Germanic NLU 🇪🇺

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

unknown

100

128000

True

576 ± 221 / 81 ± 28

1.41

1.23

1.37

1.20

1.22

1.40

1.50

1.95

1.38

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

49.59 ± 2.76 / 62.50 ± 2.08

43.03 ± 5.07 / 71.18 ± 2.64

37.26 ± 2.60 / 66.04 ± 1.95

86.51 ± 2.01 / 85.01 ± 2.45

38.22 ± 8.49 / 52.33 ± 6.78

35.09 ± 5.70 / 65.72 ± 3.27

58.65 ± 3.25 / 81.93 ± 2.20

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

13.2.0

12.10.2

12.5.1

13.3.0

12.5.1

13.0.0

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

microsoft/mdeberta-v3-base

279

251

512

True

20,637 ± 3,925 / 4,497 ± 1,502

1.60

1.62

1.35

1.38

1.25

2.15

1.66

2.06

1.35

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

45.30 ± 1.76 / 62.84 ± 1.27

54.11 ± 2.40 / 76.46 ± 1.28

30.93 ± 0.96 / 56.17 ± 1.10

88.60 ± 0.60 / 89.37 ± 0.54

6.70 ± 4.85 / 25.36 ± 7.25

46.81 ± 2.12 / 72.76 ± 1.40

20.96 ± 1.19 / 30.59 ± 1.61

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

13.3.0

0.0.0

13.3.0

0.0.0

13.0.0

12.7.0

0.0.0

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

unknown

200

128000

True

916 ± 329 / 114 ± 38

1.65

1.34

1.38

1.20

1.19

2.82

1.69

2.14

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

49.86 ± 5.14 / 64.51 ± 3.68

51.10 ± 5.09 / 73.25 ± 3.42

29.64 ± 2.12 / 55.46 ± 1.12

81.86 ± 2.08 / 67.98 ± 3.64

27.30 ± 11.60 / 55.31 ± 9.21

-0.97 ± 2.82 / 33.64 ± 0.85

56.45 ± 2.88 / 78.76 ± 1.86

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

13.2.0

12.10.2

12.10.0

13.3.0

12.10.0

13.0.0

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

1.70

1.54

1.28

1.35

1.57

2.94

1.21

2.29

1.40

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

36.87 ± 3.38 / 56.59 ± 2.94

48.29 ± 2.59 / 73.54 ± 1.99

29.38 ± 1.81 / 52.42 ± 3.00

87.35 ± 0.94 / 87.65 ± 0.94

0.04 ± 3.09 / 17.28 ± 2.02

14.65 ± 11.12 / 46.36 ± 10.23

36.10 ± 1.91 / 48.41 ± 2.09

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

13.3.0

0.0.0

13.3.0

0.0.0

13.0.0

12.7.0

12.6.1

setu4993/LaBSE

471

501

512

True

25,418 ± 6,435 / 4,536 ± 1,452

1.73

1.78

1.57

1.53

2.02

2.44

1.53

1.42

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

46.40 ± 1.18 / 63.25 ± 0.79

36.92 ± 7.62 / 66.07 ± 3.89

11.75 ± 0.66 / 46.17 ± 1.42

89.16 ± 0.66 / 89.62 ± 0.62

21.57 ± 4.96 / 45.40 ± 4.23

22.76 ± 10.57 / 60.04 ± 5.76

30.55 ± 1.05 / 41.85 ± 1.13

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

13.3.0

0.0.0

13.3.0

0.0.0

13.0.0

12.7.0

0.0.0

12.6.1

intfloat/multilingual-e5-large

560

250

512

True

6,732 ± 1,273 / 1,633 ± 523

1.74

1.53

1.47

1.38

2.46

3.09

1.33

1.35

1.30

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

48.52 ± 1.18 / 64.38 ± 1.18

10.78 ± 7.04 / 53.28 ± 3.97

13.79 ± 0.96 / 54.20 ± 1.31

88.39 ± 0.86 / 88.75 ± 0.75

18.28 ± 3.38 / 39.08 ± 2.62

2.85 ± 1.32 / 48.43 ± 2.29

31.03 ± 1.94 / 43.72 ± 2.89

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

13.3.0

0.0.0

13.3.0

0.0.0

13.0.0

12.6.1

0.0.0

12.6.1

intfloat/multilingual-e5-large-instruct

560

250

514

True

5,947 ± 1,301 / 1,129 ± 374

1.83

1.82

1.74

1.45

2.46

2.99

1.33

1.59

1.26

69.86 ± 1.64 / 65.30 ± 1.46

55.45 ± 1.57 / 69.74 ± 1.66

31.14 ± 18.61 / 63.23 ± 10.14

45.51 ± 2.60 / 52.75 ± 1.79

89.27 ± 1.00 / 90.42 ± 0.65

83.78 ± 1.53 / 86.17 ± 1.36

63.35 ± 0.63 / 74.20 ± 0.91

55.71 ± 11.72 / 77.00 ± 5.84

12.32 ± 12.70 / 53.74 ± 7.38

38.74 ± 7.61 / 58.52 ± 7.90

79.50 ± 0.96 / 77.37 ± 0.89

79.48 ± 0.87 / 77.47 ± 1.64

53.01 ± 15.20 / 75.97 ± 7.76

45.68 ± 1.62 / 53.19 ± 1.02

78.32 ± 1.32 / 79.70 ± 1.08

50.10 ± 1.59 / 64.91 ± 2.07

8.11 ± 3.77 / 50.71 ± 3.73

13.93 ± 1.14 / 53.59 ± 1.62

88.64 ± 0.34 / 89.11 ± 0.29

23.63 ± 6.26 / 44.37 ± 7.53

2.05 ± 2.30 / 47.88 ± 2.17

24.09 ± 4.66 / 37.60 ± 4.39

79.77 ± 1.22 / 78.93 ± 1.23

65.72 ± 1.70 / 76.73 ± 1.23

49.82 ± 10.56 / 73.61 ± 5.48

28.42 ± 1.71 / 55.35 ± 1.55

83.68 ± 1.57 / 87.38 ± 1.03

27.19 ± 6.73 / 45.37 ± 6.25

51.80 ± 10.91 / 75.02 ± 5.60

46.07 ± 1.33 / 58.70 ± 1.30

91.43 ± 0.52 / 91.15 ± 0.44

66.42 ± 1.01 / 64.56 ± 1.33

53.05 ± 12.06 / 75.49 ± 6.21

61.34 ± 1.79 / 74.85 ± 1.26

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

FacebookAI/xlm-roberta-large

560

250

512

True

17,897 ± 3,921 / 3,463 ± 1,141

1.92

1.60

1.44

1.56

2.04

3.66

1.26

2.01

1.76

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

48.41 ± 6.83 / 64.09 ± 6.26

22.78 ± 12.25 / 57.07 ± 8.18

15.72 ± 1.39 / 55.29 ± 1.30

87.85 ± 0.95 / 88.21 ± 0.87

5.14 ± 5.42 / 22.03 ± 5.69

1.17 ± 2.11 / 40.94 ± 5.07

27.72 ± 1.48 / 39.88 ± 2.04

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

13.3.0

0.0.0

13.3.0

0.0.0

13.0.0

12.7.0

0.0.0

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

355

50

512

True

14,014 ± 2,384 / 3,625 ± 1,146

2.12

1.30

1.08

1.18

2.94

3.25

2.62

3.26

1.36

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

38.53 ± 2.56 / 56.94 ± 2.26

2.06 ± 2.43 / 37.04 ± 4.14

11.47 ± 0.96 / 48.11 ± 0.94

88.24 ± 0.58 / 88.48 ± 0.54

6.42 ± 5.53 / 24.34 ± 7.55

1.73 ± 1.70 / 42.32 ± 5.16

35.08 ± 2.58 / 47.03 ± 3.42

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

13.3.0

10.0.1

13.3.0

10.0.1

13.0.0

12.10.0

10.0.1

intfloat/multilingual-e5-base

278

250

512

True

14,965 ± 2,890 / 3,322 ± 1,074

2.12

1.88

2.00

1.69

2.66

3.45

1.79

1.98

1.52

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

42.08 ± 1.98 / 59.90 ± 1.47

15.21 ± 8.62 / 54.40 ± 5.57

10.82 ± 0.92 / 43.65 ± 2.51

87.44 ± 0.35 / 88.01 ± 0.28

10.97 ± 3.84 / 30.74 ± 5.68

7.38 ± 6.28 / 47.69 ± 4.51

14.80 ± 3.56 / 22.12 ± 5.23

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

13.3.0

12.6.1

13.3.0

12.6.1

13.0.0

12.6.1

0.0.0

12.6.1

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

7242

32

8192

False

5,876 ± 1,021 / 1,677 ± 546

2.17

1.96

2.16

1.88

3.03

2.71

1.88

2.24

1.48

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

28.82 ± 2.16 / 48.33 ± 2.73

4.45 ± 1.40 / 51.11 ± 0.87

24.61 ± 3.36 / 54.99 ± 2.36

66.98 ± 1.97 / 60.82 ± 2.81

37.70 ± 2.15 / 56.90 ± 2.21

5.80 ± 2.04 / 42.89 ± 2.71

44.88 ± 1.73 / 63.94 ± 1.35

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

13.3.0

12.5.2

13.3.0

12.5.2

13.0.0

12.5.2

mistralai/Ministral-8B-Instruct-2410 (few-shot)

8020

131

32768

True

5,821 ± 1,090 / 1,561 ± 506

2.17

2.08

2.21

1.85

2.47

2.85

1.82

2.36

1.74

52.49 ± 1.89 / 38.85 ± 1.94

49.67 ± 1.40 / 65.83 ± 1.40

22.80 ± 5.31 / 55.25 ± 6.92

57.07 ± 0.68 / 64.46 ± 0.57

69.85 ± 2.00 / 59.43 ± 3.23

68.83 ± 1.07 / 59.51 ± 2.63

54.49 ± 2.44 / 69.23 ± 2.00

28.55 ± 2.65 / 61.53 ± 3.21

17.47 ± 3.61 / 52.60 ± 5.26

43.55 ± 3.42 / 71.05 ± 3.22

67.49 ± 2.20 / 51.10 ± 4.76

76.74 ± 1.27 / 75.66 ± 1.17

22.37 ± 3.11 / 54.47 ± 4.95

57.15 ± 0.72 / 64.47 ± 0.58

56.09 ± 3.29 / 42.39 ± 2.51

39.51 ± 2.31 / 57.84 ± 2.34

8.51 ± 1.55 / 50.18 ± 2.85

29.23 ± 1.41 / 57.06 ± 0.62

67.52 ± 2.82 / 61.64 ± 3.39

29.34 ± 4.73 / 50.04 ± 4.36

3.35 ± 2.55 / 46.55 ± 3.36

49.62 ± 1.90 / 69.57 ± 1.48

66.00 ± 1.13 / 54.14 ± 2.44

54.76 ± 3.11 / 68.36 ± 2.92

33.55 ± 4.69 / 63.49 ± 2.99

32.69 ± 1.98 / 64.23 ± 2.89

66.51 ± 1.38 / 52.40 ± 2.62

13.55 ± 2.14 / 37.36 ± 1.32

34.46 ± 2.79 / 65.61 ± 2.58

59.23 ± 1.16 / 72.56 ± 0.80

72.40 ± 0.80 / 65.83 ± 1.64

63.46 ± 2.10 / 69.49 ± 1.15

35.86 ± 7.94 / 65.20 ± 6.98

68.42 ± 1.21 / 83.97 ± 0.74

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

meta-llama/Llama-3.1-8B-Instruct (few-shot)

8030

128

131073

True

2,411 ± 465 / 686 ± 215

2.22

2.28

1.96

2.41

2.66

1.91

2.45

1.81

57.19 ± 1.73 / 44.34 ± 2.43

51.30 ± 1.32 / 64.44 ± 1.47

10.31 ± 3.91 / 42.59 ± 5.19

48.80 ± 1.66 / 60.46 ± 0.60

74.77 ± 0.84 / 71.87 ± 0.97

72.80 ± 1.57 / 69.98 ± 1.84

57.30 ± 0.98 / 71.58 ± 0.90

5.23 ± 1.83 / 34.90 ± 0.81

11.51 ± 3.24 / 45.73 ± 5.97

43.93 ± 3.73 / 70.96 ± 3.00

71.52 ± 1.43 / 59.28 ± 3.63

80.46 ± 0.83 / 78.67 ± 1.13

12.29 ± 3.59 / 40.53 ± 4.13

53.54 ± 1.52 / 62.08 ± 0.98

55.09 ± 1.76 / 40.34 ± 2.34

39.03 ± 1.68 / 56.67 ± 2.03

8.45 ± 1.33 / 51.00 ± 1.95

29.65 ± 1.09 / 56.96 ± 1.35

71.04 ± 1.85 / 70.33 ± 2.15

36.73 ± 4.80 / 52.50 ± 5.21

1.59 ± 1.29 / 33.68 ± 0.38

46.33 ± 1.15 / 70.86 ± 1.12

67.61 ± 1.23 / 60.39 ± 1.02

59.96 ± 2.00 / 70.71 ± 1.80

28.25 ± 3.57 / 59.54 ± 3.88

28.79 ± 2.02 / 55.82 ± 3.28

69.76 ± 1.36 / 57.66 ± 1.36

15.51 ± 1.59 / 39.71 ± 1.21

37.58 ± 3.42 / 66.98 ± 2.22

41.26 ± 2.09 / 65.63 ± 0.90

76.95 ± 0.95 / 72.47 ± 0.82

68.12 ± 0.92 / 72.48 ± 0.53

34.34 ± 3.37 / 65.84 ± 1.59

47.88 ± 3.37 / 76.21 ± 1.69

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

meta-llama/Llama-3.1-8B (few-shot)

8030

128

131073

True

2,439 ± 459 / 703 ± 219

2.22

2.13

2.15

1.73

2.58

3.14

1.86

2.39

1.76

47.68 ± 2.50 / 32.67 ± 2.45

49.71 ± 1.43 / 64.00 ± 1.96

25.48 ± 2.83 / 58.45 ± 2.63

60.31 ± 1.24 / 65.79 ± 0.84

64.62 ± 1.26 / 53.50 ± 3.27

65.10 ± 1.86 / 56.43 ± 2.58

52.87 ± 1.18 / 68.71 ± 1.01

28.34 ± 3.26 / 58.57 ± 4.45

22.40 ± 3.12 / 53.51 ± 5.42

53.20 ± 3.15 / 75.98 ± 2.62

63.85 ± 2.49 / 44.62 ± 4.10

79.96 ± 0.93 / 75.75 ± 2.22

31.70 ± 4.07 / 59.28 ± 5.00

59.33 ± 0.88 / 65.24 ± 0.79

52.57 ± 2.04 / 36.81 ± 2.12

44.00 ± 2.20 / 61.61 ± 1.71

4.87 ± 2.28 / 40.95 ± 4.97

30.12 ± 4.65 / 57.81 ± 4.78

65.43 ± 3.19 / 63.09 ± 4.04

24.35 ± 5.52 / 37.90 ± 6.16

1.12 ± 2.01 / 35.45 ± 2.25

51.86 ± 1.50 / 73.55 ± 1.19

60.46 ± 1.26 / 47.72 ± 1.69

58.57 ± 2.53 / 71.30 ± 1.70

26.25 ± 5.90 / 61.41 ± 3.94

34.85 ± 3.43 / 64.05 ± 3.68

64.79 ± 1.96 / 45.48 ± 2.24

11.95 ± 2.83 / 37.12 ± 2.19

32.97 ± 2.68 / 58.52 ± 2.92

63.89 ± 1.06 / 74.73 ± 1.02

69.86 ± 2.10 / 62.68 ± 2.21

66.76 ± 0.72 / 68.58 ± 0.72

30.96 ± 2.46 / 61.29 ± 3.61

71.39 ± 2.20 / 84.24 ± 1.55

12.11.0

13.0.0

12.11.0

13.0.0

12.11.0

13.3.0

12.11.0

13.0.0

12.11.0

13.3.0

12.11.0

13.0.0

12.11.0

13.0.0

12.11.0

13.0.0

12.11.0

13.0.0

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

8030

128

8192

True

4,909 ± 1,215 / 978 ± 319

2.23

2.17

2.16

2.11

2.57

2.60

1.91

2.49

1.86

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

34.95 ± 4.34 / 51.53 ± 4.46

6.10 ± 1.61 / 48.74 ± 3.05

31.52 ± 2.08 / 58.96 ± 1.57

73.76 ± 1.34 / 70.21 ± 2.63

40.84 ± 5.75 / 57.63 ± 4.87

3.47 ± 1.97 / 49.04 ± 1.89

49.53 ± 2.28 / 73.08 ± 1.05

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

13.3.0

12.6.1

13.3.0

12.6.1

13.0.0

12.6.1

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

8030

128

8192

True

4,687 ± 1,121 / 967 ± 313

2.29

2.09

2.28

1.81

2.50

3.16

2.04

2.56

1.92

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

38.90 ± 3.77 / 57.62 ± 2.79

7.49 ± 2.51 / 43.40 ± 4.41

29.56 ± 5.47 / 55.53 ± 5.79

61.11 ± 4.21 / 58.55 ± 4.19

19.96 ± 5.17 / 31.78 ± 5.62

2.02 ± 1.68 / 39.88 ± 3.56

50.34 ± 1.74 / 71.74 ± 1.27

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

13.3.0

12.6.1

13.3.0

12.6.1

13.0.0

12.6.1

ZurichNLP/unsup-simcse-xlm-roberta-base

278

250

512

True

34,520 ± 7,443 / 6,730 ± 2,224

2.31

2.30

2.19

1.95

2.93

3.21

2.05

1.84

2.00

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

46.33 ± 1.12 / 62.80 ± 1.39

3.47 ± 1.14 / 47.14 ± 3.33

7.67 ± 0.80 / 32.31 ± 0.81

84.14 ± 0.67 / 84.82 ± 0.64

21.20 ± 3.85 / 43.97 ± 3.72

1.33 ± 2.18 / 48.85 ± 1.23

14.20 ± 1.78 / 22.95 ± 2.71

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

13.3.0

12.6.1

13.3.0

12.6.1

13.0.0

12.7.0

0.0.0

12.6.1

cardiffnlp/twitter-xlm-roberta-base

278

250

512

True

34,475 ± 7,465 / 6,712 ± 2,223

2.42

2.08

2.04

1.86

2.62

4.07

2.22

2.28

2.22

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

35.62 ± 1.32 / 55.40 ± 1.15

28.72 ± 5.29 / 60.29 ± 3.57

8.46 ± 0.51 / 31.01 ± 0.72

83.96 ± 0.80 / 84.63 ± 0.76

5.16 ± 3.25 / 23.12 ± 4.48

1.05 ± 1.66 / 41.31 ± 4.91

0.00 ± 0.00 / 0.00 ± 0.00

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

13.3.0

0.0.0

13.3.0

0.0.0

13.0.0

12.7.0

0.0.0

12.6.1

CohereForAI/aya-expanse-8b (few-shot)

8028

256

8192

False

5,581 ± 1,066 / 1,471 ± 483

2.47

2.18

2.63

2.11

3.37

2.89

2.04

2.67

1.87

51.32 ± 3.82 / 25.54 ± 2.10

52.00 ± 1.67 / 66.25 ± 1.77

18.48 ± 2.44 / 52.18 ± 4.28

52.43 ± 1.19 / 62.08 ± 0.60

66.55 ± 2.12 / 39.28 ± 3.45

63.63 ± 1.62 / 37.25 ± 3.49

38.61 ± 2.28 / 51.46 ± 2.62

15.80 ± 2.22 / 51.42 ± 3.79

12.30 ± 2.38 / 51.96 ± 3.31

43.26 ± 2.53 / 71.49 ± 2.01

57.38 ± 1.93 / 29.69 ± 4.23

78.43 ± 0.93 / 74.54 ± 2.40

14.52 ± 2.43 / 45.18 ± 4.21

53.14 ± 1.81 / 63.00 ± 0.50

28.98 ± 2.63 / 21.75 ± 1.89

19.83 ± 4.76 / 41.64 ± 3.64

4.93 ± 1.06 / 49.69 ± 2.65

24.72 ± 2.22 / 54.41 ± 1.43

68.63 ± 1.70 / 41.26 ± 2.21

29.07 ± 3.30 / 46.38 ± 3.87

1.95 ± 2.22 / 42.77 ± 3.69

45.04 ± 1.74 / 63.06 ± 1.68

61.29 ± 1.06 / 39.58 ± 2.31

59.19 ± 1.49 / 71.64 ± 1.07

33.31 ± 3.00 / 64.35 ± 2.80

22.29 ± 2.02 / 57.68 ± 1.78

62.07 ± 1.67 / 37.68 ± 1.28

11.09 ± 1.67 / 31.37 ± 1.35

35.14 ± 2.33 / 66.66 ± 1.50

49.15 ± 1.48 / 68.82 ± 0.68

66.61 ± 1.39 / 47.49 ± 1.37

68.71 ± 0.63 / 68.49 ± 1.70

34.72 ± 2.23 / 66.80 ± 1.30

57.90 ± 2.96 / 80.48 ± 1.34

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

ibm-granite/granite-3.0-8b-base (few-shot)

8171

49

4097

True

5,116 ± 943 / 1,436 ± 472

2.50

2.29

2.53

2.13

3.70

3.03

2.05

2.43

1.84

44.58 ± 2.62 / 33.50 ± 2.75

47.16 ± 1.36 / 64.63 ± 1.18

19.20 ± 2.44 / 53.44 ± 4.36

58.41 ± 1.36 / 63.32 ± 0.89

49.94 ± 2.13 / 46.49 ± 2.00

52.17 ± 1.02 / 46.44 ± 2.72

53.27 ± 1.54 / 66.73 ± 1.31

17.22 ± 3.50 / 50.42 ± 5.01

12.01 ± 2.47 / 47.98 ± 4.37

45.04 ± 3.42 / 69.52 ± 2.79

44.80 ± 2.36 / 34.91 ± 2.67

75.92 ± 2.44 / 75.77 ± 2.08

24.84 ± 2.78 / 59.88 ± 4.08

56.71 ± 1.65 / 62.01 ± 1.64

37.82 ± 3.63 / 32.97 ± 3.97

2.60 ± 2.91 / 15.68 ± 0.75

-0.12 ± 1.31 / 33.78 ± 0.32

21.59 ± 2.22 / 47.09 ± 1.09

61.47 ± 1.57 / 58.60 ± 2.31

31.99 ± 3.03 / 50.94 ± 2.59

1.44 ± 1.85 / 34.71 ± 1.84

41.54 ± 1.49 / 58.90 ± 1.24

52.61 ± 1.79 / 42.68 ± 2.71

61.70 ± 1.45 / 74.22 ± 1.00

23.89 ± 4.13 / 57.16 ± 4.48

33.72 ± 1.25 / 62.41 ± 1.53

53.21 ± 1.37 / 42.13 ± 2.58

13.72 ± 2.18 / 39.38 ± 2.08

40.85 ± 4.16 / 67.34 ± 3.66

62.41 ± 0.99 / 74.19 ± 0.56

53.37 ± 1.98 / 49.01 ± 1.29

68.88 ± 1.24 / 70.64 ± 0.92

37.17 ± 3.96 / 67.71 ± 2.64

69.02 ± 2.58 / 83.72 ± 1.53

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

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

7242

32

32768

True

2,657 ± 524 / 880 ± 278

2.50

2.45

2.65

2.16

2.99

3.12

2.13

2.72

1.82

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

26.07 ± 4.82 / 46.35 ± 4.70

1.35 ± 1.70 / 39.37 ± 3.87

25.70 ± 5.36 / 49.31 ± 5.21

62.63 ± 3.44 / 57.85 ± 3.72

25.47 ± 3.14 / 45.73 ± 4.68

2.84 ± 1.84 / 42.62 ± 4.53

44.06 ± 1.93 / 60.40 ± 2.37

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

13.3.0

9.1.2

12.5.1

9.1.2

13.3.0

9.1.2

13.0.0

9.1.2

12.5.1

9.1.2

12.5.1

9.1.2

12.5.1

ibm-granite/granite-3.0-8b-instruct (few-shot)

8171

49

4096

True

5,090 ± 937 / 1,423 ± 466

2.53

2.40

2.54

2.23

3.47

3.03

2.11

2.71

1.77

44.92 ± 3.05 / 32.65 ± 2.50

49.31 ± 1.35 / 66.02 ± 1.10

10.14 ± 2.87 / 44.99 ± 4.82

57.34 ± 0.99 / 63.24 ± 0.44

53.79 ± 1.52 / 46.58 ± 1.73

56.13 ± 0.91 / 47.13 ± 2.04

51.36 ± 2.53 / 66.19 ± 2.08

6.83 ± 2.54 / 38.36 ± 3.81

8.09 ± 2.03 / 41.05 ± 4.14

48.01 ± 2.52 / 73.03 ± 1.99

44.94 ± 2.91 / 35.67 ± 3.53

76.78 ± 1.63 / 78.27 ± 1.22

16.96 ± 2.77 / 55.03 ± 3.49

56.83 ± 1.02 / 63.13 ± 0.89

42.67 ± 3.13 / 35.40 ± 3.93

9.95 ± 3.78 / 30.20 ± 5.91

1.11 ± 1.45 / 34.61 ± 0.82

22.25 ± 2.78 / 49.58 ± 2.19

59.96 ± 2.42 / 58.61 ± 2.57

28.33 ± 7.70 / 49.72 ± 6.84

2.24 ± 1.78 / 41.32 ± 3.70

39.52 ± 1.83 / 57.16 ± 2.10

54.68 ± 1.38 / 46.36 ± 2.67

55.48 ± 2.67 / 69.91 ± 1.90

26.89 ± 0.86 / 62.51 ± 0.48

31.27 ± 1.89 / 62.30 ± 2.09

53.62 ± 2.29 / 40.51 ± 1.41

13.37 ± 1.25 / 36.94 ± 1.81

23.47 ± 1.79 / 60.17 ± 1.23

61.20 ± 1.02 / 72.98 ± 0.62

62.84 ± 1.74 / 56.61 ± 1.77

68.55 ± 0.89 / 72.50 ± 1.04

41.05 ± 2.87 / 69.78 ± 1.63

66.25 ± 2.13 / 83.31 ± 0.91

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

CohereForAI/aya-23-8B (few-shot)

8028

256

8192

False

5,608 ± 1,062 / 1,472 ± 479

2.54

2.41

2.82

2.11

3.29

3.38

1.86

2.64

1.79

47.08 ± 3.39 / 32.34 ± 2.97

47.16 ± 1.21 / 63.47 ± 1.57

8.41 ± 2.40 / 37.31 ± 1.66

58.83 ± 0.73 / 63.96 ± 0.56

60.94 ± 2.30 / 53.33 ± 3.53

59.61 ± 1.37 / 50.84 ± 3.99

35.73 ± 1.26 / 50.42 ± 1.67

6.18 ± 1.69 / 35.40 ± 1.06

4.00 ± 1.01 / 36.17 ± 0.94

46.52 ± 2.15 / 71.95 ± 1.63

60.04 ± 1.22 / 43.93 ± 3.63

76.21 ± 0.85 / 67.87 ± 1.71

7.54 ± 2.52 / 35.42 ± 1.33

58.60 ± 0.59 / 63.65 ± 0.30

47.16 ± 2.83 / 38.60 ± 4.04

19.77 ± 6.04 / 34.40 ± 4.93

3.84 ± 1.27 / 40.06 ± 3.79

21.75 ± 2.21 / 48.25 ± 2.02

62.22 ± 2.10 / 58.79 ± 2.20

25.58 ± 9.25 / 44.11 ± 9.87

0.01 ± 2.43 / 37.74 ± 4.20

38.70 ± 1.22 / 54.70 ± 0.93

58.69 ± 1.32 / 45.79 ± 2.60

56.49 ± 2.69 / 70.39 ± 2.14

30.04 ± 2.28 / 62.58 ± 2.34

36.36 ± 1.07 / 66.01 ± 1.94

60.81 ± 1.94 / 46.59 ± 3.32

7.90 ± 1.63 / 24.82 ± 0.95

31.12 ± 2.35 / 64.29 ± 1.88

63.00 ± 1.23 / 74.60 ± 0.67

61.14 ± 2.97 / 53.13 ± 1.91

69.68 ± 0.65 / 67.92 ± 0.82

32.57 ± 2.11 / 65.57 ± 1.69

75.82 ± 1.63 / 87.24 ± 0.65

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

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

7248

33

32768

True

4,120 ± 976 / 926 ± 306

2.54

2.36

2.72

2.18

3.00

3.28

2.13

2.83

1.84

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

31.17 ± 3.39 / 45.66 ± 3.73

0.12 ± 1.68 / 35.09 ± 1.17

25.52 ± 5.24 / 49.15 ± 5.21

61.32 ± 4.26 / 59.28 ± 4.43

23.30 ± 4.23 / 39.80 ± 3.89

1.30 ± 1.64 / 45.10 ± 3.27

44.98 ± 1.62 / 62.38 ± 1.68

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

13.3.0

12.10.4

13.3.0

12.10.4

13.0.0

12.10.4

12.10.5

12.10.4

12.10.5

12.10.4

12.10.5

utter-project/EuroLLM-9B-Instruct (few-shot)

9152

128

4096

False

5,763 ± 1,178 / 1,390 ± 446

2.57

2.19

2.67

2.10

3.58

3.15

2.11

2.61

2.18

34.00 ± 2.69 / 25.49 ± 2.06

53.97 ± 1.21 / 68.40 ± 1.28

32.21 ± 4.81 / 56.97 ± 5.83

57.10 ± 0.99 / 63.73 ± 0.85

40.91 ± 2.56 / 33.22 ± 1.88

42.91 ± 2.34 / 35.61 ± 2.22

52.62 ± 2.01 / 68.10 ± 2.25

9.70 ± 4.22 / 36.58 ± 1.69

11.98 ± 2.76 / 39.37 ± 2.76

47.36 ± 4.28 / 72.71 ± 4.10

40.59 ± 1.98 / 28.19 ± 1.47

76.02 ± 2.40 / 77.86 ± 1.70

33.98 ± 5.90 / 57.44 ± 6.59

56.98 ± 0.58 / 63.97 ± 0.66

24.92 ± 3.54 / 23.09 ± 3.30

9.76 ± 7.16 / 26.68 ± 6.80

0.15 ± 0.29 / 33.01 ± 0.31

28.18 ± 1.51 / 54.08 ± 0.71

49.32 ± 1.94 / 47.58 ± 2.12

34.21 ± 5.26 / 43.22 ± 4.37

0.16 ± 0.32 / 33.30 ± 0.32

46.06 ± 2.09 / 65.02 ± 1.80

40.85 ± 2.21 / 34.64 ± 2.00

56.53 ± 2.49 / 69.48 ± 1.70

24.74 ± 4.45 / 56.60 ± 5.56

38.20 ± 1.47 / 67.94 ± 2.19

43.06 ± 1.89 / 30.50 ± 1.45

11.95 ± 2.25 / 33.40 ± 1.41

40.85 ± 3.31 / 68.94 ± 2.23

63.42 ± 0.63 / 74.62 ± 0.52

44.81 ± 2.07 / 39.51 ± 1.62

62.54 ± 2.18 / 68.78 ± 1.18

28.10 ± 4.55 / 62.46 ± 4.36

71.71 ± 2.21 / 84.31 ± 1.69

13.1.0

13.3.0

13.1.0

13.3.0

13.1.0

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

7242

32

32768

False

5,993 ± 1,028 / 1,742 ± 561

2.59

2.28

2.49

2.26

3.38

3.74

2.08

2.56

1.94

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

7.92 ± 3.63 / 32.79 ± 2.05

3.44 ± 2.02 / 50.18 ± 1.14

21.55 ± 2.79 / 54.79 ± 2.02

67.42 ± 2.21 / 60.87 ± 3.22

20.01 ± 4.67 / 38.23 ± 3.04

7.02 ± 1.56 / 49.32 ± 2.91

0.65 ± 0.17 / 7.03 ± 0.26

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

13.3.0

12.6.1

13.3.0

12.6.1

13.0.0

12.6.1

Twitter/twhin-bert-base

279

250

512

True

11,514 ± 2,041 / 2,862 ± 918

2.63

2.36

2.57

1.99

2.86

3.86

2.24

2.92

2.25

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

40.22 ± 1.03 / 58.56 ± 1.02

11.09 ± 6.94 / 51.60 ± 5.19

7.67 ± 0.74 / 30.52 ± 0.52

84.00 ± 1.30 / 84.83 ± 1.28

3.05 ± 3.68 / 27.70 ± 4.19

1.94 ± 2.58 / 46.27 ± 2.74

0.02 ± 0.05 / 0.02 ± 0.05

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

13.3.0

12.6.1

13.3.0

12.6.1

13.0.0

12.6.1

0.0.0

12.6.1

microsoft/xlm-align-base

278

250

512

True

14,744 ± 2,870 / 3,265 ± 1,053

2.63

2.34

2.04

2.20

2.86

4.03

2.16

2.68

2.75

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

38.76 ± 2.04 / 56.09 ± 2.02

5.92 ± 1.91 / 46.95 ± 3.38

10.47 ± 1.42 / 43.32 ± 3.55

85.97 ± 1.12 / 86.52 ± 1.08

2.54 ± 4.09 / 19.42 ± 4.54

0.02 ± 1.38 / 44.65 ± 2.65

0.72 ± 0.93 / 1.00 ± 1.31

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

13.3.0

0.0.0

13.3.0

0.0.0

13.0.0

0.0.0

12.6.1

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

7242

32

32768

False

634 ± 179 / 110 ± 35

2.64

2.38

2.82

2.36

3.26

3.06

2.38

2.80

2.09

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

22.55 ± 4.07 / 46.66 ± 3.12

3.40 ± 1.87 / 48.75 ± 1.47

19.18 ± 3.69 / 49.62 ± 2.59

61.28 ± 2.98 / 54.02 ± 3.55

32.07 ± 3.55 / 51.69 ± 3.46

1.68 ± 1.41 / 50.06 ± 1.22

39.00 ± 1.21 / 59.78 ± 1.14

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

13.3.0

9.3.1

12.4.0

9.2.0

13.3.0

9.3.1

13.0.0

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

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

7242

32

32768

True

5,054 ± 1,200 / 1,056 ± 339

2.67

2.37

2.62

2.00

3.46

3.57

2.32

3.04

1.94

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

16.08 ± 4.33 / 34.46 ± 4.77

2.54 ± 1.29 / 50.66 ± 0.62

18.66 ± 4.26 / 38.73 ± 3.66

58.96 ± 2.05 / 52.20 ± 2.50

15.18 ± 6.92 / 36.01 ± 7.24

0.00 ± 0.00 / 33.26 ± 0.34

39.20 ± 1.10 / 54.89 ± 1.25

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

13.3.0

12.5.3

13.3.0

12.5.3

13.0.0

12.5.3

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

278

250

512

True

20,154 ± 4,438 / 3,890 ± 1,256

2.70

2.40

2.67

2.25

3.24

3.93

2.54

2.37

2.18

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

33.26 ± 1.68 / 52.59 ± 1.73

1.15 ± 1.57 / 49.60 ± 0.88

9.56 ± 0.42 / 27.88 ± 0.44

80.92 ± 0.59 / 81.63 ± 0.56

12.97 ± 2.96 / 31.99 ± 2.53

1.19 ± 2.37 / 43.13 ± 4.70

0.00 ± 0.00 / 0.00 ± 0.00

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

13.3.0

12.6.1

13.3.0

0.0.0

13.0.0

12.8.0

0.0.0

12.6.1

sentence-transformers/stsb-xlm-r-multilingual

278

250

512

True

15,040 ± 2,953 / 3,417 ± 1,100

2.70

2.50

2.67

2.26

3.16

3.56

2.48

2.77

2.18

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

37.79 ± 2.49 / 56.10 ± 1.91

0.04 ± 0.78 / 45.96 ± 2.83

10.04 ± 0.99 / 28.66 ± 0.92

82.97 ± 0.83 / 83.62 ± 0.81

18.07 ± 4.85 / 39.76 ± 3.32

2.93 ± 1.96 / 46.51 ± 4.19

0.00 ± 0.00 / 0.00 ± 0.00

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

13.3.0

0.0.0

13.3.0

0.0.0

13.0.0

12.8.0

0.0.0

12.6.1

ibm-granite/granite-8b-code-base-4k (few-shot)

8055

49

4096

True

2,313 ± 423 / 682 ± 210

2.71

2.60

2.78

2.31

3.59

3.34

2.32

2.75

1.95

48.44 ± 1.69 / 36.99 ± 1.77

39.07 ± 1.03 / 56.85 ± 1.91

9.72 ± 1.58 / 46.85 ± 3.66

51.18 ± 0.92 / 56.54 ± 0.69

68.40 ± 1.16 / 62.53 ± 1.69

65.15 ± 0.79 / 60.39 ± 2.11

42.00 ± 1.78 / 59.90 ± 1.22

5.20 ± 2.23 / 36.33 ± 1.30

3.32 ± 2.02 / 37.81 ± 3.26

37.51 ± 2.58 / 60.94 ± 3.06

59.77 ± 3.55 / 45.71 ± 4.91

74.45 ± 1.19 / 72.26 ± 0.89

3.97 ± 1.50 / 34.79 ± 0.80

50.18 ± 1.05 / 56.07 ± 0.89

50.89 ± 2.90 / 35.75 ± 4.67

9.18 ± 3.91 / 27.61 ± 4.83

0.50 ± 0.94 / 33.77 ± 0.30

17.43 ± 3.38 / 41.32 ± 3.18

66.82 ± 2.36 / 65.84 ± 2.35

26.68 ± 4.88 / 47.93 ± 2.75

-0.36 ± 1.67 / 37.57 ± 3.35

36.47 ± 0.96 / 51.89 ± 1.05

59.07 ± 0.78 / 51.00 ± 2.06

49.75 ± 2.44 / 65.93 ± 1.66

14.71 ± 2.21 / 53.75 ± 3.07

29.45 ± 2.13 / 56.14 ± 2.53

63.29 ± 2.51 / 52.18 ± 4.31

13.81 ± 1.66 / 36.99 ± 2.58

8.16 ± 1.97 / 44.29 ± 4.25

56.64 ± 0.68 / 66.29 ± 0.71

72.76 ± 0.57 / 67.49 ± 0.90

62.35 ± 1.68 / 67.34 ± 0.77

21.57 ± 2.22 / 59.22 ± 1.69

69.80 ± 3.60 / 81.37 ± 2.26

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

Twitter/twhin-bert-large

561

250

512

True

9,707 ± 1,664 / 2,549 ± 831

2.75

2.59

2.89

2.33

3.17

3.86

2.28

2.89

2.03

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

32.07 ± 2.95 / 50.25 ± 3.47

2.20 ± 2.00 / 43.42 ± 4.87

8.19 ± 0.76 / 33.02 ± 1.85

84.73 ± 1.49 / 85.19 ± 1.59

-0.64 ± 3.87 / 22.47 ± 3.96

1.37 ± 2.46 / 39.78 ± 3.24

4.15 ± 4.39 / 5.74 ± 6.06

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

13.3.0

0.0.0

13.3.0

0.0.0

13.0.0

12.7.0

0.0.0

12.6.1

Geotrend/distilbert-base-25lang-cased

109

85

512

True

26,099 ± 5,881 / 5,178 ± 1,665

2.79

2.65

2.62

2.32

3.35

3.87

2.42

2.80

2.33

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

29.56 ± 1.49 / 50.69 ± 1.62

2.08 ± 1.89 / 48.68 ± 2.96

6.81 ± 0.33 / 30.96 ± 0.65

83.21 ± 0.53 / 83.81 ± 0.45

3.90 ± 4.05 / 25.25 ± 5.25

2.37 ± 4.63 / 48.46 ± 3.19

1.35 ± 1.03 / 2.54 ± 1.88

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

13.3.0

12.6.1

13.3.0

12.6.1

13.0.0

12.6.1

0.0.0

12.6.1

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

7242

32

32768

False

2,088 ± 352 / 706 ± 214

2.79

2.69

2.86

2.33

3.50

3.68

2.25

2.92

2.08

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

14.70 ± 7.78 / 36.09 ± 6.06

0.71 ± 2.00 / 36.90 ± 2.10

20.66 ± 3.67 / 45.91 ± 3.45

60.37 ± 3.60 / 59.38 ± 3.85

8.21 ± 5.06 / 27.79 ± 5.76

0.00 ± 0.00 / 33.26 ± 0.34

43.69 ± 2.03 / 60.55 ± 1.76

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

13.3.0

12.3.1

12.4.0

12.5.2

13.3.0

12.3.1

13.0.0

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

ibm-granite/granite-8b-code-instruct-4k (few-shot)

8055

49

4096

True

5,617 ± 995 / 1,623 ± 540

2.81

2.67

2.82

2.35

3.75

3.45

2.54

2.85

2.02

45.90 ± 2.53 / 33.00 ± 1.93

37.11 ± 1.88 / 56.47 ± 1.59

11.70 ± 2.16 / 50.31 ± 3.91

50.11 ± 0.83 / 55.71 ± 0.49

66.91 ± 1.50 / 54.98 ± 2.20

62.82 ± 1.23 / 53.14 ± 3.17

40.71 ± 1.63 / 59.35 ± 1.58

9.50 ± 1.68 / 46.31 ± 3.06

6.74 ± 1.70 / 42.10 ± 4.67

32.83 ± 1.83 / 55.30 ± 2.35

52.85 ± 2.76 / 35.11 ± 3.66

73.93 ± 1.58 / 73.97 ± 1.19

8.27 ± 2.90 / 43.29 ± 4.82

48.49 ± 0.77 / 54.50 ± 0.73

43.20 ± 3.61 / 32.10 ± 3.76

2.54 ± 2.60 / 17.05 ± 2.70

0.00 ± 0.00 / 33.69 ± 0.28

14.28 ± 2.94 / 38.21 ± 2.38

60.46 ± 2.53 / 58.29 ± 2.53

21.59 ± 6.94 / 40.68 ± 5.50

0.51 ± 0.78 / 36.20 ± 2.37

33.54 ± 1.00 / 49.02 ± 0.91

54.45 ± 1.17 / 42.36 ± 2.59

43.62 ± 3.18 / 59.82 ± 2.70

15.24 ± 1.87 / 55.49 ± 2.89

26.00 ± 2.28 / 51.82 ± 2.70

60.72 ± 2.14 / 45.52 ± 2.46

12.38 ± 1.62 / 29.91 ± 1.91

10.96 ± 1.47 / 47.97 ± 3.45

51.20 ± 0.91 / 61.75 ± 0.63

72.59 ± 0.91 / 65.83 ± 1.30

61.61 ± 1.45 / 67.09 ± 1.38

18.37 ± 2.07 / 56.26 ± 2.62

66.68 ± 3.56 / 78.95 ± 2.38

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

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

7242

32

32768

True

2,219 ± 427 / 717 ± 224

2.82

2.64

2.88

2.31

3.59

3.67

2.27

3.01

2.18

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

15.49 ± 6.74 / 34.45 ± 5.64

1.59 ± 1.86 / 39.93 ± 4.19

15.98 ± 3.74 / 39.67 ± 3.36

58.67 ± 3.95 / 58.47 ± 3.96

13.60 ± 5.67 / 34.63 ± 7.58

0.00 ± 0.00 / 33.26 ± 0.34

40.95 ± 1.80 / 55.82 ± 1.95

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

13.3.0

12.1.0

12.5.2

13.3.0

12.1.0

13.0.0

12.5.2

12.1.0

12.5.2

12.1.0

12.5.2

12.1.0

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

7242

32

32768

False

634 ± 179 / 110 ± 35

2.83

2.53

2.84

2.40

3.68

2.49

3.03

1.97

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

12.93 ± 5.42 / 30.40 ± 3.15

-0.36 ± 1.36 / 33.94 ± 0.32

18.06 ± 3.16 / 42.57 ± 2.89

55.42 ± 2.12 / 46.41 ± 2.50

15.85 ± 6.84 / 36.28 ± 7.13

1.11 ± 2.41 / 36.79 ± 4.00

33.54 ± 1.29 / 50.80 ± 1.31

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

13.3.0

9.3.1

12.4.0

9.3.1

13.3.0

9.3.1

13.0.0

12.9.0

9.3.1

12.4.0

9.3.1

12.4.0

meta-llama/Llama-3.2-3B-Instruct (few-shot)

3213

128

131073

False

10,424 ± 2,641 / 2,081 ± 666

2.85

2.62

3.09

2.36

3.63

3.41

2.66

3.06

2.00

41.12 ± 3.39 / 32.50 ± 2.74

42.77 ± 2.76 / 54.70 ± 4.19

11.52 ± 3.01 / 49.37 ± 4.12

51.14 ± 1.03 / 60.18 ± 0.55

49.66 ± 1.79 / 39.31 ± 2.55

51.98 ± 1.55 / 42.48 ± 3.10

44.13 ± 2.80 / 60.09 ± 3.10

0.67 ± 1.18 / 33.81 ± 0.33

1.11 ± 0.93 / 33.03 ± 0.39

28.62 ± 4.16 / 56.91 ± 4.14

43.74 ± 2.58 / 34.37 ± 2.59

76.98 ± 1.31 / 71.38 ± 3.20

16.01 ± 2.24 / 51.83 ± 3.50

48.38 ± 1.78 / 57.83 ± 0.99

27.57 ± 1.71 / 22.52 ± 1.18

10.07 ± 5.45 / 28.32 ± 4.30

-1.39 ± 1.30 / 34.40 ± 1.96

22.98 ± 2.48 / 50.74 ± 1.59

58.24 ± 3.73 / 47.44 ± 4.83

13.76 ± 2.27 / 33.66 ± 4.22

1.77 ± 2.13 / 45.44 ± 4.00

45.13 ± 1.12 / 64.71 ± 0.74

55.52 ± 2.07 / 46.18 ± 2.32

50.52 ± 2.29 / 62.39 ± 2.63

9.87 ± 2.95 / 42.20 ± 3.60

20.20 ± 3.28 / 47.02 ± 5.20

43.66 ± 2.01 / 40.23 ± 1.75

12.87 ± 1.32 / 37.23 ± 1.55

17.94 ± 3.48 / 55.88 ± 3.97

47.77 ± 1.82 / 64.44 ± 1.35

68.44 ± 1.14 / 56.80 ± 2.31

66.00 ± 1.41 / 70.47 ± 1.02

32.04 ± 3.44 / 65.62 ± 1.88

49.54 ± 3.13 / 75.26 ± 1.64

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

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

6738

32

4096

False

2,643 ± 455 / 800 ± 247

2.93

2.60

3.07

2.55

3.65

3.78

2.62

3.03

2.14

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

13.59 ± 6.27 / 36.87 ± 4.51

-1.07 ± 2.09 / 44.83 ± 2.20

16.13 ± 2.52 / 39.51 ± 1.98

59.77 ± 3.38 / 56.97 ± 4.30

13.24 ± 5.37 / 38.49 ± 4.97

-0.54 ± 1.61 / 36.94 ± 2.79

31.87 ± 2.20 / 46.21 ± 1.15

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

13.3.0

9.3.1

12.4.0

9.3.1

13.3.0

9.3.1

13.0.0

12.9.0

12.10.0

9.3.1

12.4.0

9.3.1

12.4.0

sentence-transformers/quora-distilbert-multilingual

135

120

512

True

26,458 ± 5,992 / 5,274 ± 1,731

3.08

3.07

3.08

2.66

3.36

3.78

3.11

2.68

2.89

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

33.10 ± 1.86 / 52.77 ± 1.64

1.02 ± 0.94 / 47.05 ± 2.13

6.48 ± 0.37 / 27.44 ± 0.44

82.91 ± 0.89 / 83.43 ± 0.87

9.77 ± 3.39 / 32.64 ± 2.55

1.67 ± 2.22 / 46.20 ± 3.31

0.00 ± 0.00 / 0.00 ± 0.00

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

13.3.0

0.0.0

13.3.0

0.0.0

13.0.0

12.6.1

0.0.0

12.6.1

MaLA-LM/emma-500-llama2-7b (few-shot)

6738

32

4096

True

6,275 ± 1,193 / 1,755 ± 578

3.12

3.00

3.15

2.46

3.59

3.73

3.29

3.34

2.38

28.18 ± 3.39 / 24.25 ± 3.30

29.32 ± 7.19 / 41.08 ± 8.29

2.90 ± 2.18 / 37.93 ± 4.98

56.48 ± 1.11 / 62.92 ± 0.96

36.96 ± 3.10 / 34.68 ± 3.19

39.38 ± 3.30 / 37.06 ± 3.49

32.67 ± 2.52 / 44.37 ± 3.06

2.18 ± 2.36 / 38.05 ± 3.18

5.33 ± 2.97 / 44.30 ± 4.99

45.23 ± 5.03 / 67.75 ± 4.41

41.49 ± 2.82 / 38.09 ± 2.86

75.64 ± 1.51 / 76.06 ± 1.42

0.66 ± 1.97 / 33.73 ± 0.54

57.48 ± 0.54 / 63.85 ± 0.46

31.81 ± 1.93 / 29.47 ± 2.02

19.61 ± 6.74 / 33.96 ± 6.93

3.63 ± 1.69 / 44.49 ± 3.89

16.72 ± 7.29 / 46.83 ± 5.93

40.18 ± 3.60 / 39.95 ± 3.38

14.19 ± 8.12 / 28.15 ± 8.15

0.31 ± 1.71 / 41.35 ± 4.05

41.60 ± 2.49 / 60.78 ± 2.12

32.33 ± 2.48 / 30.20 ± 1.92

26.39 ± 5.23 / 36.06 ± 6.62

1.44 ± 1.38 / 33.60 ± 0.42

28.15 ± 5.57 / 54.13 ± 6.75

36.61 ± 3.37 / 31.91 ± 2.20

8.77 ± 1.80 / 25.31 ± 1.42

3.52 ± 2.07 / 35.34 ± 1.61

59.51 ± 0.97 / 70.33 ± 0.64

47.20 ± 3.39 / 44.00 ± 3.43

64.82 ± 1.13 / 67.11 ± 1.41

7.57 ± 2.31 / 45.83 ± 3.97

73.88 ± 1.02 / 83.56 ± 0.75

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

ibm-granite/granite-3.0-3b-a800m-instruct (few-shot)

3374

49

4096

True

10,246 ± 3,021 / 1,629 ± 550

3.12

3.01

3.23

2.61

4.11

4.19

2.55

3.07

2.23

37.37 ± 2.46 / 26.81 ± 2.24

31.44 ± 1.82 / 48.96 ± 2.35

5.27 ± 2.40 / 40.63 ± 4.68

48.41 ± 1.10 / 55.05 ± 0.97

44.89 ± 2.26 / 34.93 ± 2.45

48.08 ± 1.68 / 34.39 ± 2.61

32.29 ± 1.15 / 51.91 ± 2.66

7.49 ± 1.65 / 47.79 ± 3.81

4.65 ± 1.91 / 45.75 ± 5.13

26.37 ± 1.51 / 47.59 ± 2.41

40.68 ± 2.32 / 24.33 ± 2.43

68.96 ± 2.04 / 72.76 ± 1.25

4.77 ± 1.97 / 43.64 ± 5.60

49.73 ± 0.76 / 56.63 ± 0.69

23.14 ± 2.08 / 23.09 ± 2.24

5.07 ± 2.69 / 27.01 ± 2.31

0.18 ± 1.67 / 33.93 ± 0.34

14.15 ± 2.49 / 36.10 ± 1.65

45.56 ± 1.92 / 42.78 ± 1.78

7.44 ± 3.71 / 28.90 ± 5.97

0.92 ± 2.19 / 40.29 ± 3.87

20.82 ± 1.22 / 31.49 ± 1.49

47.31 ± 1.67 / 31.36 ± 2.00

48.28 ± 4.28 / 64.07 ± 3.81

14.08 ± 1.29 / 52.67 ± 2.70

28.37 ± 4.07 / 55.92 ± 4.76

49.25 ± 2.57 / 36.48 ± 2.14

9.45 ± 1.76 / 39.66 ± 1.14

11.87 ± 2.68 / 47.32 ± 3.85

54.20 ± 1.44 / 67.04 ± 0.75

52.79 ± 4.09 / 43.45 ± 2.82

65.92 ± 1.02 / 70.47 ± 0.75

16.74 ± 2.67 / 55.45 ± 3.35

64.92 ± 2.84 / 80.88 ± 1.27

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

ibm-granite/granite-3b-code-base-2k (few-shot)

3483

49

2048

True

2,732 ± 868 / 662 ± 238

3.16

2.92

3.63

2.50

3.82

4.00

3.01

3.10

2.27

38.62 ± 3.40 / 27.71 ± 3.01

35.47 ± 1.35 / 52.70 ± 2.05

5.07 ± 1.76 / 43.91 ± 4.86

45.21 ± 0.84 / 50.96 ± 0.94

53.93 ± 3.93 / 48.95 ± 4.17

54.04 ± 1.83 / 49.74 ± 2.48

23.83 ± 3.47 / 45.39 ± 3.46

3.91 ± 1.46 / 42.54 ± 4.53

1.55 ± 2.39 / 40.63 ± 4.26

2.37 ± 0.20 / 12.14 ± 1.07

51.76 ± 4.53 / 41.73 ± 6.65

70.61 ± 1.12 / 60.47 ± 1.13

6.24 ± 3.11 / 46.34 ± 5.43

44.67 ± 1.34 / 50.56 ± 1.33

38.52 ± 3.25 / 28.84 ± 5.49

5.15 ± 4.46 / 21.10 ± 4.20

0.00 ± 0.00 / 33.69 ± 0.28

12.94 ± 2.60 / 36.06 ± 2.17

60.88 ± 2.03 / 60.02 ± 1.84

6.24 ± 4.69 / 31.19 ± 4.00

-0.35 ± 1.18 / 34.50 ± 1.25

18.54 ± 1.93 / 29.79 ± 1.35

49.38 ± 2.20 / 42.66 ± 3.24

41.72 ± 4.07 / 60.45 ± 3.07

7.67 ± 1.52 / 46.66 ± 3.23

13.70 ± 2.43 / 30.21 ± 3.80

50.88 ± 3.41 / 39.51 ± 3.29

12.39 ± 1.50 / 30.05 ± 1.80

3.31 ± 1.19 / 37.97 ± 4.40

48.44 ± 1.06 / 58.85 ± 0.75

60.64 ± 2.11 / 55.14 ± 2.01

61.20 ± 1.16 / 61.92 ± 1.68

7.63 ± 2.79 / 46.39 ± 3.79

69.83 ± 2.12 / 80.15 ± 1.27

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

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

135

120

512

True

33,753 ± 8,349 / 5,937 ± 1,946

3.16

3.07

3.08

2.66

3.41

3.78

3.11

3.25

2.89

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

33.10 ± 1.86 / 52.77 ± 1.64

0.80 ± 1.69 / 45.59 ± 3.23

6.14 ± 0.74 / 28.02 ± 0.58

82.91 ± 0.89 / 83.43 ± 0.87

9.77 ± 3.39 / 32.64 ± 2.55

1.67 ± 2.22 / 46.20 ± 3.31

0.00 ± 0.00 / 0.00 ± 0.00

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

13.3.0

12.6.1

0.0.0

13.3.0

0.0.0

13.0.0

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

3.16

2.67

2.85

2.46

3.43

3.80

3.05

4.04

2.95

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

31.32 ± 1.98 / 51.09 ± 1.51

1.91 ± 1.14 / 46.54 ± 2.46

3.69 ± 0.48 / 27.48 ± 0.49

82.24 ± 0.85 / 82.84 ± 0.78

6.35 ± 5.07 / 29.58 ± 4.89

2.84 ± 1.41 / 50.47 ± 1.13

0.00 ± 0.00 / 0.00 ± 0.00

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

13.3.0

0.0.0

13.3.0

0.0.0

13.0.0

12.8.0

12.6.1

ibm-granite/granite-3b-code-instruct-2k (few-shot)

3483

49

2048

True

9,059 ± 1,947 / 2,201 ± 728

3.20

3.02

3.29

2.55

4.08

4.19

2.90

3.24

2.35

37.21 ± 2.75 / 27.74 ± 2.59

31.54 ± 2.39 / 50.61 ± 2.88

6.30 ± 1.61 / 49.09 ± 2.54

44.86 ± 0.80 / 51.51 ± 0.91

53.78 ± 2.43 / 49.41 ± 2.56

55.14 ± 1.27 / 51.07 ± 1.78

26.21 ± 1.63 / 43.33 ± 1.46

3.90 ± 1.45 / 43.86 ± 4.21

2.42 ± 1.39 / 41.58 ± 3.89

24.86 ± 1.34 / 45.77 ± 1.85

50.10 ± 4.30 / 42.80 ± 5.47

65.67 ± 3.92 / 64.00 ± 3.84

4.55 ± 2.18 / 45.11 ± 4.32

42.83 ± 1.02 / 49.35 ± 1.09

33.57 ± 2.48 / 33.47 ± 2.48

0.60 ± 2.01 / 16.42 ± 1.16

0.00 ± 0.00 / 33.69 ± 0.28

11.27 ± 2.38 / 33.54 ± 1.64

56.88 ± 2.51 / 57.68 ± 2.14

3.80 ± 5.87 / 28.41 ± 4.70

-0.21 ± 2.20 / 34.20 ± 1.19

13.72 ± 2.56 / 24.11 ± 2.40

49.16 ± 2.12 / 40.34 ± 2.81

35.17 ± 4.48 / 51.15 ± 4.55

9.79 ± 2.06 / 50.77 ± 3.64

22.48 ± 2.59 / 45.90 ± 3.03

48.53 ± 3.89 / 38.20 ± 2.92

10.15 ± 1.55 / 22.01 ± 1.44

4.88 ± 2.27 / 38.78 ± 3.56

45.38 ± 0.93 / 56.09 ± 1.05

58.30 ± 2.16 / 53.45 ± 1.98

59.01 ± 2.14 / 62.37 ± 1.73

10.33 ± 3.06 / 53.28 ± 2.21

65.04 ± 2.20 / 75.93 ± 1.50

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

dbmdz/bert-base-historic-multilingual-cased

111

32

512

True

20,047 ± 4,407 / 3,844 ± 1,259

3.21

3.23

3.17

2.35

3.63

3.98

2.96

3.44

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

24.79 ± 3.07 / 45.25 ± 3.48

-1.21 ± 1.45 / 47.43 ± 1.67

6.01 ± 0.45 / 29.08 ± 1.30

80.45 ± 1.48 / 81.32 ± 1.42

0.90 ± 2.61 / 26.49 ± 2.31

2.52 ± 1.88 / 47.78 ± 1.67

0.58 ± 0.81 / 1.12 ± 1.62

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

13.3.0

12.6.1

0.0.0

13.3.0

0.0.0

13.0.0

12.8.0

12.6.1

EuropeanParliament/EUBERT

94

66

512

True

20,070 ± 3,977 / 4,400 ± 1,435

3.32

3.20

3.62

3.04

3.63

4.15

2.94

3.10

2.89

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

36.28 ± 1.79 / 56.00 ± 1.23

2.71 ± 1.10 / 49.68 ± 1.24

6.50 ± 0.42 / 27.51 ± 0.99

59.50 ± 1.56 / 58.98 ± 1.55

0.94 ± 4.40 / 23.64 ± 4.57

3.25 ± 2.04 / 49.77 ± 1.40

5.56 ± 1.52 / 10.14 ± 2.41

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

13.3.0

12.6.1

13.3.0

12.6.1

13.0.0

12.6.1

0.0.0

12.6.1

ibm-granite/granite-3.0-3b-a800m-base (few-shot)

3374

49

4096

True

10,504 ± 3,028 / 1,678 ± 559

3.37

3.45

3.42

2.82

4.22

4.34

3.10

3.23

2.40

31.80 ± 2.87 / 23.06 ± 2.09

6.85 ± 2.25 / 19.42 ± 0.91

0.97 ± 1.10 / 36.48 ± 3.91

49.83 ± 1.73 / 55.19 ± 1.84

40.08 ± 2.60 / 33.17 ± 1.81

43.96 ± 1.65 / 32.96 ± 2.24

31.90 ± 1.50 / 53.03 ± 1.81

-0.07 ± 0.97 / 35.01 ± 1.42

1.27 ± 2.35 / 38.10 ± 4.51

23.32 ± 2.39 / 43.13 ± 3.33

36.01 ± 3.07 / 24.61 ± 4.22

57.18 ± 5.33 / 62.72 ± 5.30

1.52 ± 2.14 / 38.30 ± 3.62

51.04 ± 0.95 / 56.97 ± 0.96

18.07 ± 3.62 / 18.73 ± 2.54

1.67 ± 1.99 / 20.92 ± 3.22

-0.72 ± 1.22 / 33.96 ± 0.50

12.27 ± 2.81 / 30.66 ± 1.47

41.27 ± 4.31 / 40.85 ± 4.31

4.35 ± 3.94 / 26.17 ± 3.53

-0.20 ± 2.17 / 43.01 ± 3.39

19.69 ± 2.66 / 29.77 ± 2.80

40.61 ± 2.18 / 28.49 ± 2.11

31.86 ± 3.60 / 42.96 ± 3.98

5.36 ± 3.96 / 37.83 ± 4.03

25.99 ± 3.85 / 47.72 ± 4.74

42.52 ± 3.31 / 33.08 ± 2.70

9.91 ± 1.71 / 35.24 ± 2.62

0.69 ± 2.82 / 36.10 ± 2.58

56.95 ± 1.18 / 66.87 ± 1.37

49.44 ± 3.68 / 39.69 ± 2.34

66.65 ± 1.04 / 65.72 ± 1.32

12.56 ± 2.15 / 54.20 ± 3.42

63.29 ± 4.61 / 75.62 ± 3.79

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

utter-project/EuroLLM-1.7B-Instruct (few-shot)

1657

128

4096

True

15,009 ± 4,072 / 2,702 ± 878

3.45

3.15

3.42

2.80

4.26

4.57

3.19

3.49

2.75

19.61 ± 2.68 / 17.44 ± 2.64

37.92 ± 1.74 / 46.23 ± 1.91

2.81 ± 1.13 / 38.15 ± 2.81

50.05 ± 1.02 / 56.82 ± 0.77

31.43 ± 1.78 / 30.82 ± 2.35

36.92 ± 1.75 / 37.80 ± 1.67

30.63 ± 1.48 / 37.24 ± 1.90

0.98 ± 1.59 / 42.00 ± 2.28

1.67 ± 1.96 / 34.92 ± 1.93

33.24 ± 2.51 / 55.11 ± 2.82

27.41 ± 2.70 / 24.45 ± 3.82

72.24 ± 0.82 / 68.89 ± 2.63

0.13 ± 1.85 / 36.22 ± 3.14

49.77 ± 0.63 / 56.59 ± 0.54

13.29 ± 2.33 / 14.72 ± 2.11

6.83 ± 5.62 / 31.41 ± 4.70

0.92 ± 1.51 / 42.09 ± 3.39

7.49 ± 1.26 / 24.16 ± 1.95

33.53 ± 3.87 / 35.41 ± 3.77

4.25 ± 5.04 / 26.21 ± 4.24

-2.32 ± 2.11 / 45.19 ± 2.78

15.41 ± 2.05 / 25.07 ± 1.98

28.49 ± 2.30 / 24.73 ± 1.76

43.18 ± 2.89 / 58.22 ± 3.50

2.92 ± 1.40 / 44.65 ± 3.51

23.26 ± 3.37 / 48.47 ± 3.57

32.45 ± 2.17 / 30.83 ± 2.31

7.03 ± 2.08 / 34.16 ± 1.83

5.58 ± 1.32 / 44.79 ± 3.28

51.18 ± 1.19 / 61.82 ± 1.19

37.47 ± 1.64 / 32.39 ± 2.53

58.61 ± 2.46 / 62.78 ± 1.22

5.30 ± 1.43 / 46.95 ± 3.51

63.26 ± 0.73 / 74.41 ± 0.65

13.1.0

13.3.0

13.1.0

13.3.0

13.1.0

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

135

120

512

True

34,042 ± 8,482 / 5,951 ± 1,950

3.46

3.39

3.57

3.13

3.65

3.88

3.51

3.21

3.31

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

35.18 ± 2.10 / 55.52 ± 1.45

1.14 ± 1.81 / 48.47 ± 1.64

1.63 ± 0.33 / 21.45 ± 1.39

75.63 ± 1.41 / 76.23 ± 1.36

9.82 ± 2.60 / 36.40 ± 2.64

3.65 ± 1.93 / 48.34 ± 1.78

0.00 ± 0.00 / 0.00 ± 0.00

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

13.3.0

12.6.1

13.3.0

0.0.0

13.0.0

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

3.46

3.75

3.49

3.09

3.62

3.77

3.33

3.42

3.21

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

33.35 ± 1.84 / 53.45 ± 3.04

2.64 ± 2.11 / 49.47 ± 1.79

1.27 ± 0.46 / 12.20 ± 2.90

77.16 ± 0.93 / 78.00 ± 0.91

10.41 ± 3.80 / 34.36 ± 3.61

4.09 ± 2.27 / 47.26 ± 3.09

0.00 ± 0.00 / 0.00 ± 0.00

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

13.3.0

12.6.1

13.3.0

0.0.0

13.0.0

12.6.1

0.0.0

12.6.1

HuggingFaceTB/SmolLM2-1.7B-Instruct (few-shot)

1711

49

8192

True

15,971 ± 3,654 / 3,609 ± 1,197

3.47

3.38

3.66

2.82

3.98

4.47

3.40

3.74

2.31

29.44 ± 1.81 / 20.31 ± 1.68

18.49 ± 2.47 / 35.29 ± 2.83

1.73 ± 1.63 / 38.18 ± 4.15

44.39 ± 0.80 / 50.40 ± 1.02

37.60 ± 2.17 / 29.30 ± 2.43

38.38 ± 2.48 / 30.13 ± 2.95

24.05 ± 3.58 / 40.36 ± 4.22

3.56 ± 1.93 / 38.60 ± 3.52

2.61 ± 2.57 / 38.57 ± 3.89

13.58 ± 3.16 / 25.34 ± 5.83

37.37 ± 1.87 / 26.31 ± 3.34

64.46 ± 3.06 / 69.83 ± 2.00

4.49 ± 1.96 / 46.63 ± 4.39

43.92 ± 1.06 / 49.57 ± 1.17

26.23 ± 3.53 / 23.26 ± 2.30

6.86 ± 5.25 / 23.96 ± 4.13

2.69 ± 1.42 / 45.61 ± 2.69

10.84 ± 2.59 / 28.57 ± 2.09

40.28 ± 3.29 / 42.15 ± 2.85

3.94 ± 3.10 / 30.51 ± 3.43

-0.26 ± 1.92 / 38.29 ± 4.03

10.68 ± 1.75 / 17.52 ± 1.85

32.54 ± 1.57 / 26.92 ± 1.87

27.03 ± 2.54 / 42.80 ± 3.28

8.95 ± 1.62 / 51.86 ± 2.23

18.38 ± 1.26 / 39.18 ± 2.13

31.84 ± 3.39 / 28.66 ± 1.77

1.56 ± 3.25 / 28.78 ± 2.60

5.05 ± 1.34 / 43.99 ± 4.14

40.55 ± 0.77 / 48.56 ± 0.95

47.58 ± 2.41 / 39.52 ± 1.41

66.78 ± 0.76 / 61.52 ± 0.99

20.53 ± 3.83 / 58.47 ± 2.90

58.07 ± 2.23 / 69.96 ± 1.63

13.1.0

13.3.0

13.1.0

13.3.0

13.1.0

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

135

120

512

True

33,247 ± 8,123 / 6,017 ± 1,977

3.53

3.75

3.49

3.09

3.56

3.86

3.33

3.92

3.21

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

34.19 ± 1.88 / 53.26 ± 3.44

2.64 ± 2.11 / 49.47 ± 1.79

1.22 ± 0.49 / 12.16 ± 3.00

77.00 ± 1.08 / 77.85 ± 1.05

9.59 ± 3.69 / 32.95 ± 3.64

4.09 ± 2.27 / 47.26 ± 3.09

0.00 ± 0.00 / 0.00 ± 0.00

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

13.3.0

12.6.1

13.3.0

0.0.0

13.0.0

12.8.0

12.6.1

HuggingFaceTB/SmolLM2-1.7B (few-shot)

1711

49

8192

True

16,249 ± 3,690 / 3,689 ± 1,226

3.63

3.66

3.83

2.76

4.07

4.60

3.60

3.89

2.64

24.47 ± 3.42 / 18.70 ± 2.18

9.93 ± 2.70 / 23.57 ± 3.00

1.22 ± 1.81 / 35.31 ± 1.93

42.09 ± 2.63 / 47.54 ± 2.94

26.70 ± 4.42 / 24.56 ± 2.10

28.23 ± 3.78 / 28.27 ± 2.80

23.25 ± 4.16 / 36.07 ± 4.20

-0.47 ± 1.05 / 33.93 ± 0.92

0.26 ± 0.74 / 33.32 ± 0.79

13.40 ± 2.83 / 26.51 ± 4.94

35.96 ± 3.50 / 26.41 ± 4.11

68.31 ± 1.43 / 72.51 ± 1.03

3.61 ± 1.79 / 49.47 ± 1.68

43.26 ± 1.85 / 49.32 ± 1.97

20.50 ± 4.51 / 18.93 ± 3.84

8.08 ± 2.30 / 27.38 ± 2.88

0.83 ± 1.65 / 45.84 ± 2.02

10.84 ± 2.45 / 28.36 ± 1.48

27.91 ± 4.97 / 30.98 ± 4.28

3.16 ± 1.14 / 23.85 ± 3.17

-0.48 ± 0.89 / 33.97 ± 1.00

16.56 ± 1.66 / 26.11 ± 1.42

28.67 ± 3.31 / 25.27 ± 2.68

19.69 ± 2.50 / 29.00 ± 2.22

5.07 ± 0.89 / 47.60 ± 2.39

18.43 ± 2.31 / 38.33 ± 2.91

22.84 ± 5.42 / 25.11 ± 3.52

4.60 ± 2.12 / 29.94 ± 1.50

2.55 ± 1.41 / 40.88 ± 3.15

40.33 ± 1.19 / 48.35 ± 1.31

41.57 ± 4.29 / 37.51 ± 3.05

62.32 ± 1.12 / 67.09 ± 0.96

8.04 ± 3.17 / 48.16 ± 5.38

56.01 ± 3.10 / 67.43 ± 2.41

13.1.0

13.3.0

13.1.0

13.3.0

13.1.0

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

278

250

512

True

12,783 ± 2,537 / 2,712 ± 885

3.79

3.89

3.48

3.59

4.28

3.73

3.89

3.71

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

20.94 ± 2.82 / 42.72 ± 2.88

1.40 ± 1.40 / 48.02 ± 2.05

10.48 ± 1.75 / 28.80 ± 1.59

73.34 ± 1.57 / 74.24 ± 1.56

1.49 ± 2.48 / 20.15 ± 3.56

0.97 ± 2.25 / 44.25 ± 3.12

0.00 ± 0.00 / 0.01 ± 0.02

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

13.3.0

12.6.1

13.3.0

12.6.1

13.0.0

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

3.84

3.91

3.94

3.63

3.98

4.17

3.75

3.89

3.44

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

9.46 ± 4.02 / 28.69 ± 4.13

0.04 ± 1.75 / 47.53 ± 1.60

6.13 ± 0.63 / 21.73 ± 0.95

72.08 ± 1.25 / 72.93 ± 1.20

-1.81 ± 2.47 / 15.54 ± 0.87

2.65 ± 2.40 / 48.48 ± 1.87

0.00 ± 0.00 / 0.00 ± 0.00

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

13.3.0

12.6.1

0.0.0

13.3.0

0.0.0

13.0.0

12.6.1

0.0.0

12.6.1

HuggingFaceTB/SmolLM2-360M (few-shot)

362

49

8192

True

22,023 ± 6,203 / 3,675 ± 1,231

4.10

4.14

4.29

4.01

4.46

4.74

4.00

4.01

3.17

12.68 ± 1.39 / 12.32 ± 1.19

3.61 ± 2.69 / 19.01 ± 3.95

1.79 ± 0.97 / 36.23 ± 3.19

28.12 ± 3.14 / 32.48 ± 3.57

26.60 ± 1.99 / 23.60 ± 2.05

23.70 ± 1.58 / 23.04 ± 2.17

6.21 ± 2.55 / 23.74 ± 3.28

-0.39 ± 0.76 / 33.40 ± 0.31

0.21 ± 0.41 / 35.33 ± 3.02

4.65 ± 1.00 / 10.23 ± 1.68

18.22 ± 1.75 / 17.97 ± 2.10

11.52 ± 7.20 / 29.30 ± 5.30

1.72 ± 1.21 / 34.96 ± 1.12

27.27 ± 3.03 / 31.25 ± 3.24

13.43 ± 1.36 / 13.81 ± 1.45

1.77 ± 3.85 / 25.49 ± 2.99

1.14 ± 1.52 / 36.93 ± 3.69

3.71 ± 1.14 / 16.21 ± 2.86

28.14 ± 2.42 / 28.12 ± 2.55

3.06 ± 3.94 / 28.82 ± 2.17

-0.06 ± 0.67 / 33.85 ± 0.68

2.43 ± 0.73 / 6.05 ± 0.59

19.94 ± 0.96 / 18.01 ± 0.59

19.64 ± 5.59 / 36.97 ± 5.41

0.00 ± 0.00 / 33.32 ± 0.30

8.78 ± 1.33 / 20.50 ± 1.50

20.95 ± 2.02 / 25.63 ± 1.96

6.84 ± 1.76 / 27.74 ± 5.49

-1.50 ± 1.30 / 34.07 ± 0.45

22.67 ± 1.77 / 30.14 ± 1.68

31.14 ± 1.79 / 28.54 ± 0.86

43.97 ± 5.28 / 55.08 ± 4.26

3.49 ± 2.49 / 46.52 ± 4.13

47.91 ± 4.97 / 60.41 ± 3.91

13.1.0

13.3.0

13.1.0

13.3.0

13.1.0

HuggingFaceTB/SmolLM2-360M-Instruct (few-shot)

362

49

8192

True

21,777 ± 6,115 / 3,617 ± 1,211

4.12

4.19

4.32

4.01

4.48

4.76

4.08

4.10

3.02

8.97 ± 3.18 / 8.62 ± 2.72

2.66 ± 2.70 / 16.29 ± 2.34

1.65 ± 1.38 / 44.50 ± 3.21

24.92 ± 1.68 / 28.73 ± 1.90

20.37 ± 5.55 / 21.57 ± 3.57

21.27 ± 5.10 / 22.34 ± 4.41

7.60 ± 2.24 / 26.47 ± 2.89

1.31 ± 1.92 / 45.75 ± 3.36

0.51 ± 1.81 / 38.71 ± 2.95

4.80 ± 1.18 / 10.53 ± 2.12

13.64 ± 5.84 / 16.38 ± 4.06

9.34 ± 6.26 / 26.00 ± 3.56

2.20 ± 1.59 / 41.62 ± 3.37

26.06 ± 2.35 / 30.05 ± 2.29

13.60 ± 1.50 / 13.99 ± 1.39

3.12 ± 4.92 / 27.55 ± 4.21

0.28 ± 1.41 / 37.58 ± 4.34

4.09 ± 1.03 / 16.34 ± 2.86

26.85 ± 3.99 / 27.35 ± 3.60

3.07 ± 2.88 / 28.68 ± 2.63

-0.12 ± 1.62 / 45.84 ± 3.59

1.39 ± 0.54 / 4.02 ± 0.64

18.77 ± 3.96 / 18.65 ± 3.26

12.59 ± 3.85 / 22.64 ± 2.25

1.64 ± 1.30 / 34.84 ± 2.12

9.27 ± 1.07 / 21.58 ± 1.37

15.68 ± 5.54 / 22.21 ± 5.42

6.73 ± 2.20 / 27.67 ± 4.00

0.63 ± 1.05 / 43.48 ± 2.98

19.73 ± 1.42 / 27.47 ± 1.35

30.73 ± 4.30 / 29.47 ± 4.10

59.51 ± 3.73 / 54.82 ± 2.43

1.55 ± 1.90 / 43.18 ± 5.08

49.03 ± 1.47 / 60.00 ± 1.53

13.1.0

13.3.0

13.1.0

13.3.0

13.1.0

fresh-xlm-roberta-base

278

250

512

True

2,214 ± 94 / 1,494 ± 229

4.23

4.20

4.23

3.96

4.19

4.39

4.21

4.44

4.20

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

25.25 ± 3.12 / 44.40 ± 4.52

-0.06 ± 0.99 / 36.73 ± 3.00

1.02 ± 0.30 / 21.61 ± 1.10

48.70 ± 1.57 / 48.51 ± 1.57

1.07 ± 2.10 / 17.71 ± 4.10

2.37 ± 2.06 / 37.68 ± 3.25

0.00 ± 0.00 / 0.00 ± 0.00

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

13.3.0

0.0.0

13.3.0

0.0.0

13.0.0

12.6.1

0.0.0

12.6.1

HuggingFaceTB/SmolLM2-135M (few-shot)

135

49

8192

True

26,346 ± 7,812 / 4,082 ± 1,372

4.34

4.30

4.24

4.36

4.50

4.85

4.49

4.38

3.63

13.72 ± 1.83 / 13.41 ± 1.52

3.79 ± 3.11 / 21.06 ± 4.74

-0.45 ± 0.70 / 39.69 ± 4.95

14.69 ± 2.86 / 17.28 ± 3.01

24.37 ± 2.17 / 26.91 ± 2.28

24.69 ± 1.85 / 27.60 ± 2.48

8.84 ± 4.19 / 29.74 ± 3.45

-1.20 ± 1.10 / 36.09 ± 3.06

-0.50 ± 1.21 / 36.68 ± 3.16

0.16 ± 0.13 / 2.31 ± 0.44

19.15 ± 1.75 / 20.52 ± 1.77

-3.03 ± 7.40 / 24.39 ± 3.87

0.06 ± 1.12 / 36.05 ± 2.59

14.18 ± 3.82 / 16.55 ± 4.25

14.74 ± 2.42 / 16.01 ± 2.04

2.10 ± 3.52 / 23.56 ± 3.05

-0.25 ± 0.60 / 34.69 ± 3.02

1.35 ± 0.73 / 10.92 ± 2.52

25.51 ± 2.40 / 26.43 ± 1.77

-0.56 ± 3.05 / 25.36 ± 4.29

0.46 ± 1.43 / 36.19 ± 3.30

0.15 ± 0.20 / 3.01 ± 0.44

16.89 ± 1.62 / 16.63 ± 1.80

2.74 ± 3.46 / 23.30 ± 3.11

-0.34 ± 1.06 / 39.21 ± 4.13

0.28 ± 0.27 / 2.91 ± 0.92

17.49 ± 2.94 / 18.59 ± 2.66

2.01 ± 1.88 / 15.88 ± 1.32

-0.02 ± 0.15 / 34.86 ± 2.12

0.53 ± 0.36 / 3.23 ± 0.51

31.26 ± 3.84 / 30.44 ± 3.28

26.69 ± 10.82 / 34.46 ± 8.00

1.78 ± 1.67 / 43.50 ± 3.99

13.88 ± 1.36 / 22.49 ± 2.14

13.1.0

13.3.0

13.1.0

13.3.0

13.1.0

HuggingFaceTB/SmolLM2-135M-Instruct (few-shot)

135

49

8192

True

25,602 ± 7,583 / 3,953 ± 1,325

4.40

4.34

4.46

4.25

4.59

4.83

4.46

4.60

3.70

12.11 ± 1.07 / 11.48 ± 1.07

2.61 ± 3.22 / 18.95 ± 3.93

0.25 ± 1.87 / 39.65 ± 4.00

14.02 ± 2.56 / 16.74 ± 2.74

20.89 ± 2.55 / 22.28 ± 2.32

19.62 ± 1.91 / 21.82 ± 2.35

2.78 ± 4.25 / 26.17 ± 3.37

-0.98 ± 1.80 / 40.63 ± 4.03

0.93 ± 2.26 / 40.91 ± 4.95

0.15 ± 0.13 / 2.19 ± 0.57

17.09 ± 2.33 / 18.78 ± 2.11

7.41 ± 9.32 / 28.42 ± 3.18

0.47 ± 1.48 / 38.19 ± 3.61

11.73 ± 3.22 / 13.94 ± 3.48

13.70 ± 2.05 / 15.01 ± 2.07

3.01 ± 2.55 / 22.58 ± 2.22

-0.83 ± 0.71 / 32.99 ± 0.27

0.94 ± 0.54 / 10.22 ± 2.52

23.22 ± 3.22 / 24.30 ± 2.81

3.78 ± 2.95 / 27.36 ± 2.62

0.41 ± 2.39 / 39.64 ± 3.47

0.54 ± 0.33 / 3.34 ± 0.61

15.54 ± 1.74 / 15.29 ± 1.88

2.51 ± 1.90 / 21.27 ± 3.22

0.36 ± 1.07 / 39.04 ± 3.21

1.77 ± 0.67 / 5.69 ± 0.96

15.82 ± 3.13 / 16.46 ± 2.61

-0.62 ± 1.55 / 16.18 ± 1.88

1.16 ± 1.38 / 34.30 ± 1.27

3.25 ± 1.17 / 5.89 ± 0.97

29.96 ± 3.19 / 28.98 ± 3.29

18.64 ± 8.52 / 28.83 ± 5.86

1.85 ± 1.20 / 44.03 ± 3.98

26.90 ± 1.56 / 36.91 ± 1.53

13.1.0

13.3.0

13.1.0

13.3.0

13.1.0

ssmits/Falcon2-5.5B-multilingual (few-shot)

5465

65

8192

True

7,692 ± 1,423 / 1,960 ± 644

4.83

4.78

4.74

4.83

4.80

5.21

4.71

4.85

4.71

0.00 ± 0.00 / 0.00 ± 0.00

0.00 ± 0.00 / 18.12 ± 0.19

0.00 ± 0.00 / 33.25 ± 0.23

0.02 ± 0.02 / 0.03 ± 0.03

0.00 ± 0.00 / 0.00 ± 0.00

0.00 ± 0.00 / 9.59 ± 0.29

0.00 ± 0.00 / 33.25 ± 0.30

0.00 ± 0.00 / 32.79 ± 0.34

0.00 ± 0.00 / 0.09 ± 0.03

0.00 ± 0.00 / 0.00 ± 0.00

0.00 ± 0.00 / 19.16 ± 0.14

0.00 ± 0.00 / 33.30 ± 0.27

0.00 ± 0.00 / 0.00 ± 0.00

0.00 ± 0.00 / 18.79 ± 0.22

0.00 ± 0.00 / 33.69 ± 0.28

0.00 ± 0.00 / 0.02 ± 0.01

0.00 ± 0.00 / 0.00 ± 0.00

0.00 ± 0.00 / 13.62 ± 0.62

0.00 ± 0.00 / 33.40 ± 0.34

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 / 0.02 ± 0.01

0.00 ± 0.00 / 0.00 ± 0.00

0.00 ± 0.00 / 8.62 ± 0.30

0.00 ± 0.00 / 33.34 ± 0.31

0.00 ± 0.00 / 0.01 ± 0.00

0.00 ± 0.00 / 0.00 ± 0.00

0.00 ± 0.00 / 19.61 ± 0.22

2.48 ± 1.94 / 34.52 ± 0.85

0.01 ± 0.02 / 0.03 ± 0.02

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0