B (few-shot) |
33119 |
131 |
4099 |
True |
2,080 ± 700 / 331 ± 117 |
3.70 |
40.40 ± 2.29 / 30.41 ± 2.07 |
44.45 ± 3.61 / 34.06 ± 3.27 |
40.79 ± 1.70 / 57.84 ± 2.77 |
56.55 ± 1.85 / 9.81 ± 1.29 |
5.91 ± 2.51 / 47.81 ± 3.76 |
2.98 ± 2.86 / 45.49 ± 4.59 |
37.75 ± 3.23 / 59.72 ± 3.03 |
1.16 ± 0.75 / 23.71 ± 0.76 |
-0.29 ± 1.00 / 24.91 ± 0.66 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
norallm/normistral-7b-warm (few-shot) |
7248 |
33 |
2048 |
True |
3,175 ± 456 / 1,186 ± 354 |
3.73 |
42.29 ± 4.36 / 31.45 ± 1.88 |
46.29 ± 3.44 / 35.99 ± 4.20 |
27.05 ± 3.33 / 45.30 ± 3.46 |
62.81 ± 1.69 / 17.08 ± 1.49 |
1.63 ± 2.58 / 38.29 ± 4.05 |
2.57 ± 1.78 / 40.92 ± 4.00 |
39.18 ± 2.84 / 61.85 ± 3.07 |
1.50 ± 0.72 / 23.00 ± 0.61 |
-0.05 ± 1.05 / 25.00 ± 0.83 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
AI-Sweden-Models/gpt-sw3-1.3b-instruct (few-shot) |
1445 |
64 |
2048 |
True |
4,544 ± 1,000 / 1,106 ± 359 |
3.75 |
33.08 ± 2.22 / 34.51 ± 2.24 |
38.28 ± 2.63 / 40.50 ± 2.72 |
35.58 ± 2.13 / 44.49 ± 2.52 |
63.11 ± 0.71 / 15.22 ± 1.02 |
0.82 ± 1.46 / 34.78 ± 1.54 |
1.43 ± 1.70 / 34.19 ± 1.10 |
36.06 ± 1.76 / 58.71 ± 1.63 |
-0.68 ± 1.21 / 24.35 ± 0.73 |
-0.32 ± 0.44 / 24.50 ± 0.55 |
12.5.2 |
12.5.2 |
9.3.1 |
12.4.0 |
12.1.0 |
12.1.0 |
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 |
3.88 |
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 |
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 |
google/gemma-2b-it (few-shot) |
2506 |
256 |
8192 |
False |
6,471 ± 1,142 / 1,961 ± 584 |
3.89 |
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 |
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 |
NorwAI/NorwAI-Mistral-7B-instruct (few-shot) |
7537 |
68 |
3841 |
False |
3,027 ± 503 / 903 ± 296 |
3.90 |
27.49 ± 2.13 / 24.26 ± 1.41 |
32.33 ± 2.92 / 29.29 ± 2.05 |
47.78 ± 3.12 / 64.33 ± 2.80 |
62.75 ± 0.25 / 13.28 ± 0.27 |
3.92 ± 1.56 / 45.78 ± 2.36 |
4.27 ± 2.44 / 42.86 ± 3.51 |
2.46 ± 0.73 / 29.01 ± 1.18 |
8.41 ± 0.77 / 32.09 ± 0.44 |
2.92 ± 1.61 / 25.82 ± 0.79 |
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 |
AI-Sweden-Models/gpt-sw3-6.7b (few-shot) |
7111 |
64 |
2048 |
True |
2,285 ± 443 / 671 ± 205 |
3.91 |
22.35 ± 7.84 / 23.89 ± 4.74 |
21.98 ± 7.52 / 27.22 ± 4.97 |
18.23 ± 9.28 / 38.93 ± 6.44 |
60.38 ± 1.78 / 12.50 ± 1.62 |
1.68 ± 1.35 / 39.93 ± 2.78 |
2.49 ± 1.88 / 40.26 ± 3.23 |
41.80 ± 3.14 / 64.25 ± 3.13 |
2.13 ± 0.65 / 26.47 ± 0.86 |
0.98 ± 1.48 / 25.66 ± 1.09 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
HPLT/gpt-33b-nordic-prerelease (few-shot) |
33119 |
131 |
4099 |
True |
501 ± 50 / 238 ± 69 |
3.92 |
31.38 ± 5.44 / 24.32 ± 2.75 |
37.84 ± 4.65 / 29.35 ± 4.10 |
38.88 ± 4.12 / 54.92 ± 4.66 |
55.01 ± 1.93 / 8.21 ± 0.98 |
3.41 ± 2.16 / 35.53 ± 2.75 |
3.11 ± 1.55 / 39.80 ± 4.20 |
30.39 ± 2.51 / 51.24 ± 2.87 |
-1.56 ± 0.62 / 21.86 ± 0.67 |
0.51 ± 1.35 / 25.31 ± 0.93 |
12.9.1 |
12.10.0 |
12.9.1 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
12.10.0 |
LumiOpen/Viking-13B (few-shot) |
14030 |
131 |
4097 |
True |
840 ± 79 / 400 ± 124 |
3.92 |
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 |
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 |
meta-llama/Llama-3.2-1B-Instruct (few-shot) |
1236 |
128 |
131073 |
False |
7,436 ± 1,846 / 1,508 ± 479 |
3.92 |
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 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
stabilityai/stablelm-2-1_6b (few-shot) |
1645 |
100 |
4096 |
True |
7,259 ± 2,120 / 1,240 ± 432 |
3.98 |
41.64 ± 3.64 / 39.43 ± 3.55 |
42.37 ± 3.13 / 40.79 ± 3.10 |
33.71 ± 2.57 / 55.00 ± 1.41 |
49.22 ± 1.24 / 6.32 ± 0.45 |
-0.19 ± 0.77 / 33.29 ± 0.30 |
-0.01 ± 1.25 / 34.51 ± 2.09 |
30.14 ± 2.44 / 50.96 ± 3.46 |
6.67 ± 0.74 / 28.30 ± 0.55 |
3.50 ± 1.56 / 26.82 ± 1.38 |
12.10.8 |
12.10.8 |
12.10.8 |
12.10.8 |
12.10.8 |
12.10.8 |
12.10.8 |
12.10.8 |
12.10.8 |
LumiOpen/Viking-7B (few-shot) |
7550 |
131 |
4096 |
True |
4,969 ± 1,109 / 1,134 ± 374 |
4.00 |
22.37 ± 5.96 / 23.75 ± 3.97 |
29.90 ± 4.44 / 26.84 ± 3.45 |
35.86 ± 3.52 / 52.28 ± 3.76 |
53.25 ± 1.69 / 6.87 ± 0.67 |
1.03 ± 2.07 / 36.12 ± 2.97 |
2.92 ± 1.89 / 36.47 ± 2.72 |
34.39 ± 3.15 / 54.65 ± 3.56 |
-1.16 ± 0.91 / 21.94 ± 0.46 |
-0.55 ± 1.14 / 25.09 ± 0.85 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
ibm-granite/granite-7b-base (few-shot) |
6738 |
32 |
2048 |
True |
4,405 ± 1,098 / 1,032 ± 345 |
4.02 |
32.21 ± 1.63 / 31.19 ± 1.29 |
36.62 ± 1.94 / 36.40 ± 2.17 |
16.98 ± 3.42 / 27.01 ± 3.17 |
55.91 ± 2.53 / 9.21 ± 1.23 |
1.57 ± 1.20 / 41.68 ± 4.20 |
0.97 ± 1.79 / 40.10 ± 4.50 |
26.28 ± 1.51 / 44.62 ± 2.11 |
8.41 ± 1.26 / 29.77 ± 1.22 |
2.47 ± 1.34 / 26.33 ± 1.07 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.5 |
12.10.8 |
12.10.8 |
AI-Sweden-Models/gpt-sw3-1.3b (few-shot) |
1445 |
64 |
2048 |
True |
4,608 ± 988 / 1,115 ± 354 |
4.04 |
13.49 ± 7.98 / 14.80 ± 7.68 |
14.74 ± 8.45 / 15.09 ± 7.85 |
27.28 ± 4.39 / 49.18 ± 4.23 |
58.46 ± 2.59 / 11.38 ± 1.45 |
3.09 ± 0.79 / 42.87 ± 3.49 |
1.86 ± 1.90 / 38.18 ± 1.44 |
34.91 ± 2.65 / 54.30 ± 2.96 |
-0.01 ± 0.86 / 24.32 ± 0.81 |
0.25 ± 0.94 / 25.10 ± 0.81 |
9.3.1 |
9.3.1 |
9.3.1 |
11.0.0 |
9.3.1 |
9.3.1 |
12.5.1 |
9.3.1 |
9.3.1 |
AI-Sweden-Models/gpt-sw3-356m-instruct (few-shot) |
471 |
64 |
2048 |
True |
5,855 ± 1,373 / 1,223 ± 391 |
4.04 |
24.38 ± 2.13 / 25.79 ± 2.29 |
31.28 ± 1.60 / 33.48 ± 1.60 |
30.88 ± 2.75 / 46.07 ± 3.07 |
60.73 ± 0.70 / 11.71 ± 0.76 |
-0.30 ± 1.46 / 34.93 ± 1.25 |
0.45 ± 0.57 / 33.74 ± 1.25 |
23.99 ± 1.59 / 42.69 ± 1.94 |
-1.01 ± 1.09 / 21.90 ± 0.67 |
-0.50 ± 0.67 / 25.00 ± 0.86 |
12.5.2 |
12.5.2 |
9.3.2 |
12.4.0 |
12.1.0 |
12.1.0 |
12.4.0 |
12.1.0 |
12.1.0 |
NbAiLab/nb-gpt-j-6B-alpaca (few-shot) |
6055 |
50 |
1024 |
False |
2,607 ± 592 / 680 ± 208 |
4.05 |
23.82 ± 4.25 / 22.08 ± 2.50 |
26.04 ± 6.38 / 24.47 ± 3.69 |
32.60 ± 1.84 / 47.47 ± 3.33 |
58.08 ± 0.42 / 11.74 ± 0.50 |
0.34 ± 1.43 / 44.47 ± 2.44 |
2.26 ± 2.27 / 45.41 ± 3.25 |
21.33 ± 0.98 / 42.76 ± 1.02 |
2.13 ± 1.32 / 26.30 ± 1.12 |
1.87 ± 1.34 / 25.87 ± 0.75 |
9.3.2 |
9.3.2 |
10.0.1 |
12.4.0 |
10.0.1 |
10.0.1 |
12.4.0 |
10.0.1 |
10.0.1 |
mhenrichsen/danskgpt-tiny-chat (few-shot) |
1100 |
32 |
2048 |
False |
1,745 ± 978 / 686 ± 159 |
4.07 |
28.74 ± 4.18 / 28.29 ± 4.37 |
30.34 ± 6.08 / 30.02 ± 6.42 |
27.49 ± 3.13 / 48.00 ± 3.89 |
60.01 ± 0.81 / 9.76 ± 0.87 |
-2.17 ± 1.06 / 33.52 ± 0.37 |
0.26 ± 1.08 / 34.12 ± 0.45 |
19.10 ± 2.33 / 38.96 ± 2.78 |
3.21 ± 0.87 / 27.07 ± 0.74 |
0.18 ± 1.02 / 25.00 ± 0.86 |
9.1.2 |
9.1.2 |
9.1.2 |
12.4.0 |
9.1.2 |
9.1.2 |
12.4.0 |
9.1.2 |
9.1.2 |
norallm/normistral-7b-scratch (few-shot) |
7248 |
33 |
2048 |
True |
3,192 ± 454 / 1,198 ± 357 |
4.07 |
14.58 ± 6.07 / 15.44 ± 5.52 |
21.06 ± 7.77 / 21.99 ± 7.14 |
32.02 ± 1.59 / 36.85 ± 2.01 |
60.36 ± 1.93 / 12.69 ± 1.69 |
1.49 ± 1.40 / 35.35 ± 1.51 |
0.98 ± 1.85 / 35.28 ± 2.43 |
22.87 ± 1.85 / 38.93 ± 2.59 |
0.99 ± 0.62 / 24.00 ± 0.70 |
-0.16 ± 0.90 / 24.84 ± 0.71 |
10.0.0 |
10.0.0 |
10.0.0 |
11.0.0 |
10.0.0 |
10.0.0 |
10.0.0 |
10.0.1 |
10.0.1 |
ibm-granite/granite-3b-code-base-2k (few-shot) |
3483 |
49 |
2048 |
True |
2,732 ± 868 / 662 ± 238 |
4.09 |
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 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
13.0.0 |
HPLT/gpt-13b-nordic-prerelease (few-shot) |
14030 |
131 |
4099 |
True |
3,520 ± 736 / 823 ± 273 |
4.11 |
28.94 ± 5.63 / 27.01 ± 4.91 |
33.83 ± 5.52 / 30.49 ± 4.07 |
27.32 ± 3.13 / 38.30 ± 2.19 |
54.05 ± 2.19 / 7.52 ± 0.86 |
1.46 ± 1.07 / 49.06 ± 1.04 |
-0.59 ± 1.36 / 45.94 ± 2.35 |
25.62 ± 4.99 / 40.88 ± 7.54 |
0.32 ± 0.70 / 24.79 ± 0.56 |
0.92 ± 1.02 / 25.43 ± 0.83 |
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 |
AI-Sweden-Models/gpt-sw3-356m (few-shot) |
471 |
64 |
2048 |
True |
5,758 ± 1,348 / 1,215 ± 391 |
4.13 |
27.37 ± 4.07 / 27.94 ± 4.04 |
31.22 ± 3.87 / 31.39 ± 3.99 |
34.21 ± 1.63 / 47.17 ± 2.76 |
54.28 ± 2.37 / 8.28 ± 0.99 |
0.92 ± 1.55 / 40.71 ± 2.58 |
1.25 ± 2.30 / 43.49 ± 3.20 |
18.52 ± 2.78 / 32.10 ± 4.23 |
0.33 ± 1.29 / 22.37 ± 1.03 |
0.11 ± 1.10 / 24.94 ± 0.94 |
9.3.1 |
9.3.1 |
9.3.1 |
11.0.0 |
9.3.2 |
9.3.2 |
12.5.1 |
9.3.2 |
9.3.2 |
meta-llama/Llama-3.2-1B (few-shot) |
1236 |
128 |
131073 |
True |
7,577 ± 1,884 / 1,555 ± 492 |
4.14 |
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 |
13.0.0 |
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/Qwen1.5-1.8B-Chat (few-shot) |
1837 |
152 |
32768 |
False |
8,304 ± 1,846 / 1,933 ± 617 |
4.19 |
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 |
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 |
Qwen/Qwen1.5-1.8B (few-shot) |
1837 |
152 |
32768 |
True |
5,666 ± 1,328 / 1,256 ± 408 |
4.20 |
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 |
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 |
HPLT/gpt-7b-nordic-prerelease (few-shot) |
7550 |
131 |
4096 |
True |
5,404 ± 931 / 1,638 ± 542 |
4.32 |
20.25 ± 6.26 / 20.45 ± 5.54 |
28.99 ± 5.03 / 27.50 ± 4.36 |
17.44 ± 3.49 / 35.51 ± 4.10 |
49.59 ± 1.68 / 5.67 ± 0.54 |
3.20 ± 1.84 / 34.58 ± 0.97 |
2.61 ± 1.80 / 34.49 ± 1.46 |
21.50 ± 2.60 / 40.73 ± 3.86 |
0.86 ± 0.91 / 21.96 ± 0.54 |
0.00 ± 0.00 / 25.02 ± 0.87 |
12.5.2 |
12.5.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
RuterNorway/Llama-2-7b-chat-norwegian (few-shot) |
unknown |
32 |
4096 |
False |
10,890 ± 2,686 / 2,186 ± 750 |
4.35 |
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 |
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 |
mhenrichsen/danskgpt-tiny (few-shot) |
1100 |
32 |
2048 |
True |
8,597 ± 1,983 / 1,926 ± 600 |
4.35 |
27.37 ± 6.89 / 27.19 ± 7.19 |
27.59 ± 6.34 / 28.03 ± 6.94 |
18.09 ± 6.14 / 31.83 ± 6.77 |
56.77 ± 2.04 / 9.18 ± 1.21 |
-0.19 ± 1.93 / 41.38 ± 3.18 |
-0.80 ± 0.89 / 40.66 ± 3.78 |
5.84 ± 1.36 / 16.14 ± 2.48 |
-0.50 ± 1.10 / 23.75 ± 0.96 |
0.07 ± 1.21 / 25.26 ± 0.95 |
0.0.0 |
0.0.0 |
0.0.0 |
11.0.0 |
0.0.0 |
0.0.0 |
12.5.1 |
0.0.0 |
0.0.0 |
AI-Sweden-Models/gpt-sw3-126m-instruct (few-shot) |
186 |
64 |
2048 |
True |
7,717 ± 1,553 / 2,013 ± 625 |
4.41 |
27.66 ± 2.00 / 28.61 ± 2.15 |
30.88 ± 2.13 / 31.97 ± 2.10 |
5.13 ± 3.33 / 20.41 ± 3.12 |
58.91 ± 0.95 / 9.74 ± 0.45 |
0.00 ± 0.00 / 33.25 ± 0.30 |
0.00 ± 0.00 / 32.79 ± 0.34 |
7.55 ± 1.17 / 15.63 ± 2.64 |
-0.68 ± 1.27 / 22.92 ± 0.65 |
0.32 ± 0.59 / 25.12 ± 0.69 |
11.0.0 |
11.0.0 |
9.3.2 |
12.4.0 |
11.0.0 |
11.0.0 |
12.4.0 |
11.0.0 |
11.0.0 |
Qwen/Qwen1.5-0.5B (few-shot) |
620 |
152 |
32768 |
True |
11,371 ± 2,924 / 2,122 ± 692 |
4.51 |
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 |
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 |
allenai/OLMo-7B (few-shot) |
6888 |
50 |
2051 |
True |
5,403 ± 1,133 / 1,294 ± 423 |
4.51 |
34.42 ± 3.22 / 27.79 ± 2.40 |
35.17 ± 4.05 / 30.70 ± 3.37 |
21.46 ± 5.63 / 38.36 ± 6.18 |
45.34 ± 0.64 / 5.61 ± 0.21 |
0.34 ± 1.25 / 33.60 ± 0.50 |
0.26 ± 0.58 / 34.69 ± 3.11 |
0.12 ± 0.04 / 9.85 ± 0.17 |
2.61 ± 1.38 / 27.69 ± 0.74 |
0.96 ± 1.02 / 25.05 ± 0.84 |
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 |
allenai/OLMo-7B-Twin-2T (few-shot) |
6888 |
50 |
2051 |
True |
5,484 ± 1,125 / 1,317 ± 425 |
4.66 |
9.06 ± 6.86 / 8.39 ± 6.41 |
17.16 ± 6.21 / 16.00 ± 5.94 |
25.52 ± 3.72 / 41.44 ± 4.44 |
40.94 ± 0.78 / 5.09 ± 0.25 |
0.68 ± 1.54 / 45.09 ± 2.63 |
0.17 ± 2.27 / 42.02 ± 4.30 |
0.46 ± 0.07 / 6.96 ± 0.13 |
2.43 ± 1.10 / 24.94 ± 0.98 |
2.35 ± 0.86 / 26.35 ± 0.78 |
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 |
NorwAI/NorwAI-Mistral-7B-pretrain (few-shot) |
7537 |
68 |
4096 |
True |
3,024 ± 496 / 909 ± 301 |
4.71 |
12.77 ± 3.48 / 14.13 ± 3.09 |
10.51 ± 3.44 / 9.95 ± 3.51 |
8.70 ± 4.43 / 25.39 ± 3.30 |
49.76 ± 2.04 / 6.51 ± 0.86 |
0.00 ± 1.60 / 38.54 ± 3.41 |
0.82 ± 1.39 / 37.77 ± 4.45 |
1.85 ± 0.82 / 10.19 ± 1.99 |
-2.42 ± 1.29 / 21.73 ± 0.58 |
1.23 ± 1.22 / 25.06 ± 0.70 |
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 |
AI-Sweden-Models/gpt-sw3-126m (few-shot) |
186 |
64 |
2048 |
True |
8,958 ± 1,815 / 2,240 ± 696 |
4.72 |
13.55 ± 6.73 / 15.90 ± 5.66 |
9.38 ± 4.88 / 11.18 ± 4.52 |
7.78 ± 3.76 / 21.70 ± 5.02 |
51.68 ± 2.20 / 7.39 ± 0.89 |
-1.46 ± 1.07 / 43.30 ± 2.30 |
-2.97 ± 1.29 / 44.41 ± 3.18 |
2.32 ± 0.68 / 6.65 ± 1.90 |
0.39 ± 1.28 / 23.22 ± 0.56 |
-0.80 ± 0.71 / 24.77 ± 0.62 |
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 |
NbAiLab/nb-gpt-j-6B-v2 (few-shot) |
6051 |
50 |
1024 |
False |
2,556 ± 580 / 681 ± 214 |
4.72 |
5.29 ± 4.68 / 4.93 ± 4.38 |
6.77 ± 6.18 / 6.78 ± 5.66 |
20.84 ± 6.06 / 35.78 ± 5.94 |
44.23 ± 0.84 / 6.81 ± 0.16 |
0.45 ± 1.09 / 34.65 ± 1.93 |
0.48 ± 0.66 / 32.86 ± 0.34 |
2.43 ± 0.61 / 22.78 ± 2.29 |
0.17 ± 1.46 / 24.43 ± 1.54 |
-0.49 ± 0.65 / 24.19 ± 0.56 |
9.3.1 |
9.3.1 |
10.0.1 |
11.0.0 |
11.0.0 |
11.0.0 |
12.5.1 |
11.0.0 |
11.0.0 |
RJuro/kanelsnegl-v0.2 (few-shot) |
7242 |
32 |
512 |
True |
1,373 ± 120 / 709 ± 172 |
4.73 |
0.00 ± 0.00 / 0.00 ± 0.00 |
0.00 ± 0.00 / 0.00 ± 0.00 |
1.27 ± 1.21 / 9.77 ± 0.51 |
59.10 ± 0.12 / 9.14 ± 0.11 |
0.00 ± 0.00 / 33.25 ± 0.30 |
0.00 ± 0.00 / 32.79 ± 0.34 |
0.00 ± 0.00 / 32.25 ± 0.29 |
0.83 ± 0.90 / 21.96 ± 0.50 |
0.09 ± 0.50 / 25.03 ± 0.89 |
10.0.1 |
10.0.1 |
10.0.1 |
11.0.0 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
11.0.0 |
RJuro/kanelsnegl-v0.1 (few-shot) |
7242 |
32 |
512 |
True |
5,847 ± 1,029 / 1,640 ± 525 |
4.75 |
0.00 ± 0.00 / 0.00 ± 0.00 |
0.00 ± 0.00 / 0.00 ± 0.00 |
0.95 ± 0.80 / 9.68 ± 0.28 |
59.32 ± 0.11 / 9.47 ± 0.12 |
0.00 ± 0.00 / 33.25 ± 0.30 |
0.00 ± 0.00 / 32.79 ± 0.34 |
0.00 ± 0.00 / 33.45 ± 0.27 |
0.18 ± 0.35 / 21.91 ± 0.52 |
0.30 ± 0.40 / 25.03 ± 0.88 |
9.3.1 |
9.3.1 |
9.3.1 |
11.0.0 |
9.3.1 |
9.3.1 |
12.5.1 |
9.3.1 |
9.3.1 |
allenai/OLMo-1B (few-shot) |
1177 |
50 |
2051 |
True |
8,536 ± 1,926 / 1,940 ± 619 |
4.77 |
30.79 ± 1.95 / 32.18 ± 1.98 |
31.12 ± 2.36 / 33.10 ± 2.68 |
9.95 ± 3.92 / 29.01 ± 2.80 |
40.45 ± 0.43 / 4.00 ± 0.12 |
-0.95 ± 1.87 / 39.37 ± 3.33 |
-0.04 ± 1.73 / 42.36 ± 4.61 |
0.00 ± 0.00 / 3.06 ± 0.05 |
0.32 ± 1.03 / 24.22 ± 1.37 |
0.12 ± 0.91 / 24.92 ± 0.59 |
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 |
NbAiLab/nb-gpt-j-6B@sharded (few-shot) |
unknown |
50 |
1024 |
True |
2,630 ± 605 / 684 ± 217 |
4.93 |
0.22 ± 0.21 / 1.66 ± 1.38 |
0.24 ± 0.40 / 1.43 ± 1.97 |
20.64 ± 5.63 / 36.75 ± 3.29 |
38.55 ± 0.48 / 5.75 ± 0.20 |
-0.99 ± 0.88 / 33.37 ± 0.27 |
-0.15 ± 0.72 / 32.83 ± 0.34 |
0.53 ± 0.31 / 22.14 ± 2.25 |
0.63 ± 1.48 / 24.41 ± 1.24 |
-0.09 ± 0.80 / 24.42 ± 0.74 |
9.3.1 |
9.3.1 |
10.0.1 |
11.0.0 |
10.0.1 |
10.0.1 |
12.5.1 |
10.0.1 |
10.0.1 |
NorGLM/NorGPT-369M (few-shot) |
unknown |
64 |
1024 |
True |
19,896 ± 5,099 / 3,848 ± 1,251 |
4.96 |
3.14 ± 2.12 / 2.91 ± 2.02 |
3.00 ± 1.58 / 2.65 ± 1.41 |
3.41 ± 2.11 / 14.87 ± 2.38 |
45.57 ± 1.88 / 4.96 ± 0.39 |
0.22 ± 0.42 / 33.42 ± 0.29 |
0.27 ± 0.79 / 38.20 ± 3.48 |
0.00 ± 0.00 / 2.27 ± 0.89 |
-0.45 ± 1.48 / 24.16 ± 1.48 |
-0.27 ± 0.89 / 24.77 ± 0.63 |
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 |
peter-sk/gpt-neox-da (few-shot) |
1515 |
50 |
1024 |
True |
6,025 ± 1,442 / 1,342 ± 431 |
5.08 |
0.29 ± 0.29 / 0.29 ± 0.27 |
0.25 ± 0.17 / 0.27 ± 0.21 |
-1.43 ± 1.45 / 20.90 ± 4.96 |
41.89 ± 1.40 / 3.46 ± 0.33 |
-0.42 ± 1.10 / 35.77 ± 3.09 |
1.11 ± 2.21 / 39.28 ± 4.12 |
0.00 ± 0.00 / 3.15 ± 0.55 |
0.69 ± 0.71 / 24.93 ± 0.99 |
0.55 ± 0.68 / 25.11 ± 0.43 |
10.0.1 |
10.0.1 |
10.0.1 |
11.0.0 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
Sigurdur/icebreaker (few-shot) |
110 |
32 |
1024 |
False |
48,619 ± 7,681 / 13,831 ± 4,404 |
5.13 |
0.00 ± 0.00 / 0.00 ± 0.00 |
0.00 ± 0.00 / 0.00 ± 0.00 |
0.00 ± 0.00 / 9.59 ± 0.29 |
39.58 ± 0.08 / 0.78 ± 0.04 |
0.00 ± 0.00 / 33.25 ± 0.30 |
0.00 ± 0.00 / 32.79 ± 0.34 |
0.00 ± 0.00 / 0.47 ± 0.03 |
0.18 ± 0.69 / 22.92 ± 0.50 |
-0.09 ± 0.53 / 24.70 ± 0.47 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
ai-forever/mGPT (few-shot) |
unknown |
100 |
1024 |
True |
11,734 ± 3,124 / 2,174 ± 720 |
5.19 |
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 |
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 |
Qwen/Qwen1.5-0.5B-Chat (few-shot) |
620 |
152 |
32768 |
False |
11,740 ± 3,000 / 2,209 ± 721 |
5.26 |
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 |
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 |