Germanic NLU 🇪🇺

gpt-4-0613 (few-shot, val)

unknown

100

8192

True

597 ± 197 / 93 ± 33

1.42

1.18

1.34

1.18

1.82

1.36

1.76

1.32

64.94 ± 1.96 / 45.76 ± 3.31

59.97 ± 2.65 / 73.06 ± 1.77

71.56 ± 2.49 / 85.36 ± 1.29

56.43 ± 2.98 / 68.46 ± 1.64

81.16 ± 2.46 / 63.39 ± 4.07

75.75 ± 4.49 / 60.44 ± 5.46

72.72 ± 3.20 / 81.35 ± 2.22

77.30 ± 2.97 / 88.39 ± 1.60

57.18 ± 3.91 / 76.40 ± 2.66

47.50 ± 2.86 / 75.24 ± 1.32

76.86 ± 1.89 / 54.97 ± 4.44

79.19 ± 1.87 / 80.56 ± 1.82

80.93 ± 1.67 / 89.90 ± 0.93

53.81 ± 1.28 / 65.15 ± 1.11

78.67 ± 2.16 / 59.54 ± 4.85

33.65 ± 3.19 / 60.56 ± 2.35

32.25 ± 2.01 / 60.12 ± 1.31

69.48 ± 2.32 / 54.66 ± 2.17

64.91 ± 1.86 / 75.96 ± 1.59

50.23 ± 4.16 / 74.54 ± 2.10

33.17 ± 1.86 / 65.14 ± 1.53

73.35 ± 2.61 / 56.00 ± 2.82

18.92 ± 2.78 / 40.80 ± 2.43

76.70 ± 2.39 / 88.16 ± 1.21

55.03 ± 1.96 / 76.47 ± 1.22

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

0.0.0

12.9.0

0.0.0

12.9.0

0.0.0

12.9.0

12.10.0

12.2.0

12.1.0

12.2.0

gpt-4-1106-preview (few-shot, val)

unknown

100

127999

True

576 ± 221 / 81 ± 28

1.45

1.26

1.42

1.27

1.31

1.50

2.04

1.36

66.80 ± 3.01 / 45.69 ± 2.85

61.62 ± 2.17 / 73.99 ± 1.48

66.84 ± 3.27 / 82.79 ± 1.86

56.85 ± 2.62 / 68.83 ± 1.50

77.48 ± 2.32 / 55.87 ± 2.83

78.70 ± 2.78 / 57.58 ± 4.23

62.55 ± 2.82 / 72.41 ± 2.42

74.45 ± 4.27 / 86.22 ± 2.49

56.31 ± 5.81 / 74.04 ± 4.03

44.67 ± 3.23 / 73.39 ± 1.83

74.45 ± 3.09 / 49.97 ± 4.23

77.59 ± 1.38 / 78.78 ± 1.69

71.35 ± 3.10 / 83.98 ± 2.23

56.56 ± 1.39 / 66.76 ± 1.10

86.37 ± 1.19 / 82.25 ± 2.73

43.03 ± 5.07 / 71.18 ± 2.64

37.26 ± 2.60 / 66.04 ± 1.95

68.94 ± 2.50 / 44.89 ± 2.85

60.47 ± 2.94 / 72.79 ± 1.90

51.26 ± 4.94 / 74.76 ± 2.45

30.04 ± 1.30 / 58.77 ± 1.50

66.44 ± 2.18 / 56.97 ± 2.87

14.22 ± 3.26 / 33.41 ± 3.24

72.30 ± 2.26 / 85.96 ± 1.13

57.81 ± 1.23 / 74.51 ± 0.62

81.79 ± 1.39 / 65.51 ± 4.16

67.55 ± 2.34 / 74.04 ± 1.80

51.21 ± 4.96 / 75.11 ± 2.42

66.60 ± 1.45 / 84.48 ± 0.76

12.10.0

12.10.2

12.10.0

12.10.2

12.10.0

12.10.2

12.10.0

12.5.1

12.10.2

12.5.1

12.6.1

12.10.2

12.6.1

12.3.2

12.10.2

12.3.2

12.10.0

12.10.2

12.10.0

gpt-4o-2024-05-13 (few-shot, val)

unknown

200

127999

True

916 ± 329 / 114 ± 38

1.55

1.37

1.53

1.27

1.30

1.68

2.21

1.48

71.15 ± 2.89 / 52.24 ± 3.76

49.42 ± 3.29 / 61.74 ± 2.59

64.59 ± 2.97 / 79.93 ± 1.88

57.35 ± 2.51 / 67.87 ± 1.75

79.07 ± 3.01 / 64.17 ± 3.51

81.56 ± 2.45 / 64.06 ± 4.11

66.66 ± 1.91 / 77.70 ± 1.29

64.53 ± 6.09 / 79.17 ± 4.89

54.70 ± 4.36 / 74.94 ± 3.26

43.51 ± 3.40 / 74.52 ± 1.79

76.66 ± 2.11 / 60.34 ± 4.71

77.16 ± 2.65 / 79.22 ± 2.36

68.99 ± 4.33 / 83.37 ± 2.61

57.96 ± 1.35 / 67.71 ± 0.96

81.19 ± 2.45 / 54.02 ± 5.60

51.10 ± 5.09 / 73.25 ± 3.42

29.64 ± 2.12 / 55.46 ± 1.12

69.99 ± 1.63 / 45.58 ± 2.42

54.82 ± 2.19 / 68.42 ± 1.67

43.66 ± 5.67 / 64.64 ± 4.65

30.06 ± 1.04 / 60.77 ± 1.11

76.75 ± 3.44 / 61.13 ± 4.40

10.80 ± 2.24 / 32.52 ± 2.18

56.26 ± 4.51 / 73.83 ± 3.26

55.55 ± 2.54 / 76.28 ± 1.13

83.48 ± 1.52 / 75.51 ± 2.26

62.74 ± 2.04 / 71.28 ± 1.46

46.56 ± 3.35 / 71.13 ± 1.97

65.41 ± 1.96 / 84.78 ± 0.68

12.10.0

12.10.2

12.10.0

12.10.2

12.10.0

12.10.2

12.10.0

12.10.2

12.10.0

12.10.2

12.10.0

12.10.2

12.10.0

12.10.2

12.10.0

google/rembert

576

250

256

True

11,736 ± 2,822 / 2,102 ± 677

1.56

1.61

1.37

1.43

1.52

1.20

2.39

1.38

70.19 ± 3.34 / 66.64 ± 2.68

50.19 ± 1.82 / 66.32 ± 1.50

69.72 ± 2.25 / 84.30 ± 1.64

39.85 ± 8.97 / 44.44 ± 9.99

88.70 ± 2.05 / 84.95 ± 2.83

86.11 ± 1.67 / 82.16 ± 1.96

54.19 ± 3.15 / 65.18 ± 4.55

69.83 ± 2.01 / 84.72 ± 1.10

54.84 ± 12.59 / 75.13 ± 9.44

58.18 ± 1.84 / 71.29 ± 1.51

78.23 ± 1.53 / 72.58 ± 1.51

75.99 ± 1.15 / 71.01 ± 4.17

72.17 ± 0.94 / 85.94 ± 0.54

46.00 ± 2.13 / 51.05 ± 2.40

78.05 ± 1.72 / 78.74 ± 1.41

48.29 ± 2.59 / 73.54 ± 1.99

29.38 ± 1.81 / 52.42 ± 3.00

77.62 ± 0.80 / 76.16 ± 0.79

60.65 ± 2.10 / 73.52 ± 1.58

62.60 ± 2.16 / 81.12 ± 1.14

33.62 ± 1.34 / 60.41 ± 1.36

75.49 ± 1.75 / 81.37 ± 1.31

4.79 ± 3.93 / 27.49 ± 2.37

66.47 ± 2.04 / 83.16 ± 1.01

55.70 ± 1.62 / 68.38 ± 1.47

90.17 ± 0.50 / 89.85 ± 0.49

51.74 ± 10.59 / 58.97 ± 6.34

55.55 ± 1.66 / 77.55 ± 0.89

69.02 ± 1.23 / 81.57 ± 1.05

0.0.0

12.7.0

12.6.1

meta-llama/Meta-Llama-3-70B (few-shot, val)

70554

128

8192

True

312 ± 55 / 177 ± 51

1.57

1.34

1.40

1.27

2.24

1.45

1.89

1.42

63.62 ± 3.74 / 53.29 ± 3.38

60.19 ± 3.31 / 73.13 ± 2.17

50.07 ± 5.86 / 72.94 ± 4.16

60.97 ± 2.76 / 66.71 ± 2.27

75.31 ± 3.84 / 64.90 ± 4.05

75.94 ± 4.62 / 62.81 ± 5.25

66.74 ± 4.50 / 74.89 ± 3.69

59.82 ± 3.52 / 79.17 ± 2.10

47.56 ± 3.52 / 71.91 ± 1.79

60.87 ± 4.82 / 82.30 ± 2.52

74.61 ± 2.99 / 56.50 ± 6.30

78.61 ± 1.40 / 78.64 ± 1.53

63.20 ± 3.34 / 80.61 ± 2.52

61.98 ± 1.65 / 66.85 ± 1.42

75.33 ± 3.06 / 62.43 ± 3.11

14.89 ± 3.28 / 51.55 ± 4.71

34.36 ± 2.87 / 64.02 ± 2.94

69.04 ± 2.51 / 61.10 ± 3.39

63.51 ± 2.57 / 75.01 ± 1.74

37.41 ± 2.43 / 67.63 ± 1.05

38.29 ± 3.54 / 69.69 ± 2.78

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

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

12.7.0

12.6.1

12.7.0

microsoft/mdeberta-v3-base

279

251

512

True

20,637 ± 3,925 / 4,497 ± 1,502

1.59

1.65

1.45

1.21

1.65

2.34

1.36

72.90 ± 2.53 / 67.41 ± 2.19

43.38 ± 3.20 / 60.05 ± 4.33

67.05 ± 1.41 / 83.18 ± 0.80

42.15 ± 2.12 / 47.97 ± 1.99

91.90 ± 0.54 / 89.55 ± 0.57

86.81 ± 1.35 / 83.46 ± 1.68

53.69 ± 4.28 / 63.69 ± 6.95

70.55 ± 1.64 / 84.79 ± 0.86

61.21 ± 1.20 / 79.87 ± 0.76

48.82 ± 1.20 / 63.72 ± 1.06

78.84 ± 2.19 / 72.86 ± 2.04

75.24 ± 0.99 / 72.06 ± 2.67

72.30 ± 1.04 / 85.77 ± 0.65

44.74 ± 1.04 / 50.62 ± 0.85

81.12 ± 2.02 / 81.48 ± 1.69

54.11 ± 2.40 / 76.46 ± 1.28

30.93 ± 0.96 / 56.17 ± 1.10

77.42 ± 1.30 / 76.39 ± 1.16

50.90 ± 6.20 / 66.89 ± 4.34

59.38 ± 2.00 / 79.12 ± 1.09

20.28 ± 1.15 / 42.79 ± 1.37

84.47 ± 1.84 / 87.98 ± 1.21

5.16 ± 5.21 / 27.85 ± 3.29

71.23 ± 1.62 / 85.45 ± 0.83

46.43 ± 0.72 / 57.80 ± 0.84

91.83 ± 0.50 / 91.40 ± 0.43

53.75 ± 1.47 / 56.40 ± 2.82

62.11 ± 1.53 / 80.67 ± 0.77

62.10 ± 1.03 / 73.26 ± 0.85

0.0.0

12.7.0

0.0.0

intfloat/multilingual-e5-large

560

250

512

True

6,732 ± 1,273 / 1,633 ± 523

1.64

1.57

1.53

1.45

2.89

1.35

1.43

1.29

69.50 ± 1.78 / 65.03 ± 1.31

55.07 ± 1.53 / 69.43 ± 1.47

57.67 ± 2.56 / 78.48 ± 1.32

46.71 ± 1.25 / 52.84 ± 1.18

89.86 ± 0.93 / 90.64 ± 0.80

84.32 ± 1.08 / 86.52 ± 0.94

61.52 ± 1.87 / 72.72 ± 1.95

62.34 ± 2.48 / 79.94 ± 1.46

34.88 ± 11.23 / 66.51 ± 5.72

53.01 ± 1.05 / 70.46 ± 0.86

80.36 ± 1.12 / 78.57 ± 1.27

79.65 ± 1.05 / 78.90 ± 1.32

63.15 ± 1.65 / 81.06 ± 0.95

46.99 ± 1.18 / 53.49 ± 0.89

78.43 ± 1.53 / 79.30 ± 1.03

10.78 ± 7.04 / 53.28 ± 3.97

13.79 ± 0.96 / 54.20 ± 1.31

79.73 ± 1.38 / 78.52 ± 1.44

64.78 ± 1.34 / 76.30 ± 0.98

47.24 ± 13.67 / 71.51 ± 8.03

28.11 ± 0.94 / 54.87 ± 1.08

82.31 ± 2.14 / 86.91 ± 1.34

32.64 ± 2.91 / 49.90 ± 3.42

58.51 ± 4.12 / 78.17 ± 2.32

45.32 ± 1.91 / 57.53 ± 1.78

91.69 ± 0.67 / 91.29 ± 0.54

64.37 ± 1.28 / 65.16 ± 2.10

53.58 ± 10.20 / 74.70 ± 7.53

60.47 ± 1.61 / 73.00 ± 1.37

0.0.0

12.6.1

0.0.0

12.6.1

setu4993/LaBSE

471

501

512

True

25,418 ± 6,435 / 4,536 ± 1,452

1.71

1.87

1.63

2.23

1.51

1.52

1.59

71.24 ± 1.63 / 66.41 ± 1.64

46.50 ± 1.57 / 64.31 ± 1.21

52.92 ± 4.42 / 75.11 ± 3.22

40.08 ± 1.22 / 45.40 ± 1.14

90.58 ± 0.91 / 87.84 ± 1.00

85.21 ± 1.05 / 81.57 ± 1.30

54.26 ± 1.75 / 67.25 ± 1.47

59.44 ± 1.47 / 78.80 ± 1.00

49.30 ± 1.39 / 74.02 ± 1.04

46.42 ± 1.44 / 61.82 ± 1.47

77.78 ± 1.69 / 72.08 ± 1.81

73.58 ± 1.37 / 70.43 ± 2.49

60.36 ± 2.98 / 79.72 ± 1.52

41.71 ± 1.08 / 47.07 ± 0.98

80.45 ± 1.29 / 81.01 ± 1.16

36.92 ± 7.62 / 66.07 ± 3.89

11.75 ± 0.66 / 46.17 ± 1.42

79.44 ± 0.96 / 78.42 ± 0.98

58.65 ± 1.67 / 72.12 ± 1.18

52.19 ± 2.96 / 74.17 ± 1.82

23.66 ± 0.97 / 45.11 ± 1.50

82.02 ± 1.04 / 84.71 ± 0.59

33.99 ± 4.05 / 50.69 ± 4.23

60.77 ± 1.53 / 79.80 ± 0.87

41.55 ± 1.08 / 51.73 ± 1.18

90.33 ± 0.62 / 90.31 ± 0.46

52.93 ± 1.41 / 58.98 ± 1.52

50.70 ± 2.70 / 74.17 ± 1.51

53.77 ± 0.57 / 65.07 ± 0.61

0.0.0

12.7.0

0.0.0

12.6.1

FacebookAI/xlm-roberta-large

560

250

512

True

17,897 ± 3,921 / 3,463 ± 1,141

1.74

1.69

1.50

1.59

2.32

1.21

2.20

1.69

72.74 ± 2.58 / 67.15 ± 2.53

48.33 ± 4.44 / 63.94 ± 5.16

57.30 ± 14.90 / 76.82 ± 8.67

43.57 ± 3.28 / 49.29 ± 3.35

91.66 ± 1.24 / 89.34 ± 1.62

86.19 ± 0.97 / 82.86 ± 1.29

50.25 ± 15.36 / 63.55 ± 13.05

55.51 ± 18.28 / 74.00 ± 13.38

43.89 ± 14.81 / 68.88 ± 10.32

57.57 ± 2.43 / 72.69 ± 2.22

80.33 ± 2.50 / 75.03 ± 3.79

76.63 ± 0.98 / 74.25 ± 3.20

49.72 ± 19.88 / 69.94 ± 13.64

46.64 ± 1.42 / 52.21 ± 1.45

82.83 ± 1.09 / 83.16 ± 1.02

22.78 ± 12.25 / 57.07 ± 8.18

15.72 ± 1.39 / 55.29 ± 1.30

80.64 ± 0.81 / 80.03 ± 0.97

63.02 ± 1.62 / 75.25 ± 1.08

54.83 ± 9.12 / 76.02 ± 5.19

29.09 ± 1.00 / 55.68 ± 1.11

83.49 ± 1.51 / 86.12 ± 1.21

8.82 ± 7.93 / 30.82 ± 4.71

64.80 ± 8.79 / 80.93 ± 6.29

50.72 ± 1.20 / 61.66 ± 1.16

89.81 ± 0.60 / 89.25 ± 0.72

41.97 ± 17.48 / 50.33 ± 9.16

35.55 ± 18.61 / 63.79 ± 12.17

68.88 ± 1.40 / 79.18 ± 1.17

0.0.0

12.7.0

0.0.0

gpt-3.5-turbo-0613 (few-shot, val)

unknown

100

4094

True

921 ± 293 / 113 ± 37

1.89

1.53

1.83

1.49

2.56

1.82

2.37

1.62

61.31 ± 2.34 / 49.86 ± 2.18

52.52 ± 2.05 / 68.10 ± 1.35

57.63 ± 2.80 / 77.01 ± 1.83

57.03 ± 1.95 / 65.51 ± 1.48

77.70 ± 2.64 / 68.71 ± 2.97

73.92 ± 2.53 / 67.96 ± 2.67

58.88 ± 3.23 / 71.00 ± 2.87

54.29 ± 4.27 / 73.02 ± 3.26

32.82 ± 3.43 / 56.05 ± 4.14

45.35 ± 2.97 / 73.47 ± 1.69

73.04 ± 2.74 / 61.64 ± 3.63

72.77 ± 2.64 / 72.56 ± 2.45

58.06 ± 3.84 / 76.06 ± 2.51

58.02 ± 2.11 / 66.84 ± 1.38

69.59 ± 4.54 / 54.49 ± 4.31

7.28 ± 4.10 / 52.96 ± 2.00

28.50 ± 1.79 / 50.29 ± 1.79

61.50 ± 2.96 / 46.22 ± 3.41

55.50 ± 2.58 / 68.96 ± 2.00

38.96 ± 4.39 / 68.89 ± 2.54

30.20 ± 1.59 / 56.58 ± 1.78

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

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

12.9.0

0.0.0

12.9.0

0.0.0

12.9.0

0.0.0

152334H/miqu-1-70b-sf (few-shot, val)

68977

32

32764

True

2,126 ± 676 / 319 ± 104

1.96

1.75

2.10

1.66

2.65

1.69

2.18

1.70

56.96 ± 2.39 / 45.84 ± 1.75

55.11 ± 4.11 / 69.60 ± 2.69

42.64 ± 3.22 / 71.04 ± 1.56

54.58 ± 2.19 / 64.12 ± 1.41

66.75 ± 2.07 / 58.61 ± 3.33

66.81 ± 2.57 / 57.71 ± 3.04

60.58 ± 4.96 / 70.33 ± 4.12

47.53 ± 4.07 / 72.24 ± 2.31

17.14 ± 4.72 / 51.14 ± 4.36

41.92 ± 3.36 / 72.51 ± 1.91

62.96 ± 3.44 / 52.14 ± 4.04

75.25 ± 2.41 / 78.80 ± 1.96

53.28 ± 3.33 / 75.37 ± 1.80

56.42 ± 1.65 / 65.04 ± 1.17

61.13 ± 3.80 / 50.79 ± 5.92

7.75 ± 5.66 / 46.83 ± 4.00

27.27 ± 4.08 / 60.91 ± 1.98

65.19 ± 2.58 / 56.17 ± 3.57

59.80 ± 2.15 / 71.98 ± 1.46

41.86 ± 5.44 / 69.70 ± 2.31

25.51 ± 3.79 / 63.19 ± 2.48

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

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

12.7.0

meta-llama/Llama-2-70b-hf (few-shot, val)

68977

32

4096

True

1,892 ± 650 / 318 ± 105

1.99

1.64

2.15

1.60

2.82

1.64

2.50

1.55

58.06 ± 2.48 / 50.10 ± 2.23

53.24 ± 4.04 / 67.81 ± 2.74

39.71 ± 4.96 / 65.90 ± 3.81

62.51 ± 1.48 / 67.47 ± 1.39

62.46 ± 4.62 / 60.77 ± 4.36

64.68 ± 3.04 / 61.69 ± 2.31

59.68 ± 3.30 / 70.62 ± 3.08

27.34 ± 12.20 / 50.42 ± 9.24

3.95 ± 4.66 / 36.08 ± 3.27

57.44 ± 4.59 / 78.69 ± 3.09

64.76 ± 3.91 / 61.08 ± 5.41

75.46 ± 1.99 / 74.35 ± 3.70

43.27 ± 5.03 / 65.62 ± 4.94

63.04 ± 1.52 / 66.95 ± 1.31

63.25 ± 4.52 / 53.70 ± 3.09

0.00 ± 0.00 / 33.12 ± 0.74

32.65 ± 4.82 / 61.15 ± 3.96

63.71 ± 2.43 / 57.08 ± 2.70

58.17 ± 2.51 / 71.34 ± 1.62

36.33 ± 5.00 / 64.51 ± 3.38

36.06 ± 2.89 / 69.62 ± 2.81

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

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

12.7.0

meta-llama/Meta-Llama-3-70B-Instruct (few-shot, val)

70554

128

8192

True

1,673 ± 583 / 275 ± 85

1.99

1.75

1.93

1.99

2.66

1.76

2.18

1.69

63.10 ± 2.12 / 55.10 ± 1.44

53.09 ± 3.85 / 68.18 ± 2.27

40.98 ± 4.46 / 69.10 ± 2.72

51.13 ± 1.89 / 63.12 ± 1.61

80.50 ± 2.85 / 76.71 ± 2.48

76.47 ± 3.13 / 73.94 ± 2.95

59.29 ± 5.92 / 69.99 ± 4.80

47.28 ± 3.57 / 69.23 ± 3.04

32.76 ± 3.80 / 60.66 ± 3.10

39.71 ± 2.59 / 71.60 ± 1.57

77.06 ± 2.72 / 67.75 ± 5.69

53.56 ± 7.15 / 67.07 ± 3.93

47.50 ± 3.37 / 71.31 ± 2.69

46.86 ± 1.77 / 60.96 ± 1.04

72.91 ± 3.48 / 68.22 ± 4.46

5.01 ± 4.64 / 50.69 ± 3.23

31.86 ± 1.86 / 60.66 ± 1.58

75.20 ± 2.15 / 64.06 ± 3.60

54.38 ± 3.31 / 68.02 ± 2.21

36.59 ± 4.24 / 67.36 ± 1.77

26.90 ± 2.67 / 58.28 ± 2.22

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

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

12.7.0

intfloat/multilingual-e5-base

278

250

512

True

14,965 ± 2,890 / 3,322 ± 1,074

2.01

1.90

2.10

1.70

3.08

1.71

2.07

1.53

68.70 ± 2.40 / 64.05 ± 2.19

49.88 ± 1.21 / 66.06 ± 1.12

44.20 ± 2.01 / 70.33 ± 1.04

39.90 ± 1.37 / 45.91 ± 1.20

88.26 ± 1.11 / 89.24 ± 0.95

81.37 ± 1.67 / 83.89 ± 1.34

54.61 ± 1.51 / 67.19 ± 1.65

50.35 ± 1.78 / 73.06 ± 1.46

22.15 ± 9.02 / 58.20 ± 5.38

31.77 ± 1.55 / 45.47 ± 2.02

79.02 ± 0.74 / 77.59 ± 0.76

76.06 ± 0.89 / 69.85 ± 3.16

50.19 ± 1.23 / 74.23 ± 0.99

40.65 ± 1.29 / 46.62 ± 1.30

75.46 ± 1.42 / 77.52 ± 0.88

15.21 ± 8.62 / 54.40 ± 5.57

10.82 ± 0.92 / 43.65 ± 2.51

74.79 ± 1.45 / 75.10 ± 1.37

63.29 ± 1.54 / 75.42 ± 1.03

45.32 ± 8.38 / 71.30 ± 4.11

16.42 ± 0.54 / 34.46 ± 1.03

79.12 ± 1.90 / 83.05 ± 1.09

27.67 ± 2.85 / 44.90 ± 2.69

39.28 ± 12.28 / 67.90 ± 5.94

35.71 ± 1.70 / 46.63 ± 1.40

89.65 ± 0.52 / 89.71 ± 0.48

61.46 ± 0.89 / 60.48 ± 2.52

51.32 ± 1.98 / 74.21 ± 1.18

50.78 ± 1.14 / 63.05 ± 0.89

12.6.1

0.0.0

12.6.1

0.0.0

12.6.1

0.0.0

12.6.1

AI-Sweden-Models/roberta-large-1350k

355

50

512

True

5,744 ± 969 / 1,539 ± 492

2.06

1.39

1.17

1.26

3.08

2.69

3.39

1.45

75.22 ± 1.64 / 71.57 ± 1.50

49.94 ± 3.25 / 65.66 ± 2.73

72.59 ± 1.38 / 85.58 ± 0.97

48.97 ± 1.22 / 54.79 ± 1.18

92.49 ± 0.81 / 92.58 ± 0.61

87.22 ± 1.19 / 88.71 ± 1.02

58.77 ± 3.69 / 69.56 ± 4.55

76.30 ± 2.09 / 87.19 ± 1.40

64.11 ± 5.18 / 80.68 ± 3.72

60.69 ± 1.15 / 75.73 ± 1.06

82.97 ± 0.98 / 81.14 ± 1.14

77.37 ± 1.25 / 73.57 ± 3.43

73.81 ± 4.60 / 86.33 ± 2.48

49.50 ± 1.32 / 55.34 ± 1.33

73.92 ± 1.40 / 75.86 ± 1.21

11.77 ± 5.19 / 43.60 ± 7.11

11.84 ± 1.07 / 48.30 ± 1.02

67.24 ± 1.51 / 66.01 ± 1.32

45.84 ± 2.11 / 63.35 ± 1.48

2.28 ± 1.62 / 35.18 ± 2.11

18.17 ± 1.85 / 33.37 ± 2.80

73.03 ± 2.07 / 79.97 ± 1.63

3.65 ± 4.19 / 26.89 ± 2.64

2.00 ± 2.03 / 39.53 ± 4.47

42.85 ± 0.98 / 53.68 ± 0.89

89.48 ± 0.86 / 89.32 ± 0.69

51.88 ± 6.25 / 56.03 ± 4.61

50.69 ± 4.90 / 73.54 ± 2.97

69.46 ± 1.02 / 80.82 ± 0.75

10.0.1

upstage/SOLAR-10.7B-v1.0 (few-shot)

10732

32

4096

True

3,780 ± 906 / 799 ± 261

2.06

2.08

2.32

1.94

2.57

1.55

2.41

1.52

58.03 ± 2.18 / 38.25 ± 2.31

46.63 ± 2.35 / 59.02 ± 3.07

15.09 ± 3.06 / 40.04 ± 1.77

62.15 ± 0.63 / 67.21 ± 0.55

68.11 ± 1.83 / 57.57 ± 3.10

68.19 ± 1.01 / 56.90 ± 2.54

55.33 ± 1.95 / 69.71 ± 1.56

10.15 ± 3.24 / 36.27 ± 1.44

7.51 ± 2.97 / 35.89 ± 1.30

55.33 ± 3.29 / 80.42 ± 1.68

59.65 ± 2.22 / 39.33 ± 3.33

77.48 ± 1.23 / 70.13 ± 2.81

16.94 ± 2.36 / 40.98 ± 1.82

62.65 ± 0.56 / 68.15 ± 0.56

62.08 ± 2.27 / 51.09 ± 4.15

7.58 ± 1.03 / 44.38 ± 3.90

29.66 ± 3.02 / 56.60 ± 2.22

68.11 ± 1.32 / 56.25 ± 1.65

59.79 ± 1.60 / 71.47 ± 1.54

35.45 ± 3.06 / 66.13 ± 1.28

37.27 ± 1.23 / 68.54 ± 1.94

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

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

12.5.3

AI-Sweden-Models/roberta-large-1160k

355

50

512

True

14,014 ± 2,384 / 3,625 ± 1,146

2.07

1.28

1.17

1.26

3.40

2.62

3.41

1.37

74.16 ± 1.73 / 70.93 ± 1.67

51.20 ± 1.67 / 66.62 ± 1.58

73.87 ± 2.13 / 86.61 ± 1.17

49.34 ± 1.14 / 55.06 ± 1.21

92.01 ± 0.98 / 92.36 ± 0.70

87.17 ± 1.24 / 88.75 ± 0.89

60.11 ± 2.96 / 70.55 ± 3.99

72.85 ± 5.60 / 85.73 ± 3.14

65.56 ± 1.91 / 82.23 ± 0.97

60.38 ± 0.95 / 75.42 ± 1.16

82.65 ± 1.04 / 80.43 ± 0.93

77.25 ± 1.20 / 73.96 ± 2.59

77.90 ± 1.45 / 88.63 ± 0.76

49.64 ± 1.11 / 55.64 ± 1.07

74.30 ± 2.15 / 76.10 ± 2.10

2.06 ± 2.43 / 37.04 ± 4.14

11.47 ± 0.96 / 48.11 ± 0.94

68.93 ± 1.48 / 67.48 ± 1.55

46.81 ± 1.79 / 64.02 ± 1.31

3.39 ± 3.01 / 39.29 ± 4.82

18.62 ± 1.74 / 34.87 ± 2.36

70.92 ± 1.61 / 78.52 ± 1.23

3.50 ± 3.15 / 27.25 ± 2.24

2.06 ± 1.79 / 41.06 ± 5.11

41.40 ± 1.92 / 51.93 ± 2.09

89.53 ± 0.40 / 89.37 ± 0.30

53.90 ± 1.96 / 54.63 ± 2.32

55.31 ± 2.36 / 76.38 ± 1.93

69.89 ± 0.99 / 80.82 ± 0.97

10.0.1

12.10.0

10.0.1

Nexusflow/Starling-LM-7B-beta (few-shot)

7242

32

8192

False

5,876 ± 1,021 / 1,677 ± 546

2.12

1.92

2.25

1.87

3.23

1.81

2.33

1.46

53.20 ± 1.97 / 32.89 ± 2.00

51.75 ± 1.18 / 67.38 ± 0.95

32.72 ± 1.79 / 62.53 ± 2.00

56.44 ± 0.99 / 65.36 ± 0.51

66.22 ± 2.15 / 48.98 ± 4.65

64.14 ± 1.26 / 49.59 ± 4.31

55.48 ± 1.77 / 69.68 ± 1.45

26.13 ± 1.28 / 56.08 ± 2.05

17.32 ± 0.77 / 54.57 ± 1.49

49.75 ± 1.22 / 77.08 ± 0.60

60.38 ± 1.60 / 36.17 ± 3.66

77.49 ± 0.98 / 72.07 ± 1.56

29.32 ± 2.34 / 54.43 ± 2.67

56.79 ± 0.83 / 65.84 ± 0.48

49.20 ± 2.64 / 40.79 ± 4.46

4.45 ± 1.40 / 51.11 ± 0.87

24.61 ± 3.36 / 54.99 ± 2.36

65.01 ± 0.68 / 43.34 ± 2.80

51.80 ± 1.29 / 67.45 ± 0.87

36.18 ± 1.31 / 67.86 ± 0.51

32.12 ± 2.08 / 67.30 ± 1.66

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

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

12.5.2

meta-llama/Meta-Llama-3-8B (few-shot)

8030

128

8192

True

4,687 ± 1,121 / 967 ± 313

2.19

2.02

2.28

1.81

2.82

1.93

2.62

1.82

46.31 ± 3.22 / 29.09 ± 2.52

51.29 ± 1.47 / 66.35 ± 1.70

25.70 ± 4.59 / 55.65 ± 5.87

59.79 ± 1.21 / 65.44 ± 0.76

61.48 ± 1.83 / 47.65 ± 2.94

61.58 ± 2.21 / 50.10 ± 2.68

49.87 ± 1.88 / 66.15 ± 1.44

21.20 ± 6.57 / 52.29 ± 7.43

19.65 ± 4.32 / 56.66 ± 4.40

53.35 ± 4.33 / 74.98 ± 3.70

60.36 ± 2.84 / 39.37 ± 3.56

79.74 ± 0.75 / 75.11 ± 1.91

28.24 ± 4.19 / 55.29 ± 5.35

59.73 ± 1.13 / 65.72 ± 0.94

48.70 ± 3.02 / 34.52 ± 2.66

7.49 ± 2.51 / 43.40 ± 4.41

29.56 ± 5.47 / 55.53 ± 5.79

56.00 ± 1.94 / 43.49 ± 2.05

56.40 ± 3.89 / 70.17 ± 2.91

22.01 ± 5.17 / 56.97 ± 3.54

35.39 ± 2.49 / 64.61 ± 2.42

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

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

12.6.1

meta-llama/Meta-Llama-3-8B-Instruct (few-shot)

8030

128

8192

True

4,909 ± 1,215 / 978 ± 319

2.23

2.14

2.25

2.16

2.82

1.86

2.56

1.80

57.74 ± 2.06 / 40.66 ± 2.58

48.43 ± 3.31 / 62.09 ± 3.62

27.12 ± 2.83 / 60.40 ± 2.70

46.76 ± 1.20 / 59.77 ± 0.51

74.47 ± 1.47 / 65.57 ± 2.39

72.93 ± 1.00 / 65.44 ± 2.55

50.62 ± 3.52 / 65.69 ± 3.50

27.77 ± 1.63 / 61.75 ± 1.77

20.35 ± 1.92 / 57.74 ± 2.28

42.90 ± 3.57 / 69.90 ± 3.17

69.67 ± 1.30 / 52.94 ± 4.01

59.93 ± 4.70 / 67.54 ± 3.04

27.63 ± 3.19 / 60.85 ± 3.29

49.84 ± 1.61 / 60.85 ± 0.93

61.69 ± 2.17 / 41.25 ± 3.12

6.10 ± 1.61 / 48.74 ± 3.05

31.52 ± 2.08 / 58.96 ± 1.57

68.18 ± 0.95 / 57.72 ± 1.15

58.33 ± 2.83 / 69.31 ± 3.16

29.12 ± 3.17 / 63.60 ± 1.63

28.68 ± 1.99 / 56.42 ± 3.34

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

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

12.6.1

cardiffnlp/twitter-xlm-roberta-base

278

250

512

True

34,475 ± 7,465 / 6,712 ± 2,223

2.24

2.13

2.15

1.91

2.71

2.15

2.42

2.21

70.10 ± 1.16 / 64.54 ± 1.00

45.30 ± 2.03 / 63.22 ± 1.47

51.74 ± 2.53 / 74.31 ± 1.94

22.01 ± 2.50 / 27.76 ± 2.44

87.70 ± 0.66 / 85.32 ± 0.94

81.41 ± 1.46 / 77.41 ± 1.57

48.34 ± 2.10 / 60.68 ± 3.61

55.30 ± 2.89 / 75.77 ± 1.87

37.46 ± 2.69 / 67.68 ± 1.66

24.49 ± 6.03 / 35.93 ± 8.56

72.49 ± 1.68 / 67.03 ± 1.55

70.69 ± 1.08 / 67.03 ± 3.40

56.60 ± 3.25 / 76.70 ± 2.48

31.89 ± 1.88 / 37.63 ± 1.86

72.69 ± 0.79 / 73.57 ± 1.02

28.72 ± 5.29 / 60.29 ± 3.57

8.46 ± 0.51 / 31.01 ± 0.72

74.89 ± 0.86 / 73.54 ± 0.84

63.01 ± 1.50 / 75.21 ± 1.03

36.60 ± 2.17 / 64.93 ± 1.39

0.65 ± 0.25 / 5.05 ± 1.30

77.15 ± 1.38 / 81.92 ± 1.32

18.78 ± 6.76 / 37.09 ± 4.14

56.72 ± 3.83 / 77.53 ± 2.17

14.61 ± 4.26 / 20.91 ± 5.21

87.09 ± 0.61 / 87.25 ± 0.49

55.40 ± 0.56 / 52.86 ± 0.29

39.78 ± 3.59 / 67.21 ± 2.02

6.20 ± 4.26 / 13.47 ± 5.29

0.0.0

12.7.0

0.0.0

12.6.1

ZurichNLP/unsup-simcse-xlm-roberta-base

278

250

512

True

34,520 ± 7,443 / 6,730 ± 2,224

2.30

2.37

2.28

2.03

3.51

2.01

1.93

1.96

65.10 ± 1.65 / 61.96 ± 1.26

45.07 ± 1.23 / 63.33 ± 0.78

26.83 ± 11.38 / 60.41 ± 6.66

29.92 ± 1.25 / 35.05 ± 1.16

86.56 ± 1.18 / 87.30 ± 0.95

80.57 ± 1.55 / 83.03 ± 1.19

49.62 ± 2.72 / 62.56 ± 3.88

38.45 ± 15.28 / 67.14 ± 7.71

11.38 ± 7.59 / 51.68 ± 4.73

31.50 ± 2.41 / 47.61 ± 2.55

75.49 ± 1.09 / 74.57 ± 0.60

71.12 ± 0.90 / 60.88 ± 2.58

36.69 ± 15.58 / 65.77 ± 8.64

33.55 ± 2.07 / 38.90 ± 2.21

75.27 ± 1.18 / 76.85 ± 0.94

3.47 ± 1.14 / 47.14 ± 3.33

7.67 ± 0.80 / 32.31 ± 0.81

74.50 ± 1.06 / 74.21 ± 0.83

58.23 ± 1.13 / 72.00 ± 0.75

34.74 ± 14.22 / 64.18 ± 7.54

11.19 ± 3.07 / 26.81 ± 6.54

78.45 ± 1.88 / 83.50 ± 0.85

22.67 ± 7.22 / 44.07 ± 6.51

54.92 ± 9.62 / 76.14 ± 5.00

31.82 ± 2.84 / 40.85 ± 3.02

85.88 ± 0.99 / 86.21 ± 0.87

51.46 ± 1.15 / 51.20 ± 0.50

35.83 ± 11.08 / 65.86 ± 4.95

43.26 ± 1.61 / 55.52 ± 1.60

12.6.1

0.0.0

12.6.1

0.0.0

12.6.1

12.7.0

0.0.0

12.6.1

meta-llama/Llama-2-70b-chat-hf (few-shot, val)

68977

32

4096

True

1,979 ± 621 / 320 ± 105

2.34

2.11

2.48

2.11

3.40

1.94

2.57

1.80

52.22 ± 2.07 / 38.82 ± 1.90

50.66 ± 1.88 / 62.04 ± 2.83

23.57 ± 3.82 / 56.09 ± 4.62

53.82 ± 2.13 / 61.94 ± 1.63

60.21 ± 1.86 / 47.06 ± 3.08

62.99 ± 2.66 / 48.82 ± 5.49

55.12 ± 5.10 / 66.55 ± 5.07

27.12 ± 4.90 / 54.26 ± 6.80

6.82 ± 5.06 / 46.18 ± 4.14

38.50 ± 3.93 / 69.99 ± 2.23

55.91 ± 3.25 / 39.73 ± 4.94

64.52 ± 3.15 / 70.51 ± 2.49

23.85 ± 7.34 / 56.89 ± 6.08

58.88 ± 1.51 / 65.82 ± 1.07

46.32 ± 5.10 / 35.77 ± 3.59

-3.31 ± 3.91 / 38.63 ± 2.52

24.26 ± 4.64 / 55.26 ± 2.41

62.39 ± 2.72 / 50.86 ± 2.31

53.16 ± 3.17 / 64.24 ± 3.42

31.81 ± 5.15 / 62.15 ± 4.02

28.99 ± 2.22 / 60.53 ± 2.92

64.00 ± 3.52 / 48.94 ± 3.83

13.30 ± 3.75 / 30.50 ± 2.48

30.88 ± 4.62 / 59.62 ± 4.50

54.14 ± 1.55 / 70.96 ± 1.01

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

12.7.0

senseable/WestLake-7B-v2 (few-shot)

7242

32

32768

False

5,993 ± 1,028 / 1,742 ± 561

2.42

2.28

2.51

2.31

3.23

2.01

2.64

1.93

52.61 ± 1.77 / 33.64 ± 2.67

49.81 ± 1.43 / 66.32 ± 1.25

19.64 ± 1.63 / 54.22 ± 2.32

48.03 ± 1.24 / 57.94 ± 1.02

64.37 ± 2.17 / 52.81 ± 2.48

62.77 ± 0.83 / 51.80 ± 2.77

50.60 ± 4.90 / 66.76 ± 3.04

18.09 ± 2.04 / 52.56 ± 2.60

12.25 ± 2.18 / 50.79 ± 2.42

38.34 ± 2.39 / 69.54 ± 1.96

58.90 ± 1.34 / 42.48 ± 3.97

67.74 ± 2.79 / 71.89 ± 1.89

16.52 ± 2.55 / 46.30 ± 2.62

49.41 ± 1.21 / 59.91 ± 0.48

56.71 ± 1.98 / 46.71 ± 5.28

3.44 ± 2.02 / 50.18 ± 1.14

21.55 ± 2.79 / 54.79 ± 2.02

64.38 ± 1.60 / 50.26 ± 2.53

54.44 ± 1.45 / 69.32 ± 1.02

26.03 ± 2.23 / 61.88 ± 1.38

25.68 ± 2.81 / 62.48 ± 2.93

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

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

12.6.1

mistralai/Mistral-7B-v0.1 (few-shot)

7242

32

32768

True

2,657 ± 524 / 880 ± 278

2.45

2.41

2.69

2.15

3.19

2.06

2.91

1.77

45.42 ± 2.88 / 32.66 ± 2.49

43.16 ± 1.69 / 54.53 ± 2.83

8.79 ± 3.23 / 38.38 ± 4.22

59.43 ± 1.04 / 64.55 ± 0.68

52.00 ± 1.91 / 43.55 ± 2.21

55.12 ± 3.14 / 45.34 ± 4.15

47.25 ± 4.11 / 64.53 ± 3.71

8.66 ± 4.12 / 38.87 ± 3.40

6.80 ± 1.59 / 39.72 ± 2.50

46.86 ± 3.27 / 70.86 ± 2.79

53.34 ± 2.55 / 40.48 ± 3.66

80.00 ± 0.70 / 79.80 ± 0.66

4.61 ± 2.18 / 34.51 ± 0.86

58.99 ± 1.05 / 64.65 ± 0.83

47.24 ± 2.54 / 37.77 ± 3.87

1.35 ± 1.70 / 39.37 ± 3.87

25.70 ± 5.36 / 49.31 ± 5.21

55.37 ± 1.32 / 44.65 ± 2.48

54.27 ± 1.71 / 68.13 ± 1.16

23.12 ± 4.07 / 57.81 ± 3.70

31.89 ± 3.29 / 59.77 ± 4.31

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

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

0.0.0

12.5.1

0.0.0

12.5.1

0.0.0

12.5.1

9.1.2

12.5.1

9.1.2

12.5.1

9.1.2

12.5.1

9.1.2

12.5.1

google/gemma-7b (few-shot)

8538

256

8192

True

1,378 ± 260 / 387 ± 119

2.46

2.42

2.68

1.95

3.24

2.00

2.96

1.95

19.59 ± 2.54 / 15.47 ± 2.19

46.55 ± 1.89 / 59.52 ± 3.56

32.64 ± 2.91 / 63.84 ± 1.69

59.40 ± 1.02 / 64.81 ± 0.91

26.43 ± 3.36 / 26.32 ± 2.35

32.66 ± 3.42 / 29.43 ± 1.74

41.82 ± 3.69 / 53.06 ± 5.15

25.82 ± 4.43 / 59.85 ± 4.07

20.16 ± 3.43 / 53.83 ± 5.61

52.68 ± 3.58 / 75.16 ± 2.44

43.68 ± 3.65 / 29.40 ± 3.10

77.72 ± 4.50 / 77.58 ± 4.13

36.25 ± 2.66 / 65.08 ± 2.92

58.62 ± 0.98 / 64.23 ± 0.88

30.61 ± 4.61 / 25.80 ± 3.57

5.60 ± 1.68 / 38.26 ± 2.47

32.22 ± 3.19 / 55.22 ± 2.59

39.88 ± 2.56 / 35.40 ± 2.63

56.23 ± 3.17 / 68.87 ± 2.73

32.71 ± 1.60 / 64.55 ± 1.54

36.58 ± 2.81 / 64.92 ± 2.97

47.75 ± 2.33 / 35.64 ± 1.89

7.68 ± 0.61 / 26.25 ± 1.18

28.28 ± 2.48 / 62.81 ± 1.70

61.49 ± 1.15 / 73.19 ± 0.81

47.20 ± 3.34 / 41.96 ± 3.12

63.88 ± 2.24 / 66.49 ± 0.81

35.75 ± 2.65 / 66.41 ± 2.26

69.40 ± 4.29 / 82.46 ± 2.86

12.9.1

mistralai/Mistral-7B-v0.3 (few-shot)

7248

33

32768

True

4,120 ± 976 / 926 ± 306

2.48

2.35

2.71

2.15

3.32

2.11

2.93

1.80

43.60 ± 2.94 / 32.17 ± 2.26

45.92 ± 1.50 / 61.91 ± 1.50

15.43 ± 3.79 / 46.20 ± 5.54

59.13 ± 0.86 / 64.43 ± 0.58

50.56 ± 2.04 / 44.38 ± 1.85

52.65 ± 2.27 / 46.48 ± 3.65

44.61 ± 2.28 / 62.22 ± 2.10

12.10 ± 4.22 / 43.27 ± 5.24

9.30 ± 0.99 / 46.11 ± 3.47

45.15 ± 3.72 / 68.61 ± 3.30

49.18 ± 2.71 / 39.25 ± 3.60

79.08 ± 0.77 / 78.81 ± 0.94

11.06 ± 3.55 / 38.96 ± 3.77

58.98 ± 1.04 / 64.79 ± 0.79

44.68 ± 3.50 / 36.20 ± 4.20

0.12 ± 1.68 / 35.09 ± 1.17

25.52 ± 5.24 / 49.15 ± 5.21

55.41 ± 1.45 / 48.39 ± 1.46

52.58 ± 2.42 / 67.52 ± 1.82

24.10 ± 2.12 / 59.47 ± 2.92

31.52 ± 2.95 / 60.03 ± 3.81

56.52 ± 1.42 / 41.84 ± 1.84

7.02 ± 1.21 / 26.40 ± 2.96

23.41 ± 2.91 / 59.14 ± 3.11

61.90 ± 1.07 / 72.49 ± 1.05

61.02 ± 2.74 / 55.65 ± 2.55

67.29 ± 0.80 / 70.81 ± 0.84

30.10 ± 5.12 / 62.99 ± 4.71

73.59 ± 1.75 / 84.31 ± 1.35

12.10.4

12.10.5

12.10.4

12.10.5

12.10.4

12.10.5

alpindale/Mistral-7B-v0.2-hf (few-shot)

7242

32

32768

True

1,841 ± 297 / 651 ± 193

2.49

2.35

2.70

2.15

3.32

2.18

2.93

1.80

43.65 ± 2.87 / 32.21 ± 2.13

45.86 ± 1.63 / 61.89 ± 1.57

15.19 ± 3.67 / 46.19 ± 5.60

59.14 ± 0.90 / 64.43 ± 0.58

50.63 ± 2.12 / 44.59 ± 1.80

52.69 ± 2.30 / 46.51 ± 3.63

44.05 ± 2.51 / 61.80 ± 2.28

11.60 ± 4.10 / 43.01 ± 5.07

9.26 ± 1.14 / 46.28 ± 3.60

45.23 ± 3.73 / 68.68 ± 3.29

48.96 ± 2.72 / 39.25 ± 3.69

78.90 ± 0.95 / 78.62 ± 1.08

10.82 ± 3.46 / 38.95 ± 3.80

58.91 ± 1.02 / 64.72 ± 0.76

44.85 ± 3.44 / 36.23 ± 4.15

-0.69 ± 2.06 / 35.01 ± 1.14

25.52 ± 5.27 / 49.12 ± 5.22

55.32 ± 1.55 / 48.33 ± 1.45

52.49 ± 2.16 / 67.50 ± 1.61

24.34 ± 2.29 / 59.66 ± 2.93

31.54 ± 3.00 / 59.96 ± 3.89

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

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

12.5.2

12.5.1

12.5.2

12.5.1

12.5.2

12.5.1

12.5.2

microsoft/xlm-align-base

278

250

512

True

14,744 ± 2,870 / 3,265 ± 1,053

2.54

2.44

2.11

2.22

3.29

2.13

2.84

2.72

70.36 ± 2.14 / 65.91 ± 2.15

47.83 ± 1.46 / 65.49 ± 0.96

11.87 ± 5.47 / 48.82 ± 4.15

29.87 ± 3.18 / 35.11 ± 2.73

90.07 ± 1.08 / 87.56 ± 1.39

85.65 ± 0.96 / 82.40 ± 1.16

54.46 ± 1.16 / 68.25 ± 0.76

12.16 ± 5.91 / 50.55 ± 4.73

8.99 ± 2.25 / 48.57 ± 3.67

49.24 ± 1.30 / 64.35 ± 1.24

78.60 ± 1.91 / 73.04 ± 2.25

73.67 ± 1.48 / 68.61 ± 3.14

15.41 ± 4.59 / 53.29 ± 3.93

32.41 ± 3.14 / 37.13 ± 3.07

78.01 ± 2.18 / 79.20 ± 2.10

5.92 ± 1.91 / 46.95 ± 3.38

10.47 ± 1.42 / 43.32 ± 3.55

79.38 ± 0.80 / 79.33 ± 0.74

58.58 ± 2.31 / 72.09 ± 1.64

15.34 ± 5.24 / 52.99 ± 1.90

16.58 ± 6.50 / 32.33 ± 11.35

78.85 ± 2.48 / 83.35 ± 2.28

11.80 ± 7.64 / 33.49 ± 6.73

14.56 ± 8.02 / 53.64 ± 5.14

42.08 ± 7.94 / 51.94 ± 9.08

88.62 ± 0.53 / 88.44 ± 0.46

11.09 ± 10.39 / 33.19 ± 4.75

8.46 ± 2.34 / 51.98 ± 2.86

49.64 ± 1.94 / 62.02 ± 1.77

0.0.0

12.6.1

timpal0l/Mistral-7B-v0.1-flashback-v2 (few-shot)

7242

32

32768

True

5,054 ± 1,200 / 1,056 ± 339

2.55

2.35

2.63

1.96

3.64

2.29

3.09

1.92

42.43 ± 3.36 / 29.30 ± 2.53

47.82 ± 2.00 / 63.19 ± 2.09

16.51 ± 2.59 / 52.73 ± 3.91

56.95 ± 1.21 / 62.20 ± 0.83

48.97 ± 2.42 / 39.15 ± 2.78

51.52 ± 2.96 / 40.17 ± 3.62

49.05 ± 2.73 / 63.94 ± 2.42

14.37 ± 2.18 / 47.80 ± 4.36

9.96 ± 1.34 / 48.97 ± 3.77

44.07 ± 3.40 / 68.49 ± 2.97

44.14 ± 2.40 / 29.77 ± 4.06

80.14 ± 1.11 / 80.19 ± 0.78

34.23 ± 2.23 / 65.29 ± 2.17

57.07 ± 1.56 / 62.52 ± 1.11

36.47 ± 4.24 / 30.33 ± 3.70

2.54 ± 1.29 / 50.66 ± 0.62

18.66 ± 4.26 / 38.73 ± 3.66

50.66 ± 1.53 / 39.89 ± 2.43

54.79 ± 3.53 / 68.79 ± 3.00

20.17 ± 1.69 / 58.67 ± 1.13

27.86 ± 4.70 / 54.38 ± 5.91

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

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

12.5.3

Twitter/twhin-bert-base

279

250

512

True

11,514 ± 2,041 / 2,862 ± 918

2.57

2.44

2.68

2.11

3.26

2.21

3.10

2.19

60.01 ± 2.63 / 56.13 ± 2.46

42.17 ± 1.64 / 61.25 ± 1.45

29.43 ± 13.02 / 62.08 ± 7.77

29.79 ± 3.33 / 34.82 ± 2.83

84.11 ± 1.00 / 81.35 ± 1.22

77.22 ± 1.99 / 73.67 ± 2.26

37.02 ± 1.09 / 47.88 ± 2.50

35.42 ± 12.32 / 66.30 ± 6.78

6.87 ± 6.85 / 50.70 ± 3.62

25.98 ± 2.87 / 36.16 ± 3.35

70.17 ± 0.99 / 64.19 ± 1.42

66.62 ± 1.71 / 61.90 ± 2.61

46.72 ± 3.65 / 72.15 ± 2.62

31.38 ± 1.36 / 35.79 ± 1.33

70.38 ± 1.44 / 72.00 ± 1.13

11.09 ± 6.94 / 51.60 ± 5.19

7.67 ± 0.74 / 30.52 ± 0.52

70.35 ± 1.34 / 69.09 ± 1.36

55.03 ± 2.38 / 69.65 ± 1.75

43.87 ± 8.85 / 69.71 ± 6.73

2.81 ± 0.73 / 10.15 ± 2.34

74.03 ± 3.05 / 80.59 ± 2.24

9.53 ± 5.28 / 32.06 ± 4.17

39.12 ± 12.90 / 68.36 ± 6.85

7.71 ± 0.42 / 12.90 ± 0.39

87.77 ± 0.51 / 87.83 ± 0.47

41.09 ± 4.38 / 48.17 ± 3.16

32.26 ± 10.79 / 61.20 ± 5.53

35.15 ± 1.89 / 44.98 ± 1.93

12.6.1

0.0.0

12.6.1

0.0.0

12.6.1

0.0.0

12.6.1

sentence-transformers/paraphrase-xlm-r-multilingual-v1

278

250

512

True

20,154 ± 4,438 / 3,890 ± 1,256

2.60

2.39

2.74

2.30

3.63

2.53

2.44

2.17

61.17 ± 2.09 / 58.41 ± 2.11

46.39 ± 1.25 / 63.97 ± 1.08

38.61 ± 1.86 / 67.08 ± 1.08

19.90 ± 1.09 / 25.77 ± 1.12

81.26 ± 1.25 / 77.69 ± 1.29

74.05 ± 1.72 / 69.84 ± 1.91

49.93 ± 1.46 / 62.37 ± 2.34

38.26 ± 7.56 / 66.01 ± 3.69

25.17 ± 5.32 / 61.27 ± 3.01

0.00 ± 0.00 / 0.00 ± 0.00

70.22 ± 1.49 / 63.97 ± 1.48

71.33 ± 1.20 / 65.44 ± 3.64

39.60 ± 5.87 / 66.60 ± 3.19

18.65 ± 1.15 / 24.75 ± 0.98

65.15 ± 1.02 / 67.50 ± 0.90

1.15 ± 1.57 / 49.60 ± 0.88

9.56 ± 0.42 / 27.88 ± 0.44

69.45 ± 0.82 / 68.02 ± 0.87

57.94 ± 2.12 / 71.92 ± 1.45

21.81 ± 12.05 / 58.13 ± 4.73

0.33 ± 0.15 / 3.03 ± 1.06

70.59 ± 1.60 / 78.25 ± 1.22

21.37 ± 8.79 / 40.62 ± 7.64

45.86 ± 2.06 / 71.32 ± 1.40

5.20 ± 0.30 / 10.40 ± 0.38

84.05 ± 0.61 / 84.48 ± 0.51

54.92 ± 1.28 / 52.65 ± 0.58

45.85 ± 1.41 / 71.78 ± 0.82

4.13 ± 0.19 / 10.53 ± 0.24

0.0.0

12.6.1

12.8.0

0.0.0

12.6.1

meta-llama/Llama-2-13b-hf (few-shot)

13016

32

4096

True

2,898 ± 637 / 736 ± 236

2.63

2.70

2.95

2.02

3.54

2.27

3.04

1.90

41.28 ± 3.92 / 31.98 ± 3.26

23.01 ± 3.87 / 36.55 ± 6.42

23.50 ± 2.75 / 58.11 ± 3.45

60.29 ± 0.81 / 65.52 ± 0.58

51.12 ± 3.13 / 47.26 ± 2.62

55.35 ± 1.60 / 49.99 ± 2.21

23.75 ± 3.25 / 42.92 ± 4.45

14.00 ± 4.25 / 42.71 ± 5.83

7.61 ± 2.57 / 45.86 ± 3.96

49.24 ± 4.28 / 72.68 ± 3.66

54.52 ± 3.33 / 44.11 ± 5.29

78.45 ± 1.21 / 79.73 ± 0.97

21.55 ± 3.74 / 49.54 ± 4.41

59.71 ± 0.68 / 65.01 ± 0.64

36.56 ± 3.03 / 34.23 ± 3.45

1.73 ± 1.56 / 45.02 ± 2.05

21.97 ± 4.26 / 46.27 ± 3.94

52.08 ± 1.86 / 46.67 ± 1.17

46.38 ± 2.70 / 60.32 ± 2.80

22.39 ± 3.96 / 57.26 ± 4.22

33.43 ± 2.38 / 62.65 ± 2.83

52.55 ± 1.64 / 43.32 ± 1.70

4.26 ± 2.09 / 28.32 ± 2.68

24.57 ± 3.54 / 54.94 ± 5.33

60.99 ± 0.95 / 72.74 ± 0.78

63.75 ± 2.50 / 59.28 ± 2.20

61.85 ± 1.70 / 69.02 ± 0.76

26.41 ± 4.93 / 59.67 ± 4.84

73.48 ± 2.06 / 85.27 ± 1.15

12.10.5

12.10.4

12.10.5

12.10.4

12.10.5

12.10.4

12.10.5

12.10.4

12.10.5

12.10.4

12.10.5

12.10.4

12.10.5

12.10.4

12.10.5

mistralai/Mistral-7B-Instruct-v0.2 (few-shot)

7242

32

32768

False

634 ± 179 / 110 ± 35

2.64

2.38

2.84

2.38

3.52

2.37

2.93

2.04

44.89 ± 2.46 / 29.13 ± 1.92

48.09 ± 1.00 / 65.40 ± 0.75

19.06 ± 2.34 / 58.77 ± 1.37

51.56 ± 1.16 / 60.81 ± 0.74

53.42 ± 2.48 / 42.63 ± 1.66

54.34 ± 1.93 / 41.06 ± 2.40

38.79 ± 2.56 / 53.72 ± 3.01

17.06 ± 1.53 / 56.51 ± 2.06

11.00 ± 1.00 / 53.26 ± 2.32

35.74 ± 2.44 / 64.27 ± 2.42

47.92 ± 2.66 / 33.00 ± 3.24

62.90 ± 2.44 / 70.61 ± 1.19

19.95 ± 2.24 / 56.49 ± 2.10

52.51 ± 0.36 / 61.42 ± 0.52

43.11 ± 2.23 / 29.34 ± 3.27

3.40 ± 1.87 / 48.75 ± 1.47

19.18 ± 3.69 / 49.62 ± 2.59

55.10 ± 1.35 / 41.89 ± 1.61

47.69 ± 2.35 / 64.93 ± 1.71

24.14 ± 2.09 / 60.83 ± 1.63

23.93 ± 2.11 / 57.64 ± 1.89

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

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

9.2.0

9.3.1

12.4.0

9.2.0

9.3.1

12.4.0

9.2.0

9.3.1

12.4.0

9.2.0

9.3.1

12.4.0

12.9.0

9.3.1

9.2.0

9.3.1

12.4.0

9.3.1

9.2.0

9.3.1

12.4.0

RuterNorway/Llama-2-13b-chat-norwegian (few-shot)

unknown

32

4096

False

3,254 ± 1,068 / 484 ± 173

2.65

2.46

2.87

2.27

3.75

2.33

2.98

1.91

43.17 ± 2.78 / 31.37 ± 2.95

43.40 ± 2.20 / 57.24 ± 3.52

11.08 ± 2.98 / 43.40 ± 4.66

56.81 ± 0.70 / 63.10 ± 0.35

58.61 ± 1.58 / 47.74 ± 2.83

60.40 ± 1.25 / 47.53 ± 2.68

41.36 ± 3.50 / 58.47 ± 3.79

6.52 ± 2.11 / 38.10 ± 2.56

3.95 ± 2.52 / 42.37 ± 4.20

38.93 ± 2.43 / 65.76 ± 3.07

50.85 ± 2.44 / 39.65 ± 3.83

74.17 ± 2.12 / 76.62 ± 1.83

7.51 ± 1.94 / 37.81 ± 1.76

57.32 ± 0.63 / 63.28 ± 0.71

28.35 ± 2.89 / 26.44 ± 2.75

3.14 ± 1.74 / 44.57 ± 3.85

19.80 ± 2.66 / 43.44 ± 1.74

57.02 ± 1.39 / 47.95 ± 2.09

49.75 ± 2.02 / 62.41 ± 3.30

19.80 ± 3.22 / 52.76 ± 5.45

27.86 ± 2.01 / 57.65 ± 2.01

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

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

9.3.1

12.9.0

9.3.1

occiglot/occiglot-7b-eu5-instruct (few-shot)

7242

32

32768

False

2,088 ± 352 / 706 ± 214

2.66

2.64

2.84

2.33

3.62

2.08

3.04

2.04

40.19 ± 2.55 / 29.73 ± 1.44

42.31 ± 1.55 / 59.29 ± 2.00

1.14 ± 1.22 / 33.83 ± 0.72

57.89 ± 1.16 / 63.95 ± 0.82

45.50 ± 2.71 / 40.02 ± 3.16

45.96 ± 2.67 / 41.28 ± 2.25

44.46 ± 3.40 / 62.00 ± 2.71

0.00 ± 0.00 / 33.41 ± 0.30

0.00 ± 0.00 / 33.86 ± 0.33

52.19 ± 2.88 / 74.97 ± 2.11

47.67 ± 2.81 / 36.91 ± 3.50

71.73 ± 2.40 / 74.97 ± 1.84

7.90 ± 3.20 / 41.24 ± 4.78

57.78 ± 0.79 / 64.48 ± 0.73

40.71 ± 2.93 / 34.57 ± 4.02

0.71 ± 2.00 / 36.90 ± 2.10

20.66 ± 3.67 / 45.91 ± 3.45

52.63 ± 1.89 / 42.99 ± 2.40

43.16 ± 4.45 / 57.79 ± 4.61

27.09 ± 1.92 / 60.29 ± 1.99

34.01 ± 4.01 / 63.29 ± 3.97

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

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

12.5.2

12.2.0

12.3.1

12.4.0

12.5.2

12.2.0

12.3.1

12.4.0

12.5.2

12.2.0

12.3.1

12.4.0

12.5.2

12.3.1

12.4.0

12.5.2

12.2.0

12.3.1

12.4.0

12.5.2

12.2.0

12.3.1

12.4.0

12.5.2

12.2.0

12.3.1

12.4.0

microsoft/Phi-3-mini-4k-instruct (few-shot)

3821

32

4096

True

5,224 ± 1,371 / 1,063 ± 358

2.68

2.70

3.03

2.53

3.68

1.98

3.02

1.83

41.37 ± 2.50 / 24.64 ± 2.50

42.60 ± 1.06 / 61.52 ± 0.75

6.52 ± 1.34 / 45.01 ± 2.64

50.57 ± 1.03 / 57.75 ± 0.64

56.33 ± 1.63 / 36.68 ± 3.27

54.68 ± 1.29 / 37.85 ± 3.79

37.18 ± 1.30 / 55.44 ± 1.46

6.76 ± 2.81 / 41.69 ± 2.82

6.79 ± 1.51 / 45.45 ± 3.51

30.11 ± 2.09 / 52.56 ± 2.38

46.15 ± 2.77 / 24.28 ± 3.74

67.17 ± 1.93 / 70.99 ± 1.64

5.30 ± 1.62 / 47.01 ± 3.23

51.12 ± 1.02 / 57.49 ± 0.81

33.05 ± 4.29 / 29.75 ± 3.67

0.71 ± 1.18 / 34.80 ± 0.88

17.23 ± 2.51 / 39.88 ± 1.59

59.68 ± 0.41 / 48.00 ± 2.44

54.75 ± 2.36 / 68.54 ± 1.62

30.22 ± 2.94 / 64.51 ± 1.55

29.27 ± 1.03 / 59.19 ± 2.46

50.31 ± 1.94 / 41.54 ± 2.19

12.58 ± 1.62 / 36.56 ± 1.79

14.72 ± 1.84 / 50.23 ± 3.10

56.19 ± 0.80 / 66.72 ± 0.92

66.13 ± 1.16 / 53.55 ± 2.73

63.66 ± 1.31 / 70.60 ± 0.63

34.07 ± 2.32 / 66.51 ± 1.23

68.10 ± 1.44 / 83.46 ± 1.01

12.10.5

12.10.4

12.10.5

sentence-transformers/stsb-xlm-r-multilingual

278

250

512

True

15,040 ± 2,953 / 3,417 ± 1,100

2.68

2.50

2.76

2.28

3.68

2.48

2.90

2.17

58.52 ± 1.78 / 55.04 ± 1.60

42.26 ± 1.13 / 61.41 ± 0.76

34.80 ± 5.89 / 64.51 ± 4.90

19.60 ± 1.60 / 25.68 ± 1.48

80.08 ± 1.46 / 75.93 ± 1.64

74.59 ± 1.98 / 70.26 ± 2.24

52.16 ± 0.99 / 66.79 ± 0.98

36.30 ± 6.44 / 65.52 ± 3.06

14.21 ± 6.44 / 52.78 ± 5.69

0.00 ± 0.00 / 0.00 ± 0.00

68.94 ± 1.53 / 62.54 ± 1.20

72.77 ± 0.89 / 68.13 ± 1.56

40.21 ± 2.53 / 67.11 ± 1.86

20.09 ± 1.31 / 25.99 ± 1.19

66.23 ± 1.24 / 67.76 ± 1.08

0.04 ± 0.78 / 45.96 ± 2.83

10.04 ± 0.99 / 28.66 ± 0.92

67.47 ± 1.09 / 66.34 ± 1.08

52.85 ± 1.53 / 68.48 ± 1.02

29.59 ± 6.40 / 60.98 ± 2.57

0.73 ± 0.17 / 4.35 ± 1.32

66.85 ± 1.32 / 72.84 ± 0.82

20.56 ± 1.44 / 39.67 ± 0.86

35.56 ± 1.76 / 66.00 ± 1.15

5.04 ± 0.46 / 10.13 ± 0.40

82.39 ± 0.62 / 83.07 ± 0.48

57.35 ± 1.00 / 54.82 ± 0.65

47.29 ± 2.10 / 71.85 ± 1.30

4.29 ± 0.33 / 10.53 ± 0.29

0.0.0

12.8.0

0.0.0

12.6.1

Twitter/twhin-bert-large

561

250

512

True

9,707 ± 1,664 / 2,549 ± 831

2.69

2.60

2.95

2.34

3.55

2.26

3.15

2.00

66.39 ± 1.42 / 62.24 ± 1.29

39.36 ± 3.13 / 58.64 ± 2.64

7.06 ± 6.11 / 49.71 ± 4.63

33.88 ± 4.27 / 38.42 ± 4.16

86.26 ± 0.71 / 83.48 ± 1.19

80.10 ± 2.44 / 76.17 ± 2.67

34.17 ± 2.42 / 43.74 ± 2.19

12.11 ± 10.47 / 50.33 ± 7.16

4.28 ± 4.18 / 45.75 ± 4.32

11.74 ± 10.45 / 16.38 ± 14.33

74.26 ± 1.65 / 68.20 ± 1.70

63.35 ± 5.43 / 60.33 ± 5.50

16.07 ± 10.73 / 52.48 ± 7.50

36.77 ± 3.78 / 41.72 ± 3.83

71.48 ± 1.97 / 73.71 ± 1.37

2.20 ± 2.00 / 43.42 ± 4.87

8.19 ± 0.76 / 33.02 ± 1.85

74.36 ± 1.33 / 73.61 ± 1.47

53.52 ± 2.28 / 68.49 ± 1.49

22.26 ± 11.63 / 58.51 ± 6.63

11.68 ± 4.11 / 22.54 ± 7.80

77.35 ± 2.80 / 82.50 ± 1.87

6.55 ± 5.33 / 28.68 ± 3.64

18.25 ± 8.41 / 54.00 ± 5.57

28.37 ± 4.84 / 36.84 ± 5.92

89.50 ± 0.47 / 89.39 ± 0.41

45.98 ± 2.97 / 49.81 ± 2.03

30.58 ± 13.07 / 61.93 ± 7.87

48.44 ± 1.37 / 59.47 ± 1.12

0.0.0

12.7.0

0.0.0

12.6.1

mistralai/Mistral-7B-Instruct-v0.1 (few-shot)

7242

32

32768

False

634 ± 179 / 110 ± 35

2.72

2.53

2.84

2.38

3.74

2.43

3.15

1.96

37.93 ± 2.71 / 23.54 ± 1.99

44.49 ± 2.56 / 60.64 ± 3.00

14.09 ± 2.94 / 42.43 ± 3.30

51.38 ± 2.31 / 58.78 ± 1.27

50.08 ± 1.54 / 34.52 ± 1.17

51.27 ± 1.52 / 33.37 ± 2.37

43.65 ± 1.98 / 60.88 ± 1.36

14.09 ± 2.85 / 44.91 ± 3.95

8.28 ± 1.82 / 47.22 ± 3.72

37.23 ± 3.15 / 63.67 ± 2.98

45.01 ± 2.11 / 27.59 ± 3.35

73.33 ± 1.98 / 76.19 ± 1.59

11.59 ± 3.45 / 40.89 ± 4.15

52.12 ± 1.42 / 59.29 ± 1.17

36.04 ± 2.59 / 24.74 ± 2.79

-0.36 ± 1.36 / 33.94 ± 0.32

18.06 ± 3.16 / 42.57 ± 2.89

47.19 ± 3.74 / 33.02 ± 2.09

47.26 ± 3.14 / 63.48 ± 2.94

22.32 ± 1.78 / 56.73 ± 4.00

24.36 ± 3.78 / 54.61 ± 4.44

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

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

9.3.1

12.4.0

9.3.1

12.4.0

9.3.1

12.4.0

9.3.1

12.4.0

12.9.0

9.3.1

12.4.0

9.3.1

12.4.0

occiglot/occiglot-7b-eu5 (few-shot)

7242

32

32768

True

2,219 ± 427 / 717 ± 224

2.72

2.62

2.89

2.27

3.77

2.26

3.12

2.11

37.93 ± 3.09 / 29.50 ± 2.18

44.62 ± 1.98 / 62.62 ± 1.54

0.28 ± 0.54 / 33.48 ± 0.24

58.05 ± 1.02 / 62.89 ± 0.89

45.28 ± 3.06 / 41.73 ± 2.14

46.00 ± 4.26 / 42.96 ± 3.38

44.95 ± 3.19 / 61.88 ± 2.88

0.00 ± 0.00 / 33.41 ± 0.30

0.00 ± 0.00 / 33.86 ± 0.33

43.88 ± 4.07 / 66.65 ± 4.20

49.02 ± 3.23 / 41.69 ± 3.74

76.56 ± 1.52 / 78.16 ± 1.12

2.18 ± 2.34 / 36.26 ± 3.89

58.98 ± 0.95 / 63.65 ± 0.89

40.08 ± 2.82 / 37.15 ± 4.07

1.59 ± 1.86 / 39.93 ± 4.19

15.98 ± 3.74 / 39.67 ± 3.36

51.39 ± 1.35 / 44.47 ± 2.77

47.30 ± 4.44 / 62.28 ± 4.24

21.83 ± 1.98 / 57.05 ± 2.18

31.55 ± 3.67 / 60.39 ± 4.29

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

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

12.5.2

12.1.0

12.5.2

12.1.0

12.5.2

12.1.0

12.5.2

12.1.0

12.5.2

12.1.0

12.5.2

12.1.0

12.5.2

12.1.0

Geotrend/distilbert-base-25lang-cased

109

85

512

True

26,099 ± 5,881 / 5,178 ± 1,665

2.73

2.67

2.40

3.70

2.43

2.94

2.30

58.44 ± 2.08 / 55.32 ± 1.81

31.81 ± 1.65 / 53.25 ± 1.65

34.13 ± 2.81 / 65.98 ± 2.30

27.60 ± 1.58 / 32.18 ± 1.64

83.59 ± 1.36 / 80.55 ± 1.53

80.29 ± 1.02 / 76.08 ± 1.06

33.19 ± 1.75 / 46.63 ± 2.55

32.60 ± 6.93 / 65.19 ± 3.31

24.97 ± 6.47 / 61.39 ± 3.34

19.93 ± 1.76 / 30.69 ± 2.36

70.56 ± 1.36 / 64.49 ± 1.43

60.69 ± 0.46 / 56.69 ± 1.35

30.83 ± 1.47 / 63.39 ± 1.60

31.41 ± 1.05 / 36.45 ± 1.05

65.76 ± 0.98 / 68.15 ± 0.89

2.08 ± 1.89 / 48.68 ± 2.96

6.81 ± 0.33 / 30.96 ± 0.65

72.97 ± 0.68 / 71.83 ± 0.80

41.51 ± 1.91 / 60.79 ± 1.27

45.39 ± 1.52 / 71.60 ± 0.73

1.89 ± 0.52 / 6.88 ± 1.73

75.02 ± 1.48 / 81.57 ± 0.76

7.45 ± 2.99 / 29.70 ± 1.94

45.28 ± 0.55 / 71.89 ± 0.59

20.18 ± 1.26 / 27.86 ± 1.48

87.08 ± 0.62 / 87.08 ± 0.57

36.77 ± 1.52 / 45.15 ± 0.60

37.10 ± 1.79 / 67.20 ± 1.15

26.99 ± 0.77 / 37.98 ± 0.63

0.0.0

12.6.1

0.0.0

12.6.1

meta-llama/Llama-2-7b-hf (few-shot)

6738

32

4096

True

930 ± 310 / 128 ± 43

2.78

2.71

2.99

2.28

3.74

2.44

3.21

2.11

31.77 ± 3.29 / 22.31 ± 2.29

43.91 ± 1.94 / 61.54 ± 2.33

0.31 ± 0.61 / 33.43 ± 0.23

58.44 ± 0.83 / 63.54 ± 0.66

42.13 ± 3.82 / 37.17 ± 3.44

43.80 ± 2.85 / 37.48 ± 4.00

41.74 ± 2.25 / 57.91 ± 2.82

0.00 ± 0.00 / 33.41 ± 0.30

0.02 ± 0.04 / 33.88 ± 0.35

44.19 ± 4.13 / 66.18 ± 4.05

44.11 ± 4.26 / 31.64 ± 4.48

79.05 ± 1.08 / 75.52 ± 2.66

7.34 ± 3.19 / 43.83 ± 5.31

57.49 ± 0.95 / 63.16 ± 0.77

32.71 ± 2.77 / 32.17 ± 2.13

0.66 ± 1.75 / 40.36 ± 4.19

18.04 ± 4.05 / 41.40 ± 3.27

43.02 ± 1.93 / 32.69 ± 1.98

50.21 ± 2.43 / 65.81 ± 1.82

15.79 ± 2.35 / 53.25 ± 4.45

28.57 ± 5.09 / 55.54 ± 6.14

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

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

9.2.0

12.5.1

9.2.0

12.5.1

9.2.0

12.5.1

9.2.0

12.5.1

12.8.0

9.2.0

12.5.1

9.2.0

12.5.1

meta-llama/Llama-2-7b-chat-hf (few-shot)

6738

32

4096

False

2,643 ± 455 / 800 ± 247

2.81

2.57

3.07

2.52

3.82

2.51

3.16

2.03

35.44 ± 3.00 / 24.63 ± 1.65

44.88 ± 1.45 / 62.35 ± 1.33

9.74 ± 1.96 / 47.42 ± 4.19

55.04 ± 0.79 / 61.34 ± 0.81

44.99 ± 2.49 / 38.59 ± 2.84

49.09 ± 1.90 / 39.09 ± 4.02

41.56 ± 3.37 / 57.09 ± 3.80

3.04 ± 2.84 / 36.81 ± 2.42

4.03 ± 2.49 / 40.55 ± 4.14

33.77 ± 2.11 / 61.99 ± 2.34

39.72 ± 2.82 / 29.85 ± 2.99

66.18 ± 3.25 / 72.00 ± 1.75

6.74 ± 1.66 / 45.55 ± 4.31

54.05 ± 0.84 / 60.90 ± 0.82

41.10 ± 3.35 / 40.54 ± 3.19

-1.07 ± 2.09 / 44.83 ± 2.20

16.13 ± 2.52 / 39.51 ± 1.98

50.09 ± 1.33 / 38.59 ± 1.66

46.52 ± 2.85 / 63.64 ± 2.10

15.23 ± 1.71 / 55.08 ± 1.88

25.54 ± 3.58 / 56.07 ± 3.76

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

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

9.3.1

12.4.0

9.3.1

12.4.0

9.3.1

12.4.0

9.3.1

12.4.0

12.9.0

12.10.0

9.3.1

12.4.0

9.3.1

12.4.0

google/gemma-7b-it (few-shot)

8538

256

8192

False

1,792 ± 249 / 668 ± 203

2.84

2.82

2.79

2.88

3.58

2.84

3.08

1.91

43.83 ± 1.93 / 34.03 ± 1.59

29.21 ± 1.92 / 52.86 ± 1.54

12.96 ± 1.67 / 55.83 ± 0.88

49.76 ± 0.59 / 56.52 ± 0.50

59.77 ± 2.77 / 56.12 ± 2.72

60.98 ± 2.01 / 57.99 ± 1.31

28.14 ± 1.90 / 49.76 ± 1.59

14.01 ± 2.15 / 56.43 ± 1.08

10.15 ± 1.06 / 54.56 ± 0.71

51.08 ± 2.83 / 74.34 ± 1.55

59.26 ± 2.00 / 52.73 ± 2.71

28.63 ± 1.24 / 50.95 ± 0.75

11.43 ± 1.88 / 53.31 ± 1.74

46.67 ± 1.97 / 53.24 ± 1.72

37.69 ± 3.97 / 34.52 ± 3.74

3.11 ± 1.49 / 48.48 ± 2.77

18.34 ± 2.07 / 43.26 ± 1.28

54.20 ± 1.00 / 48.58 ± 1.53

15.43 ± 3.70 / 43.11 ± 2.77

17.49 ± 1.23 / 57.46 ± 1.12

28.68 ± 5.36 / 60.07 ± 4.46

53.93 ± 2.71 / 47.48 ± 2.09

12.83 ± 2.37 / 34.00 ± 2.26

6.58 ± 3.36 / 48.51 ± 3.35

53.45 ± 2.52 / 67.47 ± 0.88

66.70 ± 0.99 / 61.08 ± 1.16

55.62 ± 2.54 / 64.98 ± 2.03

31.36 ± 2.63 / 65.21 ± 1.16

72.58 ± 0.68 / 84.67 ± 0.91

12.7.0

12.10.0

12.7.0

12.10.0

Qwen/Qwen1.5-4B-Chat (few-shot)

3950

152

32768

False

4,347 ± 893 / 1,135 ± 365

2.87

2.66

3.09

2.60

4.00

2.64

3.11

1.99

35.96 ± 2.61 / 28.58 ± 2.58

42.04 ± 1.42 / 60.76 ± 1.41

8.65 ± 1.52 / 49.56 ± 3.60

53.68 ± 0.94 / 59.73 ± 0.86

44.83 ± 1.58 / 40.11 ± 2.00

46.29 ± 1.65 / 41.63 ± 3.45

32.70 ± 1.59 / 45.73 ± 2.82

3.57 ± 1.55 / 37.05 ± 2.34

1.61 ± 2.11 / 37.85 ± 3.99

42.55 ± 3.36 / 67.11 ± 2.50

40.19 ± 2.97 / 31.88 ± 4.51

64.08 ± 2.44 / 69.62 ± 1.29

5.43 ± 2.02 / 38.32 ± 2.54

53.21 ± 1.08 / 59.57 ± 0.97

25.65 ± 2.99 / 22.30 ± 2.30

-0.35 ± 2.01 / 44.36 ± 4.13

14.46 ± 2.66 / 32.31 ± 1.66

42.08 ± 1.65 / 36.90 ± 2.00

41.52 ± 3.53 / 57.69 ± 3.35

12.78 ± 3.75 / 46.43 ± 5.48

29.35 ± 2.51 / 59.90 ± 2.80

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

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

12.5.2

10.0.1

12.1.0

12.5.2

10.0.1

12.1.0

12.5.2

10.0.1

12.1.0

12.5.2

12.1.0

12.5.2

10.0.1

12.1.0

12.5.2

10.0.1

12.1.0

12.5.2

10.0.1

12.1.0

12.5.2

microsoft/Phi-3-mini-128k-instruct (few-shot)

3821

32

131072

True

7,312 ± 1,668 / 1,609 ± 525

2.88

3.16

3.07

2.81

3.80

2.13

3.10

2.07

4.51 ± 2.12 / 3.71 ± 1.76

40.85 ± 1.26 / 59.79 ± 1.32

5.43 ± 1.74 / 46.21 ± 4.13

51.76 ± 0.73 / 58.44 ± 0.54

52.18 ± 2.03 / 29.83 ± 3.23

50.53 ± 1.49 / 31.94 ± 4.20

33.30 ± 2.01 / 51.15 ± 2.93

2.63 ± 2.56 / 40.21 ± 3.98

4.00 ± 1.87 / 44.87 ± 3.17

37.08 ± 2.44 / 61.14 ± 2.01

42.36 ± 1.67 / 21.33 ± 2.90

51.53 ± 6.32 / 62.14 ± 3.43

3.11 ± 1.60 / 47.93 ± 2.93

51.11 ± 0.96 / 57.21 ± 0.95

27.22 ± 3.65 / 24.21 ± 2.67

1.31 ± 1.28 / 39.67 ± 4.39

17.24 ± 2.72 / 41.15 ± 1.57

55.36 ± 0.81 / 36.14 ± 1.96

53.05 ± 2.34 / 65.57 ± 1.92

23.08 ± 1.54 / 58.65 ± 2.04

31.55 ± 1.09 / 62.02 ± 2.17

44.27 ± 2.14 / 34.47 ± 2.48

12.84 ± 1.82 / 36.64 ± 1.13

10.44 ± 1.58 / 48.93 ± 3.41

56.40 ± 1.14 / 68.02 ± 0.79

64.09 ± 0.96 / 49.92 ± 2.47

46.77 ± 4.36 / 60.99 ± 2.15

31.62 ± 2.25 / 63.73 ± 1.79

71.25 ± 0.83 / 85.72 ± 0.57

12.9.1

AI-Sweden-Models/gpt-sw3-20b (few-shot)

20918

64

2048

True

1,875 ± 673 / 261 ± 91

2.96

2.93

3.05

2.42

3.38

3.23

3.32

2.42

27.41 ± 3.48 / 19.03 ± 1.76

30.23 ± 3.43 / 41.05 ± 4.38

11.34 ± 2.73 / 46.62 ± 5.48

52.80 ± 0.68 / 59.56 ± 0.57

30.82 ± 5.81 / 25.27 ± 3.92

39.56 ± 4.73 / 32.12 ± 4.06

34.50 ± 1.29 / 42.21 ± 1.39

15.17 ± 1.41 / 49.46 ± 2.90

12.46 ± 3.29 / 48.89 ± 5.19

42.81 ± 3.10 / 66.15 ± 3.21

31.86 ± 5.09 / 21.95 ± 3.90

79.20 ± 1.03 / 79.87 ± 1.11

12.26 ± 1.97 / 46.90 ± 4.11

53.58 ± 0.97 / 60.28 ± 0.81

27.54 ± 3.01 / 23.54 ± 2.16

4.61 ± 1.64 / 41.57 ± 3.41

28.12 ± 3.77 / 54.61 ± 3.42

36.17 ± 2.52 / 27.29 ± 1.74

34.17 ± 7.08 / 46.97 ± 8.28

2.21 ± 1.64 / 38.29 ± 3.56

13.60 ± 3.04 / 30.89 ± 4.33

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

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

9.3.1

12.10.0

9.3.1

12.10.0

9.3.1

12.10.0

9.3.1

12.9.0

9.3.1

allenai/OLMo-1.7-7B-hf (few-shot)

6888

50

4096

True

3,371 ± 876 / 561 ± 184

2.96

2.95

3.11

2.39

3.80

2.71

3.38

2.36

33.80 ± 2.66 / 25.32 ± 3.06

31.57 ± 2.65 / 46.48 ± 3.84

2.76 ± 1.76 / 44.96 ± 3.93

54.20 ± 1.63 / 59.50 ± 1.54

42.78 ± 1.09 / 37.34 ± 1.81

42.85 ± 1.93 / 37.34 ± 3.04

36.68 ± 2.11 / 46.78 ± 2.71

2.39 ± 1.54 / 43.99 ± 3.66

1.91 ± 1.37 / 44.20 ± 4.28

39.16 ± 2.56 / 62.28 ± 2.34

41.25 ± 2.07 / 32.87 ± 2.49

76.60 ± 0.98 / 64.63 ± 2.41

6.37 ± 2.08 / 49.55 ± 3.34

54.87 ± 0.64 / 61.35 ± 0.68

27.44 ± 3.28 / 23.50 ± 3.29

1.46 ± 1.18 / 41.20 ± 3.25

17.26 ± 3.80 / 39.06 ± 3.00

39.41 ± 2.30 / 36.17 ± 2.32

49.42 ± 4.33 / 61.57 ± 5.43

6.02 ± 2.53 / 46.41 ± 4.35

27.69 ± 4.39 / 54.92 ± 5.38

46.95 ± 2.32 / 36.13 ± 1.88

4.34 ± 2.10 / 19.37 ± 2.08

3.46 ± 1.91 / 41.32 ± 3.08

57.07 ± 0.89 / 68.14 ± 0.65

41.02 ± 3.86 / 40.03 ± 2.56

66.43 ± 0.78 / 57.25 ± 0.33

5.17 ± 1.55 / 37.03 ± 2.40

76.04 ± 0.97 / 85.31 ± 0.82

12.10.5

12.10.4

12.10.5

12.10.4

12.10.5

12.10.4

12.10.5

12.10.4

12.10.5

12.10.4

12.10.5

12.10.4

12.10.5

12.10.4

12.10.5

01-ai/Yi-6B (few-shot)

6061

64

4096

True

6,435 ± 1,316 / 1,632 ± 549

3.03

3.40

3.00

2.41

4.14

3.03

3.30

1.95

35.08 ± 2.24 / 25.02 ± 2.03

4.00 ± 2.43 / 18.67 ± 0.94

3.68 ± 2.25 / 35.69 ± 1.87

55.09 ± 0.79 / 60.88 ± 0.55

43.44 ± 1.89 / 33.41 ± 2.21

46.33 ± 3.12 / 34.05 ± 2.27

38.96 ± 2.34 / 56.27 ± 3.65

0.75 ± 1.07 / 33.42 ± 0.29

1.04 ± 1.93 / 33.14 ± 0.66

40.28 ± 3.58 / 62.78 ± 3.34

46.69 ± 2.39 / 32.97 ± 4.57

75.39 ± 1.06 / 71.95 ± 1.42

2.91 ± 2.80 / 35.26 ± 2.12

54.95 ± 0.86 / 60.77 ± 0.75

0.00 ± 0.00 / 0.00 ± 0.00

2.12 ± 1.40 / 38.45 ± 2.47

16.91 ± 2.57 / 40.63 ± 2.83

0.00 ± 0.00 / 0.00 ± 0.00

52.66 ± 2.45 / 67.63 ± 1.87

7.33 ± 2.53 / 37.69 ± 2.51

30.05 ± 1.59 / 57.13 ± 2.48

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

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

9.3.2

10.0.0

12.5.1

9.3.2

10.0.0

12.5.1

9.3.2

10.0.0

12.5.1

9.3.2

10.0.0

12.5.1

12.10.0

9.3.2

10.0.0

12.5.1

9.3.2

10.0.0

12.5.1

sentence-transformers/quora-distilbert-multilingual

135

120

512

True

26,458 ± 5,992 / 5,274 ± 1,731

3.05

3.07

3.12

2.71

3.78

3.04

2.80

2.85

54.48 ± 2.16 / 52.85 ± 2.28

36.60 ± 1.60 / 56.93 ± 1.48

8.84 ± 5.33 / 51.76 ± 3.80

13.97 ± 1.75 / 19.76 ± 2.26

77.81 ± 0.76 / 74.83 ± 0.79

72.22 ± 0.95 / 68.32 ± 1.13

44.59 ± 1.89 / 59.87 ± 1.84

8.98 ± 3.55 / 52.49 ± 2.08

5.72 ± 3.29 / 50.40 ± 3.21

0.00 ± 0.00 / 0.00 ± 0.00

65.50 ± 1.20 / 59.72 ± 1.22

68.36 ± 1.18 / 63.94 ± 2.47

14.81 ± 6.63 / 55.50 ± 4.28

16.11 ± 1.18 / 22.88 ± 1.34

63.36 ± 0.96 / 65.24 ± 0.77

1.02 ± 0.94 / 47.05 ± 2.13

6.48 ± 0.37 / 27.44 ± 0.44

64.12 ± 0.92 / 62.50 ± 0.85

49.66 ± 1.68 / 66.33 ± 1.12

0.58 ± 1.23 / 49.27 ± 0.86

0.05 ± 0.06 / 0.36 ± 0.30

67.89 ± 1.61 / 74.48 ± 1.24

23.25 ± 6.95 / 44.88 ± 6.27

21.36 ± 7.80 / 59.50 ± 3.54

4.50 ± 0.39 / 9.94 ± 0.33

81.71 ± 0.66 / 82.33 ± 0.53

50.69 ± 1.19 / 50.90 ± 0.50

2.16 ± 1.58 / 49.99 ± 1.47

4.19 ± 0.69 / 11.99 ± 0.62

0.0.0

12.6.1

0.0.0

12.6.1

LumiOpen/Viking-13B (few-shot)

14030

131

4097

True

840 ± 79 / 400 ± 124

3.09

2.68

3.41

2.49

3.61

3.20

3.64

2.62

28.60 ± 4.69 / 20.29 ± 3.37

48.71 ± 1.27 / 60.90 ± 2.95

2.30 ± 1.34 / 37.21 ± 2.50

53.85 ± 1.73 / 58.96 ± 1.67

26.76 ± 6.99 / 23.69 ± 3.73

35.38 ± 5.87 / 27.52 ± 3.45

29.22 ± 2.89 / 39.25 ± 1.86

2.58 ± 2.68 / 36.11 ± 2.42

2.79 ± 1.44 / 36.17 ± 1.51

34.41 ± 3.68 / 53.61 ± 4.28

31.55 ± 4.67 / 18.37 ± 2.73

78.66 ± 1.03 / 78.34 ± 1.13

5.69 ± 2.24 / 44.98 ± 3.55

52.93 ± 1.30 / 57.87 ± 1.27

26.28 ± 5.09 / 22.73 ± 3.35

2.17 ± 1.98 / 48.03 ± 2.64

22.65 ± 3.50 / 45.48 ± 2.99

34.53 ± 1.24 / 29.89 ± 1.96

42.90 ± 2.66 / 56.64 ± 4.71

1.51 ± 1.64 / 43.36 ± 4.05

15.83 ± 1.42 / 29.77 ± 2.54

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

42.78 ± 4.24 / 40.64 ± 2.84

59.90 ± 4.98 / 54.05 ± 2.70

5.68 ± 1.91 / 50.82 ± 2.18

58.52 ± 1.88 / 68.97 ± 1.86

12.10.5

12.10.4

12.10.5

12.10.4

12.10.5

12.5.2

12.10.5

stabilityai/stablelm-2-1_6b (few-shot)

1645

100

4096

True

7,259 ± 2,120 / 1,240 ± 432

3.09

2.93

3.29

2.54

4.19

2.80

3.54

2.34

28.45 ± 1.61 / 22.90 ± 1.63

39.09 ± 1.15 / 45.25 ± 0.82

1.43 ± 1.26 / 37.98 ± 2.74

51.67 ± 2.31 / 57.34 ± 2.60

41.64 ± 3.64 / 39.43 ± 3.55

42.37 ± 3.13 / 40.79 ± 3.10

33.71 ± 2.57 / 55.00 ± 1.41

-0.19 ± 0.77 / 33.29 ± 0.30

-0.01 ± 1.25 / 34.51 ± 2.09

30.14 ± 2.44 / 50.96 ± 3.46

38.00 ± 4.39 / 29.74 ± 5.04

75.15 ± 0.55 / 61.46 ± 0.82

1.04 ± 2.08 / 34.49 ± 1.17

53.11 ± 0.53 / 58.91 ± 0.32

32.19 ± 2.52 / 32.88 ± 2.18

0.37 ± 1.64 / 33.39 ± 0.55

6.58 ± 2.15 / 27.03 ± 2.89

34.81 ± 2.51 / 30.33 ± 2.95

51.01 ± 2.18 / 65.35 ± 2.23

0.00 ± 0.00 / 33.34 ± 0.31

25.40 ± 3.91 / 49.38 ± 4.65

36.58 ± 3.88 / 33.82 ± 2.87

6.32 ± 1.30 / 24.04 ± 1.14

4.01 ± 2.01 / 36.03 ± 1.61

52.81 ± 0.81 / 63.87 ± 1.27

47.50 ± 1.70 / 41.85 ± 1.68

64.69 ± 1.33 / 57.60 ± 0.63

8.01 ± 1.97 / 51.78 ± 1.65

71.81 ± 1.05 / 80.90 ± 0.72

12.10.8

AI-Sweden-Models/gpt-sw3-20b-instruct (few-shot)

20918

64

2048

True

1,831 ± 587 / 268 ± 90

3.10

3.04

3.13

2.81

3.75

3.23

3.32

2.39

15.94 ± 1.59 / 14.05 ± 1.45

32.78 ± 4.04 / 47.79 ± 5.25

7.86 ± 1.87 / 41.91 ± 2.25

52.16 ± 0.84 / 60.27 ± 0.51

23.95 ± 1.93 / 21.43 ± 1.89

26.55 ± 1.50 / 25.06 ± 1.61

40.89 ± 3.60 / 59.86 ± 3.59

9.45 ± 1.58 / 44.62 ± 3.29

8.32 ± 1.89 / 42.30 ± 2.78

43.19 ± 1.82 / 67.93 ± 1.55

15.70 ± 1.54 / 14.65 ± 1.52

68.23 ± 3.81 / 71.17 ± 3.07

12.39 ± 1.39 / 50.99 ± 3.37

52.04 ± 0.97 / 60.86 ± 0.77

21.20 ± 1.45 / 19.22 ± 1.47

1.95 ± 1.01 / 35.16 ± 0.86

24.95 ± 3.00 / 53.88 ± 1.93

24.35 ± 1.72 / 21.90 ± 0.85

43.35 ± 3.81 / 60.49 ± 3.18

2.38 ± 1.21 / 37.27 ± 1.09

15.56 ± 2.24 / 34.68 ± 3.15

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

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

9.3.1

12.7.0

9.3.1

NorwAI/NorwAI-Mistral-7B (few-shot)

7537

68

4096

True

3,035 ± 503 / 911 ± 300

3.13

2.72

2.91

2.49

4.04

3.17

3.78

2.77

21.47 ± 3.87 / 16.98 ± 3.19

48.39 ± 0.66 / 64.51 ± 1.38

12.46 ± 2.22 / 52.33 ± 3.21

52.51 ± 1.57 / 58.49 ± 1.58

21.09 ± 6.44 / 20.45 ± 2.65

26.31 ± 4.64 / 26.42 ± 2.98

49.00 ± 3.88 / 65.98 ± 2.95

7.15 ± 2.14 / 40.83 ± 3.95

7.98 ± 2.64 / 45.21 ± 4.95

47.70 ± 5.32 / 68.04 ± 5.37

23.88 ± 7.28 / 17.99 ± 3.56

80.26 ± 0.89 / 77.89 ± 0.89

13.50 ± 2.27 / 52.55 ± 2.86

55.02 ± 0.96 / 60.74 ± 0.89

21.40 ± 2.86 / 19.64 ± 2.27

0.99 ± 1.30 / 35.84 ± 1.02

13.84 ± 2.99 / 36.90 ± 2.08

19.29 ± 5.77 / 20.20 ± 3.59

43.88 ± 3.42 / 61.04 ± 2.69

5.63 ± 1.32 / 49.95 ± 1.54

17.02 ± 2.10 / 36.47 ± 2.53

24.15 ± 5.73 / 26.49 ± 4.13

8.31 ± 1.56 / 20.06 ± 1.06

1.60 ± 1.71 / 41.51 ± 3.60

37.08 ± 1.76 / 49.32 ± 0.87

35.84 ± 5.12 / 35.76 ± 4.29

56.87 ± 8.16 / 59.62 ± 5.61

3.08 ± 2.98 / 40.66 ± 4.63

52.77 ± 1.53 / 66.64 ± 1.58

12.10.5

12.10.4

12.10.5

12.10.4

12.10.5

12.10.4

Qwen/Qwen1.5-4B (few-shot)

3950

152

32768

True

3,248 ± 739 / 761 ± 252

3.14

2.76

3.15

3.57

4.15

2.97

3.39

2.00

32.28 ± 3.16 / 23.24 ± 3.51

39.62 ± 2.39 / 56.09 ± 2.89

5.38 ± 2.18 / 36.31 ± 1.96

54.16 ± 0.89 / 60.63 ± 0.75

32.12 ± 5.17 / 32.01 ± 2.80

36.86 ± 3.53 / 35.46 ± 3.07

36.97 ± 1.94 / 55.08 ± 2.30

5.27 ± 3.31 / 40.91 ± 5.24

1.40 ± 1.87 / 33.64 ± 0.74

40.00 ± 2.26 / 62.87 ± 1.60

37.26 ± 4.28 / 29.89 ± 5.96

5.20 ± 7.35 / 30.65 ± 4.97

1.85 ± 1.54 / 33.71 ± 0.46

54.15 ± 0.58 / 60.15 ± 0.59

15.66 ± 5.89 / 15.78 ± 3.95

-0.55 ± 1.06 / 39.57 ± 3.61

14.11 ± 3.08 / 34.56 ± 2.38

31.52 ± 2.96 / 29.20 ± 1.88

39.91 ± 3.29 / 53.66 ± 3.20

3.27 ± 2.51 / 34.30 ± 1.29

27.55 ± 3.12 / 57.60 ± 3.34

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

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

12.5.2

10.0.1

12.1.0

12.5.2

10.0.1

12.1.0

12.5.2

9.3.2

12.1.0

12.5.2

12.1.0

12.5.2

10.0.1

12.1.0

12.5.2

10.0.1

12.1.0

12.5.2

10.0.1

12.1.0

sentence-transformers/distilbert-multilingual-nli-stsb-quora-ranking

135

120

512

True

33,753 ± 8,349 / 5,937 ± 1,946

3.14

3.07

3.12

2.71

3.83

3.06

3.34

2.85

54.48 ± 2.16 / 52.85 ± 2.28

36.60 ± 1.60 / 56.93 ± 1.48

8.84 ± 5.33 / 51.76 ± 3.80

15.42 ± 1.70 / 21.36 ± 1.94

77.81 ± 0.76 / 74.83 ± 0.79

72.22 ± 0.95 / 68.32 ± 1.13

44.59 ± 1.89 / 59.87 ± 1.84

8.98 ± 3.55 / 52.49 ± 2.08

5.72 ± 3.29 / 50.40 ± 3.21

0.00 ± 0.00 / 0.00 ± 0.00

65.50 ± 1.20 / 59.72 ± 1.22

68.33 ± 1.03 / 64.03 ± 2.47

14.81 ± 6.63 / 55.50 ± 4.28

16.11 ± 1.18 / 22.88 ± 1.34

59.15 ± 1.28 / 61.27 ± 1.27

0.80 ± 1.69 / 45.59 ± 3.23

6.14 ± 0.74 / 28.02 ± 0.58

63.78 ± 0.75 / 62.34 ± 0.64

49.69 ± 1.56 / 66.32 ± 1.07

0.74 ± 0.83 / 48.97 ± 0.85

0.02 ± 0.02 / 0.20 ± 0.17

65.04 ± 1.07 / 70.94 ± 0.61

17.40 ± 6.56 / 39.25 ± 6.11

-0.95 ± 1.35 / 49.00 ± 0.64

3.94 ± 0.39 / 9.50 ± 0.40

81.71 ± 0.66 / 82.33 ± 0.53

50.69 ± 1.19 / 50.90 ± 0.50

2.16 ± 1.58 / 49.99 ± 1.47

4.16 ± 0.71 / 11.93 ± 0.61

0.0.0

12.6.1

12.8.0

12.6.1

sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

118

250

512

True

29,201 ± 6,282 / 6,045 ± 2,027

3.14

2.69

2.92

2.48

3.88

3.00

4.11

2.90

56.75 ± 1.91 / 53.43 ± 1.87

44.48 ± 1.32 / 63.11 ± 0.83

26.74 ± 1.94 / 62.19 ± 1.84

17.89 ± 1.00 / 25.53 ± 1.05

78.31 ± 1.22 / 74.65 ± 1.36

72.13 ± 0.90 / 67.28 ± 1.09

47.53 ± 0.94 / 62.73 ± 1.07

26.92 ± 3.12 / 61.93 ± 2.04

14.63 ± 4.00 / 56.24 ± 2.51

0.00 ± 0.00 / 0.00 ± 0.00

66.50 ± 1.49 / 59.99 ± 1.40

72.19 ± 0.71 / 67.88 ± 2.34

28.75 ± 5.58 / 63.30 ± 2.60

15.91 ± 0.87 / 23.08 ± 0.95

62.44 ± 1.07 / 64.98 ± 0.92

1.91 ± 1.14 / 46.54 ± 2.46

3.69 ± 0.48 / 27.48 ± 0.49

60.54 ± 1.96 / 59.68 ± 1.94

54.99 ± 2.05 / 70.00 ± 1.37

0.52 ± 2.01 / 49.40 ± 1.06

0.80 ± 0.23 / 7.76 ± 2.10

59.61 ± 2.40 / 67.02 ± 1.16

0.00 ± 0.00 / 24.33 ± 0.14

-0.04 ± 1.84 / 48.65 ± 1.21

3.28 ± 0.31 / 9.04 ± 0.28

77.50 ± 0.54 / 78.82 ± 0.48

53.10 ± 1.18 / 51.88 ± 0.50

-0.35 ± 1.84 / 48.74 ± 1.43

3.13 ± 0.27 / 9.98 ± 0.25

0.0.0

12.8.0

12.6.1

dbmdz/bert-base-historic-multilingual-cased

111

32

512

True

20,047 ± 4,407 / 3,844 ± 1,259

3.17

3.27

3.22

2.41

3.94

2.89

3.54

2.90

47.61 ± 1.71 / 45.91 ± 1.91

24.17 ± 1.92 / 43.75 ± 2.75

8.14 ± 3.76 / 51.78 ± 1.81

25.19 ± 1.29 / 30.51 ± 1.06

68.63 ± 1.64 / 64.83 ± 1.55

67.70 ± 2.68 / 63.70 ± 2.54

25.68 ± 2.17 / 41.65 ± 2.77

6.73 ± 5.40 / 48.20 ± 3.68

3.35 ± 2.61 / 47.52 ± 3.20

22.57 ± 1.57 / 34.64 ± 1.94

68.83 ± 1.00 / 63.29 ± 1.48

64.25 ± 1.66 / 63.62 ± 2.92

28.62 ± 9.43 / 59.33 ± 5.91

28.78 ± 2.01 / 34.26 ± 2.03

56.62 ± 0.57 / 59.34 ± 0.66

-1.21 ± 1.45 / 47.43 ± 1.67

6.01 ± 0.45 / 29.08 ± 1.30

65.35 ± 1.08 / 63.62 ± 1.05

37.77 ± 2.20 / 58.20 ± 1.43

16.07 ± 3.83 / 54.09 ± 2.44

5.67 ± 1.14 / 16.63 ± 2.52

56.69 ± 1.80 / 68.42 ± 0.85

9.29 ± 3.04 / 30.73 ± 2.40

3.02 ± 1.45 / 50.08 ± 1.17

22.14 ± 1.13 / 31.59 ± 0.96

77.64 ± 0.74 / 79.56 ± 0.53

12.42 ± 9.17 / 33.80 ± 4.31

13.65 ± 6.22 / 53.84 ± 2.20

33.29 ± 0.96 / 45.71 ± 0.70

0.0.0

12.6.1

12.8.0

12.6.1

ibm-granite/granite-7b-base (few-shot)

6738

32

2048

True

4,405 ± 1,098 / 1,032 ± 345

3.19

3.10

3.70

2.66

4.14

2.83

3.53

2.36

24.93 ± 4.36 / 22.23 ± 3.32

31.65 ± 2.94 / 51.95 ± 2.92

0.06 ± 1.20 / 34.30 ± 1.04

51.47 ± 1.82 / 57.00 ± 1.94

32.21 ± 1.63 / 31.19 ± 1.29

36.62 ± 1.94 / 36.40 ± 2.17

16.98 ± 3.42 / 27.01 ± 3.17

1.57 ± 1.20 / 41.68 ± 4.20

0.97 ± 1.79 / 40.10 ± 4.50

26.28 ± 1.51 / 44.62 ± 2.11

33.34 ± 3.41 / 30.50 ± 3.44

72.00 ± 1.15 / 69.12 ± 2.00

0.25 ± 1.72 / 43.46 ± 3.96

52.53 ± 1.03 / 57.96 ± 0.98

28.06 ± 2.33 / 29.10 ± 2.34

0.10 ± 1.11 / 33.70 ± 0.88

11.07 ± 2.29 / 27.33 ± 1.88

37.68 ± 1.26 / 33.74 ± 1.78

46.00 ± 3.63 / 61.88 ± 2.94

0.83 ± 0.84 / 33.38 ± 0.28

26.65 ± 4.01 / 53.15 ± 4.26

37.39 ± 3.37 / 32.77 ± 1.97

7.51 ± 1.57 / 19.22 ± 1.72

3.11 ± 0.88 / 50.54 ± 0.90

49.60 ± 1.28 / 61.06 ± 0.94

47.76 ± 2.72 / 44.84 ± 2.71

66.41 ± 0.85 / 65.96 ± 2.20

5.76 ± 1.50 / 50.36 ± 2.34

70.34 ± 1.81 / 81.54 ± 1.06

12.10.5

EuropeanParliament/EUBERT

94

66

512

True

20,070 ± 3,977 / 4,400 ± 1,435

3.26

3.14

3.57

3.06

4.15

2.88

3.16

2.84

41.09 ± 1.83 / 40.40 ± 1.82

27.33 ± 1.92 / 49.78 ± 1.38

21.58 ± 3.92 / 59.41 ± 2.63

20.68 ± 0.82 / 26.68 ± 0.91

49.92 ± 0.61 / 49.17 ± 0.71

44.37 ± 1.15 / 43.43 ± 1.21

19.81 ± 2.15 / 40.90 ± 2.60

8.64 ± 3.57 / 53.17 ± 1.93

3.11 ± 1.16 / 50.44 ± 0.73

15.89 ± 1.29 / 26.33 ± 2.41

38.36 ± 1.60 / 37.63 ± 1.73

59.00 ± 1.72 / 56.25 ± 1.72

19.40 ± 5.65 / 58.63 ± 3.13

19.23 ± 0.59 / 26.64 ± 0.90

29.71 ± 1.94 / 28.69 ± 1.97

2.71 ± 1.10 / 49.68 ± 1.24

6.50 ± 0.42 / 27.51 ± 0.99

49.95 ± 0.72 / 49.10 ± 0.71

40.29 ± 2.70 / 59.76 ± 1.78

25.88 ± 6.61 / 61.54 ± 3.28

2.59 ± 0.71 / 8.94 ± 2.03

49.54 ± 1.42 / 50.44 ± 1.10

14.86 ± 3.09 / 35.33 ± 1.77

27.90 ± 5.58 / 62.47 ± 3.34

20.65 ± 1.02 / 29.40 ± 1.29

71.43 ± 0.88 / 71.51 ± 0.79

17.53 ± 2.21 / 38.67 ± 1.90

23.93 ± 5.87 / 59.48 ± 3.40

31.01 ± 0.89 / 42.98 ± 0.49

12.6.1

0.0.0

12.6.1

NorwAI/NorwAI-Llama2-7B (few-shot)

7033

68

4096

True

4,438 ± 1,128 / 1,028 ± 346

3.29

2.80

3.04

2.55

4.45

3.42

4.06

2.73

16.72 ± 2.23 / 15.96 ± 2.08

45.89 ± 2.13 / 63.12 ± 1.98

11.25 ± 2.33 / 51.88 ± 2.35

53.17 ± 0.79 / 59.30 ± 0.66

31.45 ± 1.64 / 31.64 ± 1.89

33.85 ± 1.95 / 34.29 ± 1.91

36.06 ± 3.96 / 52.59 ± 4.67

8.34 ± 2.97 / 45.11 ± 4.57

6.84 ± 3.88 / 45.28 ± 5.45

48.31 ± 4.22 / 69.39 ± 4.10

24.98 ± 2.04 / 25.50 ± 1.92

79.36 ± 1.35 / 76.34 ± 3.44

5.75 ± 2.23 / 41.27 ± 4.75

54.74 ± 0.84 / 60.74 ± 0.65

9.35 ± 0.70 / 9.74 ± 0.73

1.14 ± 0.97 / 35.56 ± 2.43

7.51 ± 3.09 / 30.04 ± 2.02

25.69 ± 1.43 / 25.95 ± 1.23

33.48 ± 2.83 / 47.14 ± 4.43

3.73 ± 1.14 / 44.43 ± 4.17

14.82 ± 2.69 / 35.50 ± 3.15

22.50 ± 2.27 / 24.09 ± 2.40

6.04 ± 1.51 / 18.08 ± 2.09

-0.61 ± 1.30 / 46.51 ± 2.55

26.96 ± 1.55 / 35.73 ± 1.87

38.51 ± 3.33 / 38.08 ± 2.64

63.60 ± 2.87 / 58.50 ± 1.25

2.23 ± 1.32 / 34.15 ± 0.60

45.44 ± 3.61 / 59.52 ± 2.98

12.10.5

12.10.4

12.10.5

12.10.4

google/gemma-2b (few-shot)

2506

256

8192

True

6,087 ± 1,046 / 1,902 ± 563

3.32

3.01

3.51

2.80

4.20

3.29

3.71

2.74

19.97 ± 3.91 / 16.51 ± 3.20

40.21 ± 1.00 / 46.73 ± 1.82

2.27 ± 2.39 / 38.71 ± 4.03

50.55 ± 1.22 / 56.27 ± 1.09

15.53 ± 5.69 / 15.49 ± 5.08

19.78 ± 4.54 / 18.86 ± 4.22

32.89 ± 1.65 / 42.58 ± 3.16

1.18 ± 1.00 / 33.34 ± 0.26

0.00 ± 0.00 / 32.79 ± 0.34

33.33 ± 3.73 / 53.15 ± 4.42

14.67 ± 4.71 / 14.85 ± 3.77

75.45 ± 1.10 / 64.08 ± 1.47

3.82 ± 1.23 / 44.81 ± 3.55

51.73 ± 0.88 / 57.35 ± 0.82

8.83 ± 5.85 / 9.93 ± 4.70

0.31 ± 1.95 / 45.42 ± 3.51

16.08 ± 2.91 / 37.41 ± 2.44

16.95 ± 2.96 / 15.80 ± 2.16

44.96 ± 3.30 / 61.27 ± 2.88

0.77 ± 1.22 / 33.68 ± 0.59

17.92 ± 4.72 / 40.68 ± 6.34

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

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

12.5.2

12.1.0

12.5.2

12.1.0

12.5.2

12.1.0

12.5.2

12.1.0

12.5.2

12.1.0

12.5.2

12.1.0

12.5.2

12.1.0

google/gemma-2b-it (few-shot)

2506

256

8192

False

6,471 ± 1,142 / 1,961 ± 584

3.35

3.09

3.47

3.26

4.23

3.25

3.42

2.73

24.44 ± 2.59 / 17.37 ± 2.03

34.03 ± 2.50 / 52.42 ± 2.16

2.25 ± 1.28 / 42.33 ± 3.11

42.12 ± 1.18 / 49.76 ± 1.22

39.78 ± 2.67 / 31.15 ± 2.70

43.58 ± 2.49 / 36.60 ± 2.76

22.01 ± 3.00 / 40.48 ± 2.81

2.76 ± 1.35 / 44.34 ± 3.05

1.45 ± 1.35 / 39.55 ± 3.53

32.42 ± 1.72 / 56.65 ± 0.92

33.51 ± 2.12 / 23.48 ± 2.69

43.97 ± 1.64 / 57.41 ± 1.18

0.53 ± 1.09 / 39.60 ± 1.99

39.39 ± 1.04 / 47.28 ± 1.02

20.49 ± 2.30 / 18.33 ± 1.40

-0.01 ± 2.13 / 46.02 ± 2.71

10.95 ± 2.39 / 37.64 ± 0.75

36.62 ± 1.56 / 28.22 ± 1.66

28.54 ± 2.70 / 50.10 ± 1.65

1.15 ± 1.66 / 38.16 ± 2.78

23.39 ± 1.00 / 51.61 ± 1.04

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

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

12.5.2

12.1.0

12.4.0

12.5.2

12.1.0

12.4.0

12.5.2

12.1.0

12.4.0

12.5.2

12.1.0

12.4.0

12.5.2

12.1.0

12.4.0

12.5.2

12.1.0

12.4.0

12.5.2

12.1.0

12.4.0

allenai/OLMo-7B (few-shot)

6888

50

2051

True

5,403 ± 1,133 / 1,294 ± 423

3.43

3.16

3.92

2.72

4.58

3.29

3.68

2.66

26.76 ± 3.11 / 19.46 ± 2.38

30.76 ± 4.38 / 44.83 ± 4.36

0.55 ± 1.73 / 39.40 ± 4.57

45.65 ± 1.22 / 52.49 ± 1.01

34.42 ± 3.22 / 27.79 ± 2.40

35.17 ± 4.05 / 30.70 ± 3.37

21.46 ± 5.63 / 38.36 ± 6.18

0.34 ± 1.25 / 33.60 ± 0.50

0.26 ± 0.58 / 34.69 ± 3.11

0.12 ± 0.04 / 9.85 ± 0.17

37.36 ± 2.11 / 28.59 ± 3.03

72.08 ± 1.20 / 63.52 ± 3.36

-0.86 ± 1.61 / 33.84 ± 0.59

45.16 ± 0.96 / 51.46 ± 0.93

8.84 ± 2.72 / 8.59 ± 2.81

-0.38 ± 1.52 / 34.73 ± 1.40

5.08 ± 1.06 / 18.85 ± 2.62

30.85 ± 4.69 / 24.38 ± 3.10

49.77 ± 2.81 / 64.87 ± 2.42

2.67 ± 1.77 / 41.55 ± 4.54

4.09 ± 1.94 / 12.70 ± 2.66

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

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

12.5.2

sentence-transformers/distiluse-base-multilingual-cased-v1

135

120

512

True

34,042 ± 8,482 / 5,951 ± 1,950

3.46

3.38

3.59

3.14

4.19

3.36

3.31

3.24

46.78 ± 1.50 / 44.41 ± 1.78

27.78 ± 2.22 / 49.38 ± 2.89

3.04 ± 1.85 / 46.85 ± 3.03

15.52 ± 0.98 / 23.22 ± 0.86

60.76 ± 1.53 / 58.35 ± 1.41

59.62 ± 1.19 / 55.90 ± 1.12

25.98 ± 1.33 / 40.58 ± 0.60

2.65 ± 2.08 / 48.09 ± 1.42

3.47 ± 1.47 / 48.98 ± 1.75

0.20 ± 0.09 / 0.82 ± 0.39

49.86 ± 1.85 / 44.53 ± 1.58

60.06 ± 1.30 / 55.65 ± 1.34

3.18 ± 1.63 / 48.38 ± 1.42

16.08 ± 2.60 / 23.46 ± 3.10

45.47 ± 2.05 / 47.67 ± 2.11

1.14 ± 1.81 / 48.47 ± 1.64

1.63 ± 0.33 / 21.45 ± 1.39

28.29 ± 6.50 / 27.54 ± 6.33

51.70 ± 1.63 / 67.81 ± 1.08

2.12 ± 2.30 / 49.13 ± 2.33

0.03 ± 0.05 / 0.69 ± 0.53

58.67 ± 1.07 / 68.27 ± 0.94

17.82 ± 4.47 / 37.11 ± 2.75

9.27 ± 4.66 / 52.04 ± 4.01

2.17 ± 0.34 / 8.02 ± 0.41

71.33 ± 0.75 / 73.43 ± 0.61

36.75 ± 1.28 / 47.80 ± 1.46

0.24 ± 1.44 / 47.55 ± 1.59

1.30 ± 0.31 / 9.37 ± 0.28

0.0.0

12.6.1

12.8.0

0.0.0

12.6.1

sentence-transformers/distiluse-base-multilingual-cased

135

120

512

True

19,206 ± 4,451 / 3,658 ± 1,187

3.48

3.67

3.49

3.14

4.08

3.22

3.60

3.19

26.96 ± 1.31 / 25.63 ± 1.35

30.13 ± 2.10 / 46.78 ± 4.49

2.01 ± 1.29 / 48.79 ± 1.65

8.25 ± 1.03 / 16.49 ± 1.77

63.79 ± 2.11 / 67.14 ± 1.91

60.96 ± 1.11 / 64.65 ± 1.00

32.83 ± 1.48 / 43.32 ± 0.69

1.09 ± 1.93 / 48.72 ± 1.29

0.18 ± 1.93 / 47.30 ± 1.44

0.00 ± 0.00 / 0.00 ± 0.00

51.67 ± 1.46 / 53.62 ± 1.02

63.04 ± 0.70 / 56.50 ± 1.19

2.32 ± 1.83 / 48.77 ± 1.62

8.93 ± 1.00 / 17.75 ± 1.16

47.62 ± 2.97 / 50.59 ± 2.81

2.64 ± 2.11 / 49.47 ± 1.79

1.27 ± 0.46 / 12.20 ± 2.90

40.20 ± 3.20 / 40.33 ± 3.13

48.71 ± 1.60 / 65.32 ± 1.57

5.53 ± 1.92 / 51.10 ± 1.38

0.06 ± 0.06 / 1.12 ± 1.10

56.98 ± 1.37 / 66.91 ± 1.60

9.66 ± 4.65 / 31.17 ± 3.34

19.37 ± 4.34 / 56.74 ± 3.13

3.11 ± 0.37 / 7.91 ± 0.25

71.90 ± 1.49 / 74.21 ± 1.10

36.22 ± 1.39 / 45.80 ± 1.20

0.47 ± 1.65 / 48.67 ± 1.71

2.44 ± 0.17 / 8.50 ± 0.20

12.6.1

0.0.0

12.6.1

Qwen/Qwen1.5-1.8B-Chat (few-shot)

1837

152

32768

False

8,304 ± 1,846 / 1,933 ± 617

3.50

3.34

3.85

3.19

4.39

3.25

3.87

2.59

18.00 ± 2.52 / 14.88 ± 1.68

26.58 ± 2.81 / 45.88 ± 3.40

0.63 ± 1.48 / 33.42 ± 0.28

41.66 ± 1.48 / 49.40 ± 1.53

26.99 ± 3.92 / 24.61 ± 2.74

25.74 ± 3.76 / 24.51 ± 2.96

19.85 ± 1.97 / 35.75 ± 1.74

1.96 ± 1.33 / 44.22 ± 2.93

-0.01 ± 1.39 / 39.57 ± 2.97

16.33 ± 2.17 / 31.16 ± 3.40

20.94 ± 3.73 / 18.26 ± 2.84

52.54 ± 3.33 / 60.44 ± 3.13

0.34 ± 1.22 / 36.61 ± 1.57

43.55 ± 1.14 / 50.53 ± 1.40

14.15 ± 1.92 / 14.96 ± 2.11

0.78 ± 1.70 / 44.74 ± 3.57

7.80 ± 1.32 / 23.47 ± 1.64

28.04 ± 2.71 / 24.08 ± 1.58

36.21 ± 3.42 / 54.82 ± 3.32

3.12 ± 1.42 / 46.21 ± 2.93

16.33 ± 3.22 / 41.91 ± 4.34

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

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

12.5.2

11.0.0

12.1.0

12.5.0

12.5.2

11.0.0

12.1.0

12.5.0

12.5.2

11.0.0

12.1.0

12.5.0

12.5.2

12.1.0

12.5.0

12.5.2

11.0.0

12.1.0

12.5.0

12.5.2

11.0.0

12.1.0

12.5.0

12.5.2

11.0.0

12.1.0

12.5.0

sentence-transformers/distiluse-base-multilingual-cased-v2

135

120

512

True

33,247 ± 8,123 / 6,017 ± 1,977

3.55

3.67

3.49

3.14

4.08

3.22

4.09

3.19

26.96 ± 1.31 / 25.63 ± 1.35

30.13 ± 2.10 / 46.78 ± 4.49

2.01 ± 1.29 / 48.79 ± 1.65

8.22 ± 1.11 / 16.40 ± 1.79

63.79 ± 2.11 / 67.14 ± 1.91

60.96 ± 1.11 / 64.65 ± 1.00

32.83 ± 1.48 / 43.32 ± 0.69

1.09 ± 1.93 / 48.72 ± 1.29

0.18 ± 1.93 / 47.30 ± 1.44

0.00 ± 0.00 / 0.00 ± 0.00

51.67 ± 1.46 / 53.62 ± 1.02

62.71 ± 0.81 / 57.24 ± 1.73

2.32 ± 1.83 / 48.77 ± 1.62

8.76 ± 1.03 / 17.62 ± 1.24

48.62 ± 2.65 / 51.75 ± 2.37

2.64 ± 2.11 / 49.47 ± 1.79

1.22 ± 0.49 / 12.16 ± 3.00

41.82 ± 3.25 / 42.03 ± 3.15

49.38 ± 1.72 / 66.10 ± 1.17

4.77 ± 2.08 / 49.48 ± 2.07

0.05 ± 0.06 / 0.92 ± 0.55

49.82 ± 2.71 / 62.06 ± 1.69

2.70 ± 3.10 / 26.12 ± 2.40

6.60 ± 3.84 / 50.71 ± 1.92

2.13 ± 0.10 / 6.80 ± 0.37

71.90 ± 1.49 / 74.21 ± 1.10

36.22 ± 1.39 / 45.80 ± 1.20

0.47 ± 1.65 / 48.67 ± 1.71

2.40 ± 0.23 / 8.51 ± 0.21

12.6.1

12.8.0

12.6.1

Qwen/Qwen1.5-1.8B (few-shot)

1837

152

32768

True

5,666 ± 1,328 / 1,256 ± 408

3.57

3.44

3.93

3.17

4.45

3.54

4.04

2.44

9.83 ± 3.50 / 8.97 ± 2.64

29.03 ± 2.48 / 46.75 ± 3.69

0.56 ± 0.87 / 33.34 ± 0.23

46.43 ± 0.74 / 53.20 ± 0.47

12.10 ± 5.58 / 12.85 ± 4.80

13.42 ± 6.02 / 13.82 ± 5.16

22.82 ± 3.11 / 43.88 ± 3.10

2.70 ± 2.16 / 47.68 ± 3.18

2.21 ± 1.46 / 42.80 ± 4.36

16.31 ± 2.22 / 30.78 ± 3.64

18.01 ± 6.41 / 18.55 ± 4.65

51.91 ± 4.78 / 59.44 ± 4.65

1.49 ± 1.95 / 40.76 ± 4.07

44.83 ± 0.63 / 51.87 ± 0.72

12.26 ± 4.13 / 12.77 ± 3.60

0.94 ± 1.34 / 40.66 ± 3.73

6.31 ± 1.01 / 20.24 ± 2.02

9.23 ± 4.86 / 10.43 ± 3.83

38.30 ± 2.90 / 56.94 ± 2.83

0.39 ± 1.17 / 33.47 ± 0.34

16.67 ± 3.02 / 41.61 ± 3.00

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

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

12.5.2

10.0.1

12.1.0

12.5.2

10.0.1

12.1.0

12.5.2

10.0.1

12.1.0

12.5.2

12.1.0

12.5.2

10.0.1

12.1.0

12.5.2

10.0.1

12.1.0

12.5.2

10.0.1

12.1.0

allenai/OLMo-7B-Twin-2T (few-shot)

6888

50

2051

True

5,484 ± 1,125 / 1,317 ± 425

3.66

3.56

4.10

2.88

4.45

3.80

4.09

2.74

7.52 ± 3.92 / 6.60 ± 2.84

18.30 ± 3.89 / 27.62 ± 5.78

3.23 ± 1.94 / 45.74 ± 3.06

46.35 ± 1.42 / 51.37 ± 1.43

9.06 ± 6.86 / 8.39 ± 6.41

17.16 ± 6.21 / 16.00 ± 5.94

25.52 ± 3.72 / 41.44 ± 4.44

0.68 ± 1.54 / 45.09 ± 2.63

0.17 ± 2.27 / 42.02 ± 4.30

0.46 ± 0.07 / 6.96 ± 0.13

20.49 ± 7.78 / 19.50 ± 6.82

70.04 ± 2.28 / 60.77 ± 3.00

2.28 ± 1.77 / 36.86 ± 3.97

45.85 ± 1.19 / 51.08 ± 1.21

9.04 ± 5.36 / 9.25 ± 4.70

-0.08 ± 1.02 / 34.02 ± 0.68

8.86 ± 2.70 / 27.28 ± 1.45

14.06 ± 5.31 / 12.90 ± 4.52

28.07 ± 6.33 / 38.61 ± 7.42

2.31 ± 1.88 / 44.45 ± 4.23

6.89 ± 2.35 / 17.95 ± 3.37

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

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

12.5.2

3ebdola/Dialectal-Arabic-XLM-R-Base

278

250

512

True

12,783 ± 2,537 / 2,712 ± 885

3.74

3.75

3.81

3.59

3.78

3.70

3.91

3.61

36.51 ± 2.44 / 36.31 ± 2.71

22.07 ± 2.24 / 44.70 ± 3.72

1.63 ± 1.49 / 45.36 ± 3.07

3.09 ± 1.00 / 9.48 ± 1.61

55.55 ± 3.71 / 52.52 ± 3.51

53.53 ± 3.03 / 50.23 ± 3.00

12.69 ± 4.51 / 32.23 ± 3.53

2.79 ± 1.16 / 47.71 ± 2.00

1.66 ± 2.18 / 46.60 ± 2.87

0.00 ± 0.00 / 0.60 ± 0.72

42.78 ± 3.26 / 40.46 ± 3.04

44.95 ± 2.30 / 48.17 ± 1.06

1.43 ± 1.34 / 48.66 ± 2.45

8.71 ± 2.58 / 16.77 ± 2.50

46.95 ± 2.05 / 50.04 ± 1.99

1.40 ± 1.40 / 48.02 ± 2.05

10.48 ± 1.75 / 28.80 ± 1.59

30.18 ± 6.85 / 29.11 ± 6.64

32.66 ± 3.87 / 53.17 ± 4.09

2.10 ± 1.30 / 47.10 ± 2.29

0.46 ± 0.39 / 4.04 ± 2.36

44.46 ± 2.24 / 60.04 ± 1.09

8.39 ± 4.20 / 30.69 ± 2.83

2.07 ± 1.34 / 48.42 ± 1.31

4.30 ± 1.26 / 9.24 ± 1.13

68.25 ± 2.50 / 70.44 ± 2.50

1.92 ± 1.68 / 28.84 ± 2.38

1.08 ± 1.34 / 47.42 ± 1.71

2.79 ± 0.93 / 10.00 ± 0.84

0.0.0

12.6.1

12.8.0

0.0.0

12.6.1

dbmdz/bert-tiny-historic-multilingual-cased

5

32

512

True

78,027 ± 15,466 / 17,064 ± 5,335

3.78

3.89

3.88

3.60

4.09

3.68

3.96

3.37

33.62 ± 1.57 / 31.69 ± 1.40

20.71 ± 1.68 / 40.07 ± 2.65

1.19 ± 1.08 / 48.46 ± 1.34

4.19 ± 0.88 / 7.68 ± 1.59

46.11 ± 3.68 / 43.54 ± 3.44

35.18 ± 4.90 / 33.22 ± 4.64

19.19 ± 2.87 / 37.36 ± 1.97

2.76 ± 1.42 / 50.99 ± 0.83

0.42 ± 1.04 / 49.39 ± 0.80

0.00 ± 0.00 / 0.00 ± 0.00

26.87 ± 2.26 / 25.42 ± 2.14

57.41 ± 1.89 / 53.50 ± 0.75

-1.06 ± 1.33 / 48.72 ± 0.87

5.54 ± 1.44 / 10.83 ± 2.62

43.93 ± 1.57 / 46.59 ± 1.50

0.04 ± 1.75 / 47.53 ± 1.60

6.13 ± 0.63 / 21.73 ± 0.95

33.18 ± 2.13 / 32.48 ± 2.13

33.61 ± 2.23 / 55.01 ± 2.11

1.83 ± 1.54 / 49.40 ± 1.24

0.00 ± 0.00 / 0.00 ± 0.00

41.38 ± 2.82 / 56.29 ± 1.61

8.45 ± 2.80 / 29.85 ± 1.86

1.55 ± 1.97 / 49.24 ± 1.16

4.40 ± 0.22 / 6.62 ± 0.38

65.85 ± 0.80 / 68.72 ± 0.81

25.85 ± 2.01 / 40.72 ± 0.85

1.21 ± 1.72 / 50.03 ± 0.84

4.00 ± 0.55 / 11.02 ± 0.40

12.6.1

0.0.0

12.6.1

0.0.0

12.6.1

RuterNorway/Llama-2-7b-chat-norwegian (few-shot)

unknown

32

4096

False

10,890 ± 2,686 / 2,186 ± 750

3.79

4.01

3.95

3.45

4.73

3.22

3.52

3.64

10.12 ± 1.24 / 9.84 ± 1.12

10.65 ± 3.65 / 28.33 ± 5.27

-0.66 ± 1.24 / 33.61 ± 0.26

26.08 ± 3.96 / 28.87 ± 4.21

21.04 ± 2.63 / 20.44 ± 2.47

18.71 ± 2.67 / 19.91 ± 2.89

12.22 ± 1.17 / 23.50 ± 3.03

-1.18 ± 1.40 / 35.70 ± 2.67

0.36 ± 1.28 / 37.66 ± 4.07

26.86 ± 1.65 / 50.11 ± 1.80

22.38 ± 3.00 / 22.09 ± 2.85

31.11 ± 12.17 / 36.84 ± 11.52

0.09 ± 0.67 / 33.42 ± 0.30

44.36 ± 1.34 / 50.14 ± 1.15

9.48 ± 1.48 / 10.10 ± 1.44

0.07 ± 1.06 / 43.54 ± 3.63

1.04 ± 0.96 / 7.35 ± 3.52

27.22 ± 1.38 / 24.48 ± 1.76

33.61 ± 5.06 / 49.68 ± 5.74

0.45 ± 0.91 / 35.24 ± 3.71

20.44 ± 3.29 / 45.50 ± 3.33

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

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

9.3.1

12.5.2

9.3.1

12.5.2

9.3.1

12.5.2

9.3.1

12.5.2

9.3.1

12.10.0

9.3.1

12.5.2

9.3.1

12.5.2

9.3.1

12.5.2

Qwen/Qwen1.5-0.5B-Chat (few-shot)

620

152

32768

False

11,740 ± 3,000 / 2,209 ± 721

3.82

3.81

4.08

3.51

4.61

3.90

3.96

2.84

17.38 ± 2.04 / 15.74 ± 1.99

10.72 ± 3.35 / 25.21 ± 3.80

1.32 ± 1.08 / 42.05 ± 3.69

34.58 ± 0.97 / 40.37 ± 1.02

29.52 ± 1.48 / 29.79 ± 1.62

31.27 ± 1.30 / 31.91 ± 1.31

11.49 ± 1.38 / 27.12 ± 1.98

0.29 ± 1.58 / 40.21 ± 4.22

-0.12 ± 1.48 / 39.92 ± 3.90

7.80 ± 1.19 / 17.09 ± 2.72

18.57 ± 4.62 / 17.69 ± 4.61

40.23 ± 5.86 / 49.01 ± 4.77

0.21 ± 1.06 / 39.60 ± 3.61

29.49 ± 2.47 / 35.01 ± 2.72

9.50 ± 3.17 / 9.41 ± 3.40

1.76 ± 1.62 / 38.51 ± 3.72

3.14 ± 0.71 / 17.84 ± 2.26

24.67 ± 0.99 / 23.98 ± 0.73

9.31 ± 2.97 / 21.50 ± 2.70

1.11 ± 1.69 / 37.88 ± 4.05

13.60 ± 1.60 / 29.10 ± 1.94

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

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

12.5.2

11.0.0

12.1.0

12.4.0

12.5.2

11.0.0

12.1.0

12.4.0

12.5.2

11.0.0

12.1.0

12.4.0

12.5.2

12.1.0

12.5.0

12.5.2

11.0.0

12.1.0

12.5.0

12.5.2

11.0.0

12.1.0

12.5.0

12.5.2

11.0.0

12.1.0

12.5.0

Qwen/Qwen1.5-0.5B (few-shot)

620

152

32768

True

11,371 ± 2,924 / 2,122 ± 692

3.85

3.76

4.17

3.57

4.56

3.89

4.09

2.91

19.01 ± 1.91 / 17.08 ± 1.83

8.88 ± 1.86 / 24.27 ± 2.45

0.66 ± 1.41 / 37.98 ± 4.14

32.78 ± 2.33 / 38.31 ± 2.81

34.46 ± 2.01 / 33.09 ± 2.32

33.41 ± 2.21 / 33.91 ± 2.33

6.31 ± 3.46 / 20.67 ± 2.69

-1.59 ± 1.08 / 36.27 ± 3.71

0.61 ± 1.41 / 38.84 ± 5.10

5.95 ± 1.53 / 16.20 ± 1.93

28.96 ± 2.39 / 26.49 ± 3.14

26.58 ± 5.12 / 28.64 ± 5.35

-1.88 ± 1.46 / 35.45 ± 2.92

34.59 ± 1.06 / 40.95 ± 1.11

16.20 ± 1.52 / 16.96 ± 1.71

-0.57 ± 1.20 / 41.25 ± 3.51

3.31 ± 0.82 / 16.86 ± 2.98

27.34 ± 1.95 / 24.46 ± 1.25

10.64 ± 5.31 / 26.79 ± 4.73

0.33 ± 1.20 / 35.20 ± 2.45

11.81 ± 2.10 / 27.38 ± 2.49

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

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

12.5.2

10.0.1

12.1.0

12.5.2

10.0.1

12.1.0

12.5.2

10.0.1

12.1.0

12.5.2

12.1.0

12.5.2

10.0.1

12.1.0

12.5.2

10.0.1

12.1.0

12.5.2

10.0.1

12.1.0

allenai/OLMo-1B (few-shot)

1177

50

2051

True

8,536 ± 1,926 / 1,940 ± 619

3.94

3.89

4.18

3.60

4.67

4.04

4.30

2.93

13.39 ± 2.60 / 12.39 ± 2.46

17.94 ± 5.58 / 32.80 ± 3.63

-2.02 ± 2.28 / 40.63 ± 4.12

23.65 ± 2.96 / 26.24 ± 3.20

30.79 ± 1.95 / 32.18 ± 1.98

31.12 ± 2.36 / 33.10 ± 2.68

9.95 ± 3.92 / 29.01 ± 2.80

-0.95 ± 1.87 / 39.37 ± 3.33

-0.04 ± 1.73 / 42.36 ± 4.61

0.00 ± 0.00 / 3.06 ± 0.05

29.39 ± 3.08 / 29.93 ± 3.14

38.95 ± 11.78 / 43.61 ± 8.46

-1.35 ± 1.76 / 40.70 ± 4.25

17.85 ± 3.77 / 20.30 ± 4.04

13.60 ± 2.38 / 14.36 ± 2.36

-1.04 ± 0.90 / 34.46 ± 1.41

1.51 ± 0.68 / 13.16 ± 3.12

21.46 ± 2.04 / 20.83 ± 1.63

21.03 ± 6.33 / 38.33 ± 7.79

0.13 ± 1.48 / 43.17 ± 4.90

0.71 ± 0.53 / 6.02 ± 1.37

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

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

12.5.2

12.1.0

12.5.2

12.1.0

12.5.2

12.1.0

12.5.2

12.1.0

12.5.2

12.1.0

12.5.2

12.1.0

12.5.2

12.1.0

fresh-xlm-roberta-base

278

250

512

True

2,214 ± 94 / 1,494 ± 229

4.25

4.12

4.20

3.88

4.65

4.09

4.70

4.08

16.04 ± 2.47 / 15.60 ± 2.62

17.37 ± 3.82 / 36.83 ± 4.86

1.34 ± 0.97 / 35.45 ± 3.20

1.58 ± 0.51 / 6.64 ± 1.56

25.49 ± 3.39 / 23.54 ± 3.23

25.94 ± 1.70 / 24.10 ± 1.64

12.60 ± 2.97 / 32.27 ± 3.43

0.50 ± 1.27 / 36.93 ± 4.00

1.83 ± 1.64 / 37.67 ± 4.40

0.00 ± 0.00 / 0.00 ± 0.00

11.91 ± 3.04 / 11.31 ± 2.90

51.11 ± 5.32 / 50.09 ± 3.33

0.86 ± 0.82 / 39.16 ± 3.63

2.00 ± 0.63 / 7.20 ± 1.68

17.34 ± 1.13 / 16.43 ± 1.26

-0.06 ± 0.99 / 36.73 ± 3.00

1.02 ± 0.30 / 21.61 ± 1.10

8.03 ± 1.35 / 8.63 ± 1.36

23.44 ± 7.21 / 42.87 ± 7.78

-0.17 ± 1.13 / 39.21 ± 4.70

0.00 ± 0.00 / 0.00 ± 0.00

13.09 ± 1.68 / 16.25 ± 2.85

0.92 ± 2.11 / 25.39 ± 1.86

1.93 ± 1.37 / 40.76 ± 4.83

0.26 ± 0.09 / 2.70 ± 1.10

34.64 ± 1.25 / 34.41 ± 1.49

4.00 ± 3.78 / 24.24 ± 3.94

1.33 ± 1.00 / 42.07 ± 4.82

0.43 ± 0.11 / 6.18 ± 1.24

0.0.0

12.6.1

0.0.0

12.6.1

fresh-electra-small

14

31

512

True

7,840 ± 1,538 / 3,024 ± 438

4.31

4.21

4.26

3.90

4.75

4.19

4.72

4.15

12.87 ± 1.63 / 13.23 ± 1.55

18.61 ± 4.17 / 35.23 ± 3.90

0.30 ± 1.39 / 37.84 ± 3.88

0.00 ± 0.00 / 0.00 ± 0.00

18.38 ± 2.01 / 17.08 ± 1.97

12.76 ± 1.29 / 11.65 ± 1.21

15.29 ± 5.37 / 34.15 ± 4.23

0.17 ± 0.84 / 36.29 ± 2.91

0.37 ± 0.69 / 35.08 ± 2.81

0.00 ± 0.00 / 0.00 ± 0.00

10.54 ± 1.12 / 9.71 ± 1.00

55.54 ± 2.75 / 52.75 ± 1.09

-0.15 ± 0.52 / 35.33 ± 3.00

0.02 ± 0.03 / 0.04 ± 0.05

9.96 ± 1.11 / 8.96 ± 1.05

-0.10 ± 1.46 / 35.81 ± 3.45

0.12 ± 0.10 / 4.48 ± 1.39

9.53 ± 0.71 / 9.93 ± 0.76

13.29 ± 8.29 / 29.94 ± 8.32

-0.15 ± 0.77 / 33.37 ± 0.37

0.00 ± 0.00 / 0.00 ± 0.00

11.66 ± 1.16 / 13.45 ± 1.20

0.00 ± 0.00 / 24.33 ± 0.14

-0.21 ± 1.89 / 35.79 ± 2.99

0.17 ± 0.04 / 0.17 ± 0.04

30.77 ± 0.92 / 30.14 ± 1.03

0.58 ± 1.45 / 20.82 ± 1.74

-0.17 ± 0.47 / 37.18 ± 3.93

0.46 ± 0.14 / 6.16 ± 0.24

0.0.0

12.8.0

12.6.1

NorwAI/NorwAI-Mistral-7B-pretrain (few-shot)

7537

68

4096

True

3,024 ± 496 / 909 ± 301

4.47

4.19

4.35

4.24

4.78

4.50

4.83

4.41

12.82 ± 2.64 / 12.37 ± 1.95

3.55 ± 3.64 / 22.75 ± 4.02

0.68 ± 1.41 / 35.13 ± 0.98

19.85 ± 1.75 / 24.31 ± 1.88

12.77 ± 3.48 / 14.13 ± 3.09

10.51 ± 3.44 / 9.95 ± 3.51

8.70 ± 4.43 / 25.39 ± 3.30

0.00 ± 1.60 / 38.54 ± 3.41

0.82 ± 1.39 / 37.77 ± 4.45

1.85 ± 0.82 / 10.19 ± 1.99

9.75 ± 3.30 / 9.18 ± 3.19

17.76 ± 4.89 / 28.16 ± 7.50

1.22 ± 0.95 / 43.54 ± 3.79

14.98 ± 2.49 / 18.46 ± 2.99

3.69 ± 1.28 / 3.66 ± 1.30

1.24 ± 1.37 / 42.67 ± 4.99

0.29 ± 0.19 / 5.14 ± 0.75

5.80 ± 1.56 / 5.41 ± 1.56

4.45 ± 1.73 / 29.26 ± 3.66

-0.48 ± 1.33 / 43.09 ± 3.56

0.08 ± 0.12 / 4.02 ± 1.17

3.80 ± 1.23 / 4.24 ± 1.19

0.97 ± 1.50 / 13.00 ± 2.52

-0.37 ± 0.55 / 33.40 ± 0.35

0.40 ± 0.25 / 2.98 ± 0.44

12.34 ± 2.70 / 12.41 ± 2.54

-1.48 ± 3.09 / 21.17 ± 2.22

-0.48 ± 1.52 / 42.45 ± 3.99

0.72 ± 0.25 / 6.31 ± 0.51

12.10.5

12.10.4

12.10.5

12.10.4

RJuro/kanelsnegl-v0.1 (few-shot)

7242

32

512

True

5,847 ± 1,029 / 1,640 ± 525

4.65

4.52

4.69

4.38

4.92

4.65

4.88

4.54

0.00 ± 0.00 / 0.00 ± 0.00

13.00 ± 4.17 / 24.41 ± 3.12

0.00 ± 0.00 / 33.25 ± 0.23

0.00 ± 0.00 / 12.39 ± 1.52

0.00 ± 0.00 / 0.00 ± 0.00

0.95 ± 0.80 / 9.68 ± 0.28

0.00 ± 0.00 / 33.25 ± 0.30

0.00 ± 0.00 / 32.79 ± 0.34

0.00 ± 0.00 / 33.45 ± 0.27

0.00 ± 0.00 / 0.00 ± 0.00

34.63 ± 9.69 / 40.92 ± 6.88

0.00 ± 0.00 / 33.30 ± 0.27

0.00 ± 0.00 / 8.92 ± 2.90

0.00 ± 0.00 / 0.00 ± 0.00

0.00 ± 0.00 / 33.69 ± 0.28

0.00 ± 0.00 / 11.90 ± 2.74

0.00 ± 0.00 / 0.00 ± 0.00

0.00 ± 0.00 / 17.05 ± 0.35

0.00 ± 0.00 / 33.34 ± 0.31

0.00 ± 0.00 / 14.17 ± 0.79

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

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

9.3.1

12.5.1

9.3.1

12.5.1

9.3.1

12.5.1

9.3.1

12.10.0

9.3.1

12.5.1

9.3.1

12.5.1

ai-forever/mGPT (few-shot)

unknown

100

1024

True

11,734 ± 3,124 / 2,174 ± 720

4.68

4.64

4.60

4.66

4.92

4.65

4.88

4.43

0.65 ± 0.68 / 0.59 ± 0.63

2.61 ± 2.75 / 20.51 ± 2.48

-0.73 ± 1.72 / 41.15 ± 3.71

1.99 ± 1.69 / 2.68 ± 1.87

0.08 ± 0.16 / 0.07 ± 0.14

0.00 ± 0.00 / 0.00 ± 0.00

4.76 ± 1.84 / 16.95 ± 5.07

0.67 ± 1.94 / 40.42 ± 4.43

-0.88 ± 1.89 / 40.70 ± 4.30

0.00 ± 0.00 / 0.74 ± 0.05

0.00 ± 0.00 / 0.00 ± 0.00

0.00 ± 0.00 / 19.32 ± 0.16

0.49 ± 1.29 / 39.12 ± 3.92

6.24 ± 3.13 / 7.85 ± 3.67

0.00 ± 0.00 / 0.00 ± 0.00

0.00 ± 0.00 / 33.69 ± 0.28

0.00 ± 0.00 / 0.05 ± 0.03

0.00 ± 0.00 / 0.00 ± 0.00

0.19 ± 1.24 / 17.20 ± 1.22

-0.12 ± 0.91 / 36.65 ± 3.92

0.00 ± 0.00 / 1.29 ± 0.49

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

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

9.3.1

10.0.1

11.0.0

12.5.1

9.3.1

10.0.1

11.0.0

12.5.1

9.3.1

10.0.1

11.0.0

12.5.1

9.3.1

11.0.0

12.5.1

12.10.0

9.3.1

10.0.1

11.0.0

12.5.1

9.3.1

10.0.1

11.0.0

12.5.1