Germanic NLG 🇪🇺

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

unknown

100

128000

True

576 ± 221 / 81 ± 28

1.16

1.15

1.19

1.04

1.13

1.00

1.25

1.34

1.17

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

66.21 ± 0.44 / 18.02 ± 0.61

95.21 ± 0.55 / 96.41 ± 0.41

97.19 ± 1.15 / 98.12 ± 0.76

78.74 ± 3.12 / 83.91 ± 2.42

77.48 ± 2.32 / 55.87 ± 2.83

78.70 ± 2.78 / 57.58 ± 4.23

62.55 ± 2.82 / 72.41 ± 2.42

63.60 ± 0.15 / 13.15 ± 0.35

74.45 ± 4.27 / 86.22 ± 2.49

56.31 ± 5.81 / 74.04 ± 4.03

44.67 ± 3.23 / 73.39 ± 1.83

70.84 ± 1.92 / 78.12 ± 1.44

86.30 ± 2.04 / 89.53 ± 1.60

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

66.08 ± 0.14 / 17.19 ± 0.38

71.32 ± 1.56 / 78.48 ± 1.15

84.09 ± 2.99 / 88.01 ± 2.26

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

69.61 ± 0.61 / 23.98 ± 1.17

89.09 ± 1.59 / 91.76 ± 1.19

72.03 ± 3.91 / 86.09 ± 1.96

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

63.62 ± 0.65 / 13.08 ± 0.87

73.80 ± 2.03 / 80.31 ± 1.54

83.93 ± 2.38 / 87.85 ± 1.80

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

67.13 ± 0.50 / 17.61 ± 0.76

70.04 ± 1.91 / 77.58 ± 1.42

88.29 ± 2.26 / 91.17 ± 1.70

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

68.80 ± 0.43 / 21.84 ± 0.45

81.71 ± 1.12 / 86.29 ± 0.83

89.91 ± 1.81 / 92.38 ± 1.34

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

12.5.1

13.2.0

12.10.2

12.5.1

12.10.8

12.10.2

12.5.1

13.3.0

12.5.1

13.0.0

12.6.1

12.10.2

12.6.1

12.10.2

12.3.2

12.10.2

12.3.2

12.10.2

12.10.0

12.10.2

12.10.0

12.10.2

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

unknown

200

128000

True

916 ± 329 / 114 ± 38

1.42

1.14

1.19

1.04

1.16

2.75

1.35

1.51

1.26

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

66.03 ± 0.24 / 17.74 ± 0.71

96.41 ± 0.63 / 97.30 ± 0.48

97.68 ± 1.06 / 98.44 ± 0.72

85.96 ± 1.48 / 89.41 ± 1.15

79.07 ± 3.01 / 64.17 ± 3.51

81.56 ± 2.45 / 64.06 ± 4.11

66.66 ± 1.91 / 77.70 ± 1.29

63.25 ± 0.26 / 13.02 ± 0.33

64.53 ± 6.09 / 79.17 ± 4.89

54.70 ± 4.36 / 74.94 ± 3.26

43.51 ± 3.40 / 74.52 ± 1.79

73.81 ± 1.88 / 80.39 ± 1.45

89.91 ± 1.13 / 92.42 ± 0.83

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

66.00 ± 0.29 / 16.97 ± 0.45

70.70 ± 1.32 / 77.97 ± 0.99

86.30 ± 2.23 / 89.65 ± 1.68

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

68.25 ± 0.27 / 19.22 ± 0.51

91.27 ± 1.41 / 93.40 ± 1.09

70.85 ± 5.98 / 85.55 ± 3.05

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

63.80 ± 0.60 / 13.87 ± 1.05

74.13 ± 1.60 / 80.59 ± 1.22

88.18 ± 1.79 / 91.13 ± 1.34

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

66.86 ± 0.46 / 16.93 ± 0.91

73.11 ± 1.87 / 79.69 ± 1.46

92.69 ± 1.46 / 94.53 ± 1.09

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

67.64 ± 0.97 / 20.90 ± 0.92

78.55 ± 1.82 / 83.91 ± 1.34

91.34 ± 1.66 / 93.48 ± 1.27

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

13.2.0

12.10.2

12.10.0

12.10.8

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

12.10.2

12.10.0

12.10.2

12.10.0

12.10.2

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

8020

131

32768

True

5,821 ± 1,090 / 1,561 ± 506

2.22

2.07

2.32

2.00

3.12

2.93

1.68

1.98

1.63

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

66.75 ± 0.97 / 21.86 ± 0.87

59.57 ± 1.49 / 69.19 ± 1.13

65.34 ± 2.38 / 76.95 ± 1.56

53.97 ± 2.40 / 64.76 ± 2.17

69.85 ± 2.00 / 59.43 ± 3.23

68.83 ± 1.07 / 59.51 ± 2.63

54.49 ± 2.44 / 69.23 ± 2.00

64.05 ± 0.67 / 16.34 ± 1.01

28.55 ± 2.65 / 61.53 ± 3.21

17.47 ± 3.61 / 52.60 ± 5.26

43.55 ± 3.42 / 71.05 ± 3.22

34.93 ± 1.01 / 50.67 ± 0.80

49.83 ± 2.75 / 61.44 ± 2.40

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

65.37 ± 0.39 / 19.85 ± 0.39

37.50 ± 0.73 / 52.72 ± 0.63

55.01 ± 2.40 / 65.64 ± 2.12

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

65.90 ± 0.71 / 18.54 ± 0.92

30.58 ± 1.40 / 47.95 ± 1.05

6.77 ± 2.10 / 53.92 ± 1.32

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

69.65 ± 1.12 / 27.94 ± 2.90

43.46 ± 0.81 / 57.37 ± 0.63

68.11 ± 1.40 / 75.60 ± 1.16

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

68.87 ± 0.72 / 21.06 ± 1.13

40.81 ± 1.05 / 55.44 ± 0.80

60.68 ± 1.04 / 70.24 ± 0.85

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

69.38 ± 0.48 / 24.96 ± 0.47

53.42 ± 0.91 / 64.98 ± 0.74

78.36 ± 2.31 / 83.62 ± 1.78

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

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

7242

32

8192

False

5,876 ± 1,021 / 1,677 ± 546

2.25

2.04

2.30

2.08

3.65

2.65

1.86

1.97

1.45

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

67.46 ± 0.76 / 23.35 ± 0.88

59.78 ± 1.61 / 69.68 ± 1.23

58.63 ± 2.54 / 71.72 ± 1.82

50.74 ± 1.16 / 62.79 ± 0.92

66.22 ± 2.15 / 48.98 ± 4.65

64.14 ± 1.26 / 49.59 ± 4.31

55.48 ± 1.77 / 69.68 ± 1.45

65.32 ± 0.41 / 18.53 ± 0.65

26.13 ± 1.28 / 56.08 ± 2.05

17.32 ± 0.77 / 54.57 ± 1.49

49.75 ± 1.22 / 77.08 ± 0.60

29.72 ± 1.33 / 46.95 ± 0.96

46.78 ± 2.83 / 59.65 ± 2.28

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

65.75 ± 0.16 / 20.23 ± 0.23

36.05 ± 1.10 / 51.86 ± 0.87

51.15 ± 1.71 / 63.20 ± 1.32

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

63.74 ± 2.25 / 18.29 ± 1.40

8.45 ± 1.35 / 31.54 ± 1.03

1.14 ± 0.97 / 50.10 ± 0.82

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

66.92 ± 0.41 / 23.23 ± 1.24

37.90 ± 1.03 / 53.36 ± 0.80

60.66 ± 1.28 / 70.32 ± 1.01

64.47 ± 2.31 / 40.89 ± 2.81

13.83 ± 1.91 / 41.53 ± 1.23

45.69 ± 1.76 / 72.13 ± 1.39

58.03 ± 1.37 / 73.17 ± 0.58

69.34 ± 0.77 / 22.22 ± 0.98

37.60 ± 0.83 / 53.13 ± 0.62

54.33 ± 0.84 / 65.41 ± 0.59

71.81 ± 1.02 / 59.93 ± 2.52

69.98 ± 1.00 / 69.79 ± 0.76

45.34 ± 2.51 / 72.10 ± 1.10

72.49 ± 1.57 / 87.51 ± 0.74

70.37 ± 0.32 / 27.70 ± 0.38

50.93 ± 1.34 / 62.98 ± 0.98

83.82 ± 0.80 / 87.83 ± 0.60

12.5.2

13.3.0

12.5.2

12.10.8

12.5.2

13.3.0

12.5.2

13.0.0

12.5.2

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

8030

128

131073

True

2,411 ± 465 / 686 ± 215

2.33

2.32

2.39

2.19

3.02

2.77

1.98

2.19

1.80

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

67.38 ± 1.09 / 23.21 ± 0.94

61.78 ± 1.70 / 71.28 ± 1.27

66.61 ± 1.90 / 77.73 ± 1.31

39.62 ± 2.26 / 53.92 ± 1.96

74.77 ± 0.84 / 71.87 ± 0.97

72.80 ± 1.57 / 69.98 ± 1.84

57.30 ± 0.98 / 71.58 ± 0.90

66.08 ± 0.56 / 19.80 ± 0.86

5.23 ± 1.83 / 34.90 ± 0.81

11.51 ± 3.24 / 45.73 ± 5.97

43.93 ± 3.73 / 70.96 ± 3.00

38.10 ± 0.57 / 52.64 ± 0.47

39.30 ± 1.01 / 54.03 ± 0.82

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

66.27 ± 0.15 / 19.05 ± 0.30

39.40 ± 1.44 / 53.87 ± 1.19

38.88 ± 1.25 / 53.72 ± 0.91

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

68.27 ± 0.25 / 22.14 ± 0.62

30.33 ± 1.72 / 47.81 ± 1.31

10.48 ± 2.28 / 54.89 ± 1.49

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

66.87 ± 0.54 / 21.31 ± 1.47

40.00 ± 0.97 / 54.88 ± 0.70

45.93 ± 1.38 / 58.95 ± 1.06

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

68.84 ± 0.62 / 21.41 ± 1.20

40.98 ± 0.71 / 55.51 ± 0.59

39.98 ± 1.59 / 54.32 ± 1.27

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

69.57 ± 0.25 / 26.30 ± 0.35

56.62 ± 0.49 / 67.29 ± 0.39

69.03 ± 1.19 / 76.69 ± 0.89

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

2.39

2.32

2.38

2.10

3.10

3.01

2.00

2.26

1.92

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

64.74 ± 0.50 / 17.82 ± 0.98

57.60 ± 1.58 / 67.81 ± 1.23

65.98 ± 1.72 / 77.34 ± 1.16

28.65 ± 2.52 / 45.11 ± 2.33

64.62 ± 1.26 / 53.50 ± 3.27

65.10 ± 1.86 / 56.43 ± 2.58

52.87 ± 1.18 / 68.71 ± 1.01

63.88 ± 1.12 / 16.54 ± 1.58

28.34 ± 3.26 / 58.57 ± 4.45

22.40 ± 3.12 / 53.51 ± 5.42

53.20 ± 3.15 / 75.98 ± 2.62

35.80 ± 0.97 / 51.22 ± 0.67

30.31 ± 1.70 / 46.84 ± 1.59

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

65.07 ± 0.28 / 18.94 ± 0.35

37.48 ± 0.64 / 52.46 ± 0.52

31.27 ± 1.39 / 47.97 ± 1.30

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

66.17 ± 0.86 / 18.71 ± 0.89

25.93 ± 1.51 / 44.54 ± 1.14

8.48 ± 2.66 / 53.76 ± 1.54

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

69.58 ± 1.37 / 28.95 ± 2.96

38.77 ± 0.95 / 53.99 ± 0.67

34.29 ± 1.05 / 49.79 ± 0.88

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

66.29 ± 1.29 / 20.14 ± 1.64

38.44 ± 1.33 / 53.68 ± 1.01

30.88 ± 2.27 / 47.18 ± 1.81

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

67.93 ± 0.44 / 22.00 ± 0.51

52.47 ± 0.85 / 64.25 ± 0.66

43.95 ± 3.26 / 57.04 ± 2.74

12.11.0

13.0.0

12.11.0

13.0.0

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

2.40

2.38

2.42

2.28

3.19

2.68

2.09

2.31

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

66.36 ± 0.47 / 19.75 ± 0.84

57.87 ± 1.67 / 67.43 ± 1.34

50.42 ± 3.32 / 65.43 ± 2.41

29.17 ± 2.24 / 44.59 ± 2.00

74.47 ± 1.47 / 65.57 ± 2.39

72.93 ± 1.00 / 65.44 ± 2.55

50.62 ± 3.52 / 65.69 ± 3.50

63.98 ± 0.50 / 14.75 ± 0.79

27.77 ± 1.63 / 61.75 ± 1.77

20.35 ± 1.92 / 57.74 ± 2.28

42.90 ± 3.57 / 69.90 ± 3.17

33.44 ± 0.67 / 48.76 ± 0.58

30.91 ± 1.88 / 45.85 ± 1.93

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

66.60 ± 0.07 / 19.13 ± 0.31

33.54 ± 1.40 / 49.20 ± 1.13

30.32 ± 2.27 / 45.96 ± 1.87

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

66.98 ± 1.04 / 19.84 ± 1.97

25.16 ± 1.55 / 43.57 ± 1.26

1.50 ± 1.22 / 48.33 ± 1.21

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

65.23 ± 0.49 / 16.56 ± 0.94

38.44 ± 0.81 / 53.38 ± 0.60

37.69 ± 1.00 / 51.24 ± 0.73

68.72 ± 1.81 / 54.89 ± 2.10

14.67 ± 2.51 / 41.36 ± 2.04

32.91 ± 2.56 / 64.93 ± 1.97

45.36 ± 1.31 / 67.50 ± 0.69

67.62 ± 0.82 / 18.19 ± 1.14

36.18 ± 1.31 / 51.68 ± 1.05

33.91 ± 1.71 / 48.01 ± 1.47

75.02 ± 1.31 / 69.47 ± 1.18

67.64 ± 1.12 / 71.04 ± 1.17

32.29 ± 3.05 / 64.85 ± 2.07

54.84 ± 2.22 / 79.10 ± 1.10

69.28 ± 0.17 / 25.48 ± 0.61

53.77 ± 1.03 / 64.91 ± 0.80

57.64 ± 1.55 / 67.29 ± 1.30

12.6.1

13.3.0

12.6.1

12.10.8

12.6.1

13.3.0

12.6.1

13.0.0

12.6.1

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

8028

256

8192

False

5,581 ± 1,066 / 1,471 ± 483

2.48

2.40

2.61

2.31

3.81

2.98

1.89

2.10

1.74

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

66.18 ± 0.84 / 21.10 ± 0.69

41.32 ± 1.11 / 55.43 ± 0.86

52.24 ± 1.55 / 68.01 ± 1.05

37.67 ± 0.80 / 53.26 ± 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

64.48 ± 0.61 / 17.46 ± 0.76

15.80 ± 2.22 / 51.42 ± 3.79

12.30 ± 2.38 / 51.96 ± 3.31

43.26 ± 2.53 / 71.49 ± 2.01

36.48 ± 0.85 / 52.32 ± 0.62

35.85 ± 1.48 / 51.83 ± 1.11

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

65.69 ± 0.22 / 19.95 ± 0.16

37.32 ± 0.70 / 52.95 ± 0.50

38.28 ± 1.31 / 53.70 ± 0.97

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

63.45 ± 1.92 / 16.81 ± 2.23

10.97 ± 1.13 / 33.51 ± 0.81

4.23 ± 1.80 / 49.31 ± 0.84

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

69.05 ± 1.11 / 26.68 ± 3.04

44.87 ± 0.70 / 58.71 ± 0.53

63.66 ± 0.91 / 72.68 ± 0.68

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

74.40 ± 0.20 / 31.66 ± 0.46

46.76 ± 0.71 / 60.01 ± 0.54

60.36 ± 0.88 / 70.23 ± 0.64

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

71.92 ± 0.17 / 29.79 ± 0.15

56.93 ± 0.67 / 67.67 ± 0.51

74.42 ± 0.88 / 80.74 ± 0.65

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

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

8030

128

8192

True

4,687 ± 1,121 / 967 ± 313

2.51

2.35

2.54

2.20

3.13

3.23

2.14

2.49

1.99

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

65.16 ± 0.48 / 18.74 ± 0.83

56.20 ± 2.22 / 66.91 ± 1.68

61.16 ± 2.54 / 73.63 ± 1.85

24.99 ± 2.12 / 42.57 ± 1.91

61.48 ± 1.83 / 47.65 ± 2.94

61.58 ± 2.21 / 50.10 ± 2.68

49.87 ± 1.88 / 66.15 ± 1.44

63.38 ± 1.15 / 15.74 ± 1.68

21.20 ± 6.57 / 52.29 ± 7.43

19.65 ± 4.32 / 56.66 ± 4.40

53.35 ± 4.33 / 74.98 ± 3.70

33.02 ± 1.35 / 49.25 ± 1.04

24.93 ± 3.13 / 42.47 ± 2.74

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

64.81 ± 0.24 / 18.56 ± 0.35

35.86 ± 0.90 / 51.39 ± 0.69

26.49 ± 1.89 / 44.41 ± 1.56

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

66.34 ± 1.09 / 19.13 ± 0.96

26.78 ± 1.59 / 45.17 ± 1.12

7.41 ± 3.26 / 52.13 ± 1.97

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

68.92 ± 0.99 / 26.93 ± 2.01

38.12 ± 0.75 / 53.52 ± 0.56

31.37 ± 1.37 / 47.65 ± 1.09

62.26 ± 2.20 / 42.41 ± 2.02

10.45 ± 2.69 / 33.45 ± 1.99

30.30 ± 3.94 / 62.28 ± 2.89

62.99 ± 1.00 / 73.73 ± 0.98

65.17 ± 1.24 / 18.63 ± 1.85

36.38 ± 0.86 / 52.08 ± 0.66

28.33 ± 2.31 / 45.29 ± 1.78

66.31 ± 2.09 / 58.68 ± 1.95

64.30 ± 0.65 / 69.26 ± 0.50

28.18 ± 3.96 / 58.97 ± 4.03

70.38 ± 3.51 / 82.95 ± 2.38

67.90 ± 0.49 / 21.54 ± 0.57

52.54 ± 0.88 / 64.26 ± 0.66

41.19 ± 4.40 / 54.78 ± 3.62

12.6.1

13.3.0

12.6.1

12.10.8

12.6.1

13.3.0

12.6.1

13.0.0

12.6.1

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

8171

49

4097

True

5,116 ± 943 / 1,436 ± 472

2.60

2.54

2.75

2.49

4.05

3.13

1.99

2.12

1.73

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

65.64 ± 0.99 / 21.12 ± 0.86

32.05 ± 2.18 / 47.54 ± 1.78

47.42 ± 1.74 / 65.02 ± 1.13

28.73 ± 1.32 / 46.04 ± 1.04

49.94 ± 2.13 / 46.49 ± 2.00

52.17 ± 1.02 / 46.44 ± 2.72

53.27 ± 1.54 / 66.73 ± 1.31

63.01 ± 1.50 / 15.82 ± 1.50

17.22 ± 3.50 / 50.42 ± 5.01

12.01 ± 2.47 / 47.98 ± 4.37

45.04 ± 3.42 / 69.52 ± 2.79

24.31 ± 1.12 / 42.68 ± 0.87

30.34 ± 1.41 / 47.38 ± 1.10

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

63.65 ± 0.52 / 18.25 ± 0.41

26.71 ± 1.53 / 44.61 ± 1.21

30.43 ± 0.92 / 47.06 ± 0.83

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

62.35 ± 3.34 / 16.15 ± 1.66

6.54 ± 1.30 / 28.63 ± 1.24

1.83 ± 3.53 / 49.23 ± 2.07

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

70.32 ± 0.87 / 31.24 ± 2.42

39.82 ± 0.77 / 54.72 ± 0.59

53.82 ± 1.15 / 64.95 ± 0.94

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

66.70 ± 0.37 / 19.34 ± 0.85

39.74 ± 0.95 / 54.61 ± 0.75

54.37 ± 0.74 / 65.48 ± 0.65

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

68.38 ± 0.45 / 24.50 ± 0.64

51.00 ± 1.07 / 62.95 ± 0.81

78.18 ± 1.10 / 83.30 ± 0.85

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

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

9152

128

4096

False

5,763 ± 1,178 / 1,390 ± 446

2.61

2.20

2.65

2.25

3.95

3.20

2.14

2.30

2.16

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

67.55 ± 1.08 / 23.77 ± 0.94

80.75 ± 1.25 / 85.31 ± 0.98

74.77 ± 1.93 / 83.14 ± 1.29

36.86 ± 1.37 / 51.61 ± 1.09

40.91 ± 2.56 / 33.22 ± 1.88

42.91 ± 2.34 / 35.61 ± 2.22

52.62 ± 2.01 / 68.10 ± 2.25

65.77 ± 0.38 / 19.35 ± 0.75

9.70 ± 4.22 / 36.58 ± 1.69

11.98 ± 2.76 / 39.37 ± 2.76

47.36 ± 4.28 / 72.71 ± 4.10

36.97 ± 1.21 / 52.08 ± 0.96

37.64 ± 1.86 / 51.95 ± 1.52

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

66.33 ± 0.19 / 20.77 ± 0.27

40.09 ± 0.90 / 54.78 ± 0.70

36.27 ± 1.57 / 50.67 ± 1.45

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

64.67 ± 1.48 / 18.74 ± 1.31

11.10 ± 0.78 / 33.53 ± 0.69

0.89 ± 1.86 / 51.27 ± 1.18

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

69.44 ± 1.03 / 28.76 ± 2.71

39.43 ± 1.06 / 54.28 ± 0.77

37.67 ± 1.13 / 51.67 ± 1.11

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

69.33 ± 0.60 / 23.01 ± 1.18

41.90 ± 1.02 / 56.09 ± 0.76

36.69 ± 1.64 / 50.85 ± 1.65

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

69.27 ± 0.77 / 25.38 ± 1.10

45.95 ± 0.80 / 59.04 ± 0.60

43.97 ± 1.97 / 56.43 ± 1.61

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

2.64

2.34

2.60

2.39

3.79

3.71

2.11

2.24

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

66.67 ± 0.87 / 21.08 ± 0.83

57.65 ± 1.99 / 68.08 ± 1.51

51.99 ± 3.67 / 66.43 ± 2.85

44.44 ± 1.52 / 58.16 ± 1.21

64.37 ± 2.17 / 52.81 ± 2.48

62.77 ± 0.83 / 51.80 ± 2.77

50.60 ± 4.90 / 66.76 ± 3.04

65.09 ± 0.31 / 17.27 ± 0.66

18.09 ± 2.04 / 52.56 ± 2.60

12.25 ± 2.18 / 50.79 ± 2.42

38.34 ± 2.39 / 69.54 ± 1.96

27.33 ± 0.72 / 45.16 ± 0.55

41.59 ± 2.61 / 56.02 ± 2.08

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

66.09 ± 0.17 / 19.64 ± 0.27

31.76 ± 0.89 / 48.64 ± 0.69

45.84 ± 1.47 / 59.27 ± 1.16

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

65.39 ± 0.80 / 18.24 ± 1.00

9.11 ± 0.92 / 32.06 ± 0.70

3.30 ± 2.81 / 44.40 ± 1.61

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

68.16 ± 0.95 / 24.52 ± 2.45

33.84 ± 1.54 / 50.24 ± 1.19

50.99 ± 0.99 / 63.11 ± 0.75

64.25 ± 2.23 / 46.52 ± 1.72

13.66 ± 1.99 / 39.45 ± 1.52

28.59 ± 1.48 / 61.24 ± 1.46

49.64 ± 0.86 / 68.04 ± 0.55

68.66 ± 0.57 / 19.51 ± 0.67

35.37 ± 1.30 / 51.43 ± 0.96

47.50 ± 1.75 / 60.41 ± 1.32

70.62 ± 0.90 / 58.92 ± 2.15

67.78 ± 1.03 / 72.29 ± 0.47

30.99 ± 2.94 / 62.20 ± 2.56

49.56 ± 2.85 / 76.72 ± 1.15

70.76 ± 0.56 / 24.95 ± 1.03

44.11 ± 4.39 / 57.76 ± 3.36

69.20 ± 2.71 / 76.75 ± 2.06

12.6.1

13.3.0

12.6.1

12.10.8

12.6.1

13.3.0

12.6.1

13.0.0

12.6.1

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

8028

256

8192

False

5,608 ± 1,062 / 1,472 ± 479

2.69

2.67

2.99

2.55

3.93

3.40

1.95

2.28

1.76

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

65.03 ± 0.98 / 20.21 ± 0.77

36.64 ± 1.30 / 49.92 ± 1.19

39.24 ± 1.63 / 59.45 ± 1.09

27.29 ± 1.22 / 45.01 ± 0.99

60.94 ± 2.30 / 53.33 ± 3.53

59.61 ± 1.37 / 50.84 ± 3.99

35.73 ± 1.26 / 50.42 ± 1.67

62.45 ± 1.72 / 15.67 ± 1.26

6.18 ± 1.69 / 35.40 ± 1.06

4.00 ± 1.01 / 36.17 ± 0.94

46.52 ± 2.15 / 71.95 ± 1.63

20.14 ± 1.32 / 38.69 ± 0.99

27.50 ± 1.61 / 44.60 ± 1.39

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

63.00 ± 0.55 / 18.11 ± 0.35

20.97 ± 0.82 / 39.72 ± 0.64

28.96 ± 2.18 / 46.32 ± 1.64

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

59.16 ± 2.91 / 14.91 ± 1.85

3.70 ± 1.01 / 27.71 ± 0.66

-3.24 ± 3.16 / 49.96 ± 2.38

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

69.07 ± 1.43 / 28.50 ± 3.72

32.49 ± 1.21 / 48.62 ± 0.79

55.40 ± 1.43 / 65.83 ± 1.23

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

72.90 ± 0.24 / 30.63 ± 0.42

32.37 ± 1.09 / 48.63 ± 0.82

53.32 ± 1.89 / 64.30 ± 1.72

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

68.14 ± 1.53 / 25.56 ± 0.98

40.73 ± 0.87 / 54.65 ± 0.63

79.38 ± 0.82 / 84.41 ± 0.65

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

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

8171

49

4096

True

5,090 ± 937 / 1,423 ± 466

2.71

2.68

2.82

2.54

3.95

3.13

2.24

2.59

1.72

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

66.02 ± 0.75 / 20.91 ± 0.70

33.71 ± 1.69 / 49.70 ± 1.24

43.55 ± 3.67 / 62.50 ± 2.36

21.34 ± 1.27 / 39.77 ± 1.09

53.79 ± 1.52 / 46.58 ± 1.73

56.13 ± 0.91 / 47.13 ± 2.04

51.36 ± 2.53 / 66.19 ± 2.08

62.40 ± 1.11 / 13.68 ± 1.61

6.83 ± 2.54 / 38.36 ± 3.81

8.09 ± 2.03 / 41.05 ± 4.14

48.01 ± 2.52 / 73.03 ± 1.99

24.55 ± 0.94 / 42.12 ± 0.85

26.71 ± 1.68 / 44.15 ± 1.46

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

65.09 ± 0.37 / 19.37 ± 0.37

26.57 ± 1.18 / 44.19 ± 0.95

24.62 ± 2.11 / 42.11 ± 1.50

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

63.81 ± 1.05 / 16.07 ± 1.19

5.12 ± 1.20 / 27.91 ± 0.90

0.89 ± 2.37 / 53.27 ± 1.64

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

66.33 ± 0.75 / 20.58 ± 1.77

33.98 ± 0.82 / 50.12 ± 0.65

34.59 ± 1.42 / 49.13 ± 1.25

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

62.34 ± 3.24 / 18.49 ± 1.19

34.69 ± 0.59 / 50.59 ± 0.56

31.36 ± 1.90 / 46.78 ± 1.51

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

69.36 ± 0.50 / 25.91 ± 0.54

53.62 ± 0.83 / 65.00 ± 0.65

71.00 ± 2.12 / 77.45 ± 1.78

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

2.71

2.52

2.91

2.50

3.59

3.17

2.25

2.74

2.01

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

66.33 ± 0.98 / 22.03 ± 0.96

53.81 ± 1.88 / 64.81 ± 1.53

61.06 ± 2.83 / 73.89 ± 2.00

20.64 ± 1.95 / 39.21 ± 1.79

50.56 ± 2.04 / 44.38 ± 1.85

52.65 ± 2.27 / 46.48 ± 3.65

44.61 ± 2.28 / 62.22 ± 2.10

63.13 ± 1.63 / 16.19 ± 1.73

12.10 ± 4.22 / 43.27 ± 5.24

9.30 ± 0.99 / 46.11 ± 3.47

45.15 ± 3.72 / 68.61 ± 3.30

28.31 ± 1.01 / 45.93 ± 0.80

13.59 ± 2.44 / 33.95 ± 1.83

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

64.79 ± 0.32 / 19.30 ± 0.42

34.51 ± 1.13 / 50.46 ± 0.88

20.84 ± 2.19 / 39.88 ± 1.85

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

61.40 ± 2.38 / 14.90 ± 1.60

10.25 ± 1.54 / 32.81 ± 1.22

5.24 ± 1.65 / 52.80 ± 2.41

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

68.96 ± 1.13 / 28.26 ± 2.32

35.06 ± 0.54 / 51.20 ± 0.43

28.85 ± 1.70 / 45.83 ± 1.39

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

64.37 ± 0.74 / 17.69 ± 0.90

34.93 ± 1.11 / 51.02 ± 0.87

23.73 ± 1.97 / 41.93 ± 1.68

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

69.04 ± 0.56 / 23.86 ± 0.77

47.63 ± 1.17 / 60.45 ± 0.88

35.63 ± 4.21 / 49.72 ± 3.73

12.10.4

12.10.5

12.10.4

12.10.5

12.10.4

12.10.5

12.10.4

13.3.0

12.10.4

12.10.5

12.10.8

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

12.10.4

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

7242

32

32768

True

2,657 ± 524 / 880 ± 278

2.72

2.59

2.93

2.50

3.64

3.21

2.25

2.68

1.99

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

66.47 ± 1.00 / 22.11 ± 1.08

53.26 ± 1.94 / 64.50 ± 1.68

58.26 ± 2.62 / 71.56 ± 1.79

18.53 ± 2.03 / 37.79 ± 1.68

52.00 ± 1.91 / 43.55 ± 2.21

55.12 ± 3.14 / 45.34 ± 4.15

47.25 ± 4.11 / 64.53 ± 3.71

63.49 ± 1.49 / 16.48 ± 1.62

8.66 ± 4.12 / 38.87 ± 3.40

6.80 ± 1.59 / 39.72 ± 2.50

46.86 ± 3.27 / 70.86 ± 2.79

27.78 ± 1.08 / 45.76 ± 0.79

10.88 ± 3.63 / 32.43 ± 2.67

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

64.87 ± 0.31 / 19.30 ± 0.43

35.52 ± 1.01 / 51.52 ± 0.73

19.67 ± 2.31 / 38.98 ± 1.98

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

61.96 ± 3.10 / 16.11 ± 1.80

10.25 ± 0.96 / 32.89 ± 0.83

1.99 ± 2.95 / 54.48 ± 1.27

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

68.24 ± 0.70 / 25.71 ± 1.33

35.63 ± 1.12 / 51.69 ± 0.85

26.40 ± 1.86 / 43.98 ± 1.58

58.15 ± 1.14 / 40.78 ± 1.91

7.94 ± 1.25 / 31.02 ± 3.45

25.41 ± 3.46 / 61.11 ± 2.36

62.56 ± 1.10 / 73.16 ± 0.93

64.24 ± 0.91 / 17.54 ± 1.10

35.49 ± 0.57 / 51.51 ± 0.42

19.88 ± 1.80 / 39.13 ± 1.56

63.40 ± 2.72 / 56.92 ± 2.17

68.17 ± 1.33 / 70.74 ± 0.93

30.92 ± 4.81 / 63.79 ± 4.42

73.45 ± 1.83 / 84.54 ± 1.42

69.11 ± 0.31 / 23.70 ± 0.53

47.74 ± 1.26 / 60.63 ± 0.97

34.96 ± 4.19 / 49.62 ± 3.28

0.0.0

12.5.1

12.6.1

10.0.1

9.1.2

0.0.0

11.0.0

0.0.0

12.5.1

9.1.2

0.0.0

12.5.1

11.0.0

9.1.2

13.3.0

9.1.2

12.5.1

11.0.0

12.10.8

12.1.0

9.1.2

13.3.0

9.1.2

13.0.0

9.1.2

12.5.1

11.0.0

9.1.2

9.2.0

9.1.2

12.5.1

11.0.0

9.2.0

9.1.2

12.5.1

11.0.0

9.2.0

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

7242

32

32768

False

634 ± 179 / 110 ± 35

2.83

2.61

2.99

2.64

3.81

3.16

2.47

2.70

2.23

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

66.84 ± 0.77 / 21.21 ± 1.08

51.60 ± 1.33 / 63.50 ± 1.03

35.85 ± 2.68 / 52.62 ± 2.08

22.21 ± 1.60 / 40.78 ± 1.32

53.42 ± 2.48 / 42.63 ± 1.66

54.34 ± 1.93 / 41.06 ± 2.40

38.79 ± 2.56 / 53.72 ± 3.01

64.43 ± 0.45 / 16.11 ± 0.97

17.06 ± 1.53 / 56.51 ± 2.06

11.00 ± 1.00 / 53.26 ± 2.32

35.74 ± 2.44 / 64.27 ± 2.42

20.37 ± 1.34 / 39.32 ± 1.03

21.16 ± 2.07 / 39.85 ± 1.73

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

66.11 ± 0.18 / 19.64 ± 0.28

25.60 ± 1.10 / 43.53 ± 0.90

21.75 ± 1.61 / 40.57 ± 1.45

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

65.01 ± 1.51 / 18.34 ± 1.35

5.49 ± 1.98 / 28.73 ± 1.39

0.24 ± 0.71 / 38.95 ± 0.84

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

67.51 ± 0.71 / 22.63 ± 1.73

26.06 ± 1.65 / 44.13 ± 1.29

31.09 ± 1.35 / 47.48 ± 0.98

55.56 ± 2.66 / 39.56 ± 2.13

12.37 ± 1.64 / 37.37 ± 1.35

21.50 ± 1.70 / 59.10 ± 1.32

50.77 ± 0.95 / 66.54 ± 0.79

67.99 ± 0.49 / 19.54 ± 0.55

22.86 ± 1.89 / 41.71 ± 1.45

24.80 ± 1.77 / 42.93 ± 1.38

62.11 ± 1.61 / 52.36 ± 2.00

59.91 ± 2.10 / 68.92 ± 1.21

30.66 ± 3.60 / 64.32 ± 2.03

58.27 ± 2.09 / 77.85 ± 0.70

69.75 ± 0.63 / 24.71 ± 0.72

34.93 ± 1.35 / 50.71 ± 1.00

44.91 ± 2.44 / 58.07 ± 1.93

9.2.0

9.3.1

12.4.0

12.6.1

10.0.1

9.3.2

9.2.0

12.4.0

9.3.1

12.4.0

9.3.2

9.2.0

9.3.1

12.4.0

9.3.2

9.2.0

13.3.0

9.3.1

12.4.0

12.10.8

12.1.0

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

9.3.2

9.3.1

9.2.0

9.3.1

12.4.0

9.3.2

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

7242

32

32768

True

5,054 ± 1,200 / 1,056 ± 339

2.90

2.62

2.93

2.35

3.86

3.59

2.55

3.19

2.14

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

65.43 ± 1.12 / 20.36 ± 0.95

50.76 ± 1.75 / 62.66 ± 1.43

50.82 ± 1.17 / 66.66 ± 0.76

14.47 ± 2.35 / 34.86 ± 1.97

48.97 ± 2.42 / 39.15 ± 2.78

51.52 ± 2.96 / 40.17 ± 3.62

49.05 ± 2.73 / 63.94 ± 2.42

63.32 ± 1.58 / 16.33 ± 1.63

14.37 ± 2.18 / 47.80 ± 4.36

9.96 ± 1.34 / 48.97 ± 3.77

44.07 ± 3.40 / 68.49 ± 2.97

25.07 ± 1.48 / 43.13 ± 1.15

15.56 ± 3.55 / 35.85 ± 2.56

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

65.15 ± 0.31 / 18.72 ± 0.57

33.24 ± 0.85 / 49.69 ± 0.67

25.50 ± 2.25 / 43.44 ± 2.03

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

63.68 ± 1.75 / 16.38 ± 1.24

5.12 ± 1.30 / 28.85 ± 0.99

8.30 ± 1.28 / 57.35 ± 0.75

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

65.53 ± 1.07 / 19.46 ± 1.48

27.04 ± 1.04 / 44.99 ± 0.77

17.47 ± 3.26 / 36.70 ± 2.93

54.56 ± 2.96 / 37.86 ± 2.49

8.43 ± 1.27 / 24.23 ± 0.94

10.99 ± 2.55 / 50.46 ± 4.17

55.91 ± 1.08 / 66.78 ± 1.13

57.88 ± 1.41 / 12.36 ± 1.30

25.12 ± 1.17 / 43.50 ± 0.92

10.65 ± 1.55 / 31.51 ± 1.52

59.10 ± 1.87 / 51.31 ± 1.87

68.41 ± 1.17 / 70.85 ± 0.74

25.43 ± 4.22 / 60.79 ± 3.45

71.89 ± 2.20 / 82.99 ± 1.78

67.99 ± 0.41 / 22.12 ± 0.52

44.09 ± 1.21 / 56.37 ± 0.96

32.29 ± 4.57 / 45.16 ± 4.28

12.5.3

12.6.1

12.5.3

13.3.0

12.5.3

12.10.8

12.5.3

13.3.0

12.5.3

13.0.0

12.5.3

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

7242

32

32768

False

2,088 ± 352 / 706 ± 214

2.96

2.82

3.09

2.71

3.90

3.71

2.31

2.86

2.27

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

66.68 ± 0.81 / 22.38 ± 0.71

44.30 ± 2.46 / 57.00 ± 2.30

48.76 ± 2.39 / 65.51 ± 1.72

15.44 ± 1.66 / 35.82 ± 1.14

45.50 ± 2.71 / 40.02 ± 3.16

45.96 ± 2.67 / 41.28 ± 2.25

44.46 ± 3.40 / 62.00 ± 2.71

63.95 ± 0.42 / 16.91 ± 0.61

0.00 ± 0.00 / 33.41 ± 0.30

0.00 ± 0.00 / 33.86 ± 0.33

52.19 ± 2.88 / 74.97 ± 2.11

20.61 ± 1.27 / 39.79 ± 1.10

16.18 ± 1.88 / 36.19 ± 1.66

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

65.07 ± 0.34 / 19.59 ± 0.38

25.52 ± 1.30 / 43.68 ± 1.03

14.06 ± 1.68 / 35.12 ± 1.47

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

65.25 ± 0.97 / 19.09 ± 1.05

5.35 ± 1.32 / 28.11 ± 1.13

0.35 ± 2.49 / 51.16 ± 2.74

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

69.43 ± 0.97 / 29.48 ± 2.59

32.56 ± 1.16 / 49.02 ± 0.79

23.61 ± 2.42 / 41.55 ± 2.14

53.78 ± 1.86 / 41.29 ± 2.07

7.78 ± 1.43 / 24.33 ± 1.57

16.23 ± 2.49 / 55.09 ± 3.18

63.09 ± 1.18 / 73.88 ± 0.72

66.46 ± 0.67 / 19.49 ± 0.92

28.37 ± 0.99 / 45.81 ± 0.88

15.25 ± 1.71 / 35.83 ± 1.42

56.90 ± 3.08 / 51.16 ± 2.56

62.10 ± 1.65 / 68.81 ± 0.76

20.17 ± 3.68 / 54.76 ± 4.24

75.29 ± 1.37 / 86.48 ± 0.72

69.63 ± 0.46 / 25.61 ± 0.45

38.48 ± 1.10 / 53.32 ± 0.83

27.67 ± 2.08 / 43.61 ± 2.08

12.5.2

12.2.0

12.3.1

12.4.0

12.6.1

12.3.1

12.5.2

12.2.0

12.4.0

12.3.1

12.4.0

12.3.1

12.5.2

12.2.0

12.3.1

12.4.0

12.3.1

12.5.2

13.3.0

12.3.1

12.4.0

12.10.8

12.3.1

12.5.2

13.3.0

12.3.1

13.0.0

12.5.2

12.2.0

12.3.1

12.4.0

12.3.1

12.5.2

12.2.0

12.3.1

12.4.0

12.3.1

12.5.2

12.2.0

12.3.1

12.4.0

12.3.1

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

3213

128

131073

False

10,424 ± 2,641 / 2,081 ± 666

2.97

2.79

3.23

2.67

4.03

3.49

2.63

2.81

2.09

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

65.19 ± 0.78 / 18.34 ± 1.22

49.78 ± 1.52 / 62.29 ± 1.14

45.88 ± 2.43 / 63.96 ± 1.59

21.89 ± 1.77 / 41.16 ± 1.43

49.66 ± 1.79 / 39.31 ± 2.55

51.98 ± 1.55 / 42.48 ± 3.10

44.13 ± 2.80 / 60.09 ± 3.10

60.50 ± 0.73 / 10.91 ± 0.62

0.67 ± 1.18 / 33.81 ± 0.33

1.11 ± 0.93 / 33.03 ± 0.39

28.62 ± 4.16 / 56.91 ± 4.14

26.82 ± 1.08 / 45.32 ± 0.84

20.98 ± 1.40 / 40.34 ± 1.17

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

64.98 ± 0.47 / 17.53 ± 0.50

29.44 ± 0.61 / 47.21 ± 0.47

22.42 ± 1.89 / 41.45 ± 1.49

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

62.00 ± 1.89 / 14.40 ± 1.93

13.33 ± 1.23 / 35.42 ± 0.93

0.74 ± 1.09 / 50.92 ± 0.73

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

66.40 ± 0.98 / 21.21 ± 2.33

33.58 ± 0.41 / 50.27 ± 0.28

28.97 ± 1.01 / 46.45 ± 0.80

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

66.74 ± 1.00 / 18.33 ± 1.28

33.80 ± 0.84 / 50.30 ± 0.61

21.02 ± 1.29 / 40.27 ± 1.09

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

69.23 ± 0.19 / 24.84 ± 0.39

45.50 ± 0.74 / 58.96 ± 0.57

46.50 ± 1.78 / 59.43 ± 1.44

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

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

7242

32

32768

False

634 ± 179 / 110 ± 35

3.01

2.79

3.12

2.81

4.04

3.59

2.61

3.00

2.16

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

65.80 ± 0.93 / 19.91 ± 1.41

45.07 ± 1.34 / 58.18 ± 1.03

35.36 ± 2.19 / 55.82 ± 1.48

14.85 ± 1.19 / 35.26 ± 1.24

50.08 ± 1.54 / 34.52 ± 1.17

51.27 ± 1.52 / 33.37 ± 2.37

43.65 ± 1.98 / 60.88 ± 1.36

62.39 ± 0.76 / 14.24 ± 0.81

14.09 ± 2.85 / 44.91 ± 3.95

8.28 ± 1.82 / 47.22 ± 3.72

37.23 ± 3.15 / 63.67 ± 2.98

20.44 ± 1.03 / 39.51 ± 0.72

15.87 ± 1.29 / 35.89 ± 1.06

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

63.10 ± 0.60 / 18.05 ± 0.36

24.03 ± 1.09 / 42.32 ± 0.70

15.37 ± 0.71 / 35.78 ± 0.69

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

62.80 ± 1.69 / 15.23 ± 1.01

5.44 ± 1.14 / 28.13 ± 1.06

6.35 ± 2.71 / 50.49 ± 1.57

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

67.75 ± 1.10 / 25.91 ± 2.95

26.79 ± 1.01 / 44.58 ± 0.85

20.33 ± 1.63 / 39.63 ± 1.09

52.72 ± 2.58 / 33.51 ± 1.22

7.91 ± 2.16 / 27.82 ± 1.97

18.14 ± 2.10 / 55.42 ± 3.05

52.75 ± 0.88 / 67.15 ± 1.08

64.77 ± 0.97 / 16.55 ± 0.81

26.06 ± 0.77 / 44.08 ± 0.51

14.26 ± 1.48 / 35.14 ± 1.18

57.58 ± 2.30 / 47.94 ± 2.89

61.44 ± 2.02 / 69.47 ± 0.98

34.92 ± 2.40 / 66.67 ± 1.41

65.38 ± 1.76 / 81.90 ± 0.57

69.62 ± 0.31 / 24.65 ± 0.44

38.40 ± 0.98 / 53.43 ± 0.76

35.72 ± 1.56 / 49.69 ± 1.42

9.3.1

12.4.0

12.6.1

10.0.1

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

12.10.8

12.1.0

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

9.3.1

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

7242

32

32768

True

2,219 ± 427 / 717 ± 224

3.03

2.87

3.19

2.75

4.04

3.68

2.37

2.97

2.35

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

66.05 ± 1.13 / 21.82 ± 0.96

38.54 ± 1.47 / 53.57 ± 1.26

45.89 ± 3.00 / 63.14 ± 1.98

12.38 ± 1.99 / 33.54 ± 1.61

45.28 ± 3.06 / 41.73 ± 2.14

46.00 ± 4.26 / 42.96 ± 3.38

44.95 ± 3.19 / 61.88 ± 2.88

63.26 ± 1.07 / 16.04 ± 1.34

0.00 ± 0.00 / 33.41 ± 0.30

0.00 ± 0.00 / 33.86 ± 0.33

43.88 ± 4.07 / 66.65 ± 4.20

20.87 ± 1.54 / 39.98 ± 1.27

13.10 ± 2.04 / 34.20 ± 1.55

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

64.42 ± 0.45 / 18.79 ± 0.47

23.68 ± 1.41 / 42.15 ± 1.14

14.05 ± 1.60 / 34.81 ± 1.58

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

62.55 ± 3.03 / 15.26 ± 2.31

5.98 ± 1.66 / 28.18 ± 1.30

-0.51 ± 1.95 / 47.23 ± 2.39

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

69.31 ± 0.68 / 28.27 ± 1.70

32.49 ± 0.91 / 48.82 ± 0.70

22.25 ± 2.13 / 40.28 ± 1.67

51.31 ± 2.32 / 42.95 ± 2.58

7.41 ± 1.24 / 26.93 ± 1.56

13.04 ± 1.93 / 53.54 ± 2.70

59.28 ± 1.15 / 69.67 ± 0.95

64.66 ± 0.74 / 18.22 ± 0.85

27.12 ± 0.86 / 44.36 ± 0.75

13.99 ± 2.04 / 34.45 ± 1.89

55.37 ± 2.94 / 51.08 ± 2.87

63.32 ± 1.29 / 68.50 ± 0.53

18.92 ± 2.39 / 57.96 ± 1.89

72.38 ± 2.57 / 83.46 ± 1.49

68.61 ± 0.55 / 23.48 ± 0.74

37.04 ± 1.33 / 52.33 ± 1.02

23.54 ± 2.08 / 40.78 ± 1.59

12.5.2

12.1.0

12.6.1

12.1.0

12.2.0

12.5.2

12.1.0

12.2.0

12.5.2

12.1.0

12.2.0

12.5.2

13.3.0

12.1.0

12.10.8

12.2.0

12.5.2

13.3.0

12.1.0

13.0.0

12.5.2

12.1.0

12.2.0

12.5.2

12.1.0

12.2.0

12.5.2

12.1.0

12.2.0

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

8055

49

4096

True

2,313 ± 423 / 682 ± 210

3.05

3.01

3.20

2.90

4.03

3.36

2.64

2.89

2.34

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

63.93 ± 0.79 / 17.49 ± 0.73

33.11 ± 2.59 / 49.31 ± 2.03

18.96 ± 2.16 / 46.29 ± 1.39

9.03 ± 1.28 / 31.42 ± 1.04

68.40 ± 1.16 / 62.53 ± 1.69

65.15 ± 0.79 / 60.39 ± 2.11

42.00 ± 1.78 / 59.90 ± 1.22

61.27 ± 0.80 / 13.34 ± 0.66

5.20 ± 2.23 / 36.33 ± 1.30

3.32 ± 2.02 / 37.81 ± 3.26

37.51 ± 2.58 / 60.94 ± 3.06

12.42 ± 1.42 / 34.82 ± 0.98

8.32 ± 0.78 / 30.87 ± 0.75

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

62.61 ± 0.55 / 17.92 ± 0.33

14.34 ± 0.73 / 35.93 ± 0.55

7.40 ± 1.39 / 30.20 ± 1.23

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

59.94 ± 2.87 / 12.62 ± 1.91

5.52 ± 1.26 / 28.97 ± 0.97

1.73 ± 2.31 / 50.89 ± 3.35

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

67.78 ± 1.54 / 26.66 ± 3.40

16.39 ± 1.29 / 37.35 ± 0.95

10.68 ± 1.41 / 32.52 ± 1.35

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

63.08 ± 0.90 / 15.69 ± 0.65

16.86 ± 1.16 / 37.54 ± 0.93

6.24 ± 0.78 / 29.25 ± 0.61

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

67.73 ± 0.60 / 23.48 ± 0.91

25.63 ± 0.81 / 44.26 ± 0.63

16.44 ± 1.84 / 36.73 ± 1.54

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

3.12

2.89

3.30

2.92

4.05

3.74

2.78

2.98

2.33

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

66.15 ± 0.67 / 19.69 ± 0.94

32.17 ± 2.28 / 46.67 ± 1.92

35.74 ± 2.46 / 55.18 ± 1.81

11.32 ± 0.41 / 32.24 ± 0.79

44.99 ± 2.49 / 38.59 ± 2.84

49.09 ± 1.90 / 39.09 ± 4.02

41.56 ± 3.37 / 57.09 ± 3.80

63.59 ± 0.40 / 14.15 ± 0.70

3.04 ± 2.84 / 36.81 ± 2.42

4.03 ± 2.49 / 40.55 ± 4.14

33.77 ± 2.11 / 61.99 ± 2.34

14.81 ± 0.79 / 34.79 ± 0.63

12.69 ± 0.77 / 31.84 ± 1.05

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

65.92 ± 0.05 / 18.51 ± 0.18

17.73 ± 0.98 / 37.55 ± 0.69

12.85 ± 0.93 / 33.37 ± 0.90

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

62.30 ± 0.90 / 13.28 ± 1.36

3.16 ± 0.79 / 27.40 ± 0.79

1.84 ± 2.19 / 43.79 ± 0.73

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

67.62 ± 0.89 / 23.52 ± 2.43

20.12 ± 1.13 / 39.48 ± 1.02

13.98 ± 1.56 / 34.07 ± 1.30

50.23 ± 2.34 / 37.12 ± 3.30

10.07 ± 1.84 / 35.66 ± 2.24

14.73 ± 1.62 / 54.59 ± 2.24

53.42 ± 0.80 / 66.24 ± 0.84

67.59 ± 0.56 / 18.45 ± 0.65

20.19 ± 1.26 / 39.24 ± 1.03

11.42 ± 1.29 / 32.50 ± 1.10

62.53 ± 1.35 / 53.42 ± 2.04

62.23 ± 1.29 / 68.09 ± 1.34

22.71 ± 1.81 / 60.79 ± 1.08

64.45 ± 1.39 / 80.79 ± 0.79

69.95 ± 0.32 / 25.22 ± 0.33

30.47 ± 0.70 / 46.82 ± 0.55

30.18 ± 1.87 / 45.85 ± 1.98

9.3.1

12.4.0

12.6.1

10.0.1

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

12.10.8

12.1.0

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

9.3.1

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

8055

49

4096

True

5,617 ± 995 / 1,623 ± 540

3.18

3.10

3.28

2.95

4.35

3.48

2.84

3.02

2.41

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

63.86 ± 0.96 / 18.38 ± 0.71

32.44 ± 2.29 / 46.63 ± 2.29

7.46 ± 1.83 / 39.41 ± 1.17

5.62 ± 1.16 / 28.71 ± 0.79

66.91 ± 1.50 / 54.98 ± 2.20

62.82 ± 1.23 / 53.14 ± 3.17

40.71 ± 1.63 / 59.35 ± 1.58

60.59 ± 0.99 / 12.74 ± 0.82

9.50 ± 1.68 / 46.31 ± 3.06

6.74 ± 1.70 / 42.10 ± 4.67

32.83 ± 1.83 / 55.30 ± 2.35

11.35 ± 1.23 / 32.01 ± 0.91

6.21 ± 0.99 / 29.05 ± 0.80

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

60.98 ± 0.80 / 16.18 ± 0.48

13.69 ± 0.86 / 33.34 ± 0.46

5.68 ± 1.13 / 27.99 ± 1.11

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

49.66 ± 3.28 / 7.97 ± 1.43

3.07 ± 1.66 / 25.74 ± 1.09

2.79 ± 3.13 / 47.97 ± 1.43

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

66.68 ± 1.30 / 24.80 ± 3.14

15.81 ± 1.07 / 36.18 ± 0.94

9.60 ± 1.12 / 31.31 ± 1.02

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

63.23 ± 0.96 / 16.22 ± 0.74

15.26 ± 0.67 / 35.76 ± 0.34

4.03 ± 0.90 / 27.17 ± 0.73

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

68.41 ± 0.33 / 24.66 ± 0.47

24.14 ± 0.58 / 42.17 ± 0.33

14.42 ± 2.00 / 34.50 ± 1.81

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

3.34

3.35

3.58

3.11

4.43

4.15

2.75

2.98

2.35

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

63.82 ± 0.97 / 18.09 ± 0.88

18.25 ± 1.54 / 38.38 ± 1.12

19.54 ± 2.59 / 46.35 ± 1.91

2.64 ± 1.03 / 26.88 ± 0.77

44.89 ± 2.26 / 34.93 ± 2.45

48.08 ± 1.68 / 34.39 ± 2.61

32.29 ± 1.15 / 51.91 ± 2.66

59.77 ± 0.91 / 11.96 ± 0.65

7.49 ± 1.65 / 47.79 ± 3.81

4.65 ± 1.91 / 45.75 ± 5.13

26.37 ± 1.51 / 47.59 ± 2.41

11.54 ± 1.37 / 32.89 ± 1.10

3.42 ± 1.93 / 26.93 ± 1.47

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

60.93 ± 0.49 / 14.76 ± 0.77

13.55 ± 1.27 / 34.97 ± 0.99

5.27 ± 1.49 / 27.92 ± 1.10

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

60.80 ± 0.81 / 10.79 ± 1.85

2.86 ± 1.31 / 26.61 ± 1.04

-1.31 ± 2.24 / 50.29 ± 1.93

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

61.97 ± 1.94 / 19.06 ± 1.18

22.99 ± 0.83 / 41.98 ± 0.66

20.06 ± 1.95 / 38.69 ± 1.78

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

64.77 ± 0.96 / 16.74 ± 0.86

21.52 ± 1.18 / 40.76 ± 0.95

22.32 ± 2.02 / 39.89 ± 1.82

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

65.50 ± 0.97 / 21.90 ± 0.40

33.84 ± 0.87 / 50.07 ± 0.67

49.84 ± 1.22 / 61.87 ± 1.03

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

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

6738

32

4096

True

6,275 ± 1,193 / 1,755 ± 578

3.49

3.52

3.74

3.13

3.99

3.77

3.44

3.56

2.76

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

53.81 ± 1.18 / 9.42 ± 0.33

27.86 ± 1.78 / 43.42 ± 1.51

34.62 ± 2.93 / 55.21 ± 2.08

4.73 ± 0.61 / 27.77 ± 0.53

36.96 ± 3.10 / 34.68 ± 3.19

39.38 ± 3.30 / 37.06 ± 3.49

32.67 ± 2.52 / 44.37 ± 3.06

51.44 ± 1.23 / 8.37 ± 0.51

2.18 ± 2.36 / 38.05 ± 3.18

5.33 ± 2.97 / 44.30 ± 4.99

45.23 ± 5.03 / 67.75 ± 4.41

9.35 ± 1.27 / 30.22 ± 0.88

4.85 ± 0.63 / 27.55 ± 0.65

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

55.94 ± 1.10 / 13.29 ± 0.34

10.56 ± 1.14 / 31.45 ± 0.92

5.03 ± 1.36 / 28.41 ± 0.76

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

58.72 ± 3.28 / 13.71 ± 1.35

12.62 ± 1.36 / 34.51 ± 1.27

3.43 ± 2.18 / 44.56 ± 1.09

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

58.62 ± 3.80 / 13.54 ± 2.20

14.94 ± 1.09 / 35.44 ± 0.89

8.70 ± 0.96 / 31.09 ± 0.58

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

54.50 ± 5.78 / 15.01 ± 1.59

14.90 ± 1.44 / 35.20 ± 1.09

7.26 ± 1.56 / 29.91 ± 1.18

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

67.34 ± 0.38 / 21.61 ± 0.61

16.59 ± 1.01 / 35.35 ± 0.70

11.97 ± 1.35 / 32.72 ± 0.94

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

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

3374

49

4096

True

10,504 ± 3,028 / 1,678 ± 559

3.51

3.59

3.66

3.28

4.62

4.33

3.02

3.11

2.46

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

63.43 ± 0.90 / 16.85 ± 1.02

15.97 ± 1.54 / 36.37 ± 1.08

17.19 ± 2.72 / 45.23 ± 1.84

3.07 ± 0.91 / 27.05 ± 0.83

40.08 ± 2.60 / 33.17 ± 1.81

43.96 ± 1.65 / 32.96 ± 2.24

31.90 ± 1.50 / 53.03 ± 1.81

59.98 ± 1.54 / 11.97 ± 1.13

-0.07 ± 0.97 / 35.01 ± 1.42

1.27 ± 2.35 / 38.10 ± 4.51

23.32 ± 2.39 / 43.13 ± 3.33

11.78 ± 1.09 / 33.75 ± 0.93

5.48 ± 1.23 / 28.09 ± 1.29

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

58.57 ± 0.73 / 15.09 ± 0.29

13.42 ± 0.96 / 34.81 ± 0.72

7.33 ± 1.70 / 29.31 ± 1.45

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

56.49 ± 3.33 / 8.77 ± 1.24

0.32 ± 1.35 / 24.82 ± 1.04

1.00 ± 2.57 / 51.21 ± 2.91

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

66.77 ± 0.94 / 23.71 ± 1.90

22.17 ± 1.05 / 41.55 ± 0.85

22.61 ± 1.75 / 41.16 ± 1.46

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

63.71 ± 0.60 / 17.04 ± 0.70

20.93 ± 1.42 / 40.35 ± 1.23

24.42 ± 1.73 / 42.26 ± 1.49

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

66.38 ± 0.28 / 21.17 ± 0.41

32.06 ± 0.87 / 49.12 ± 0.61

58.21 ± 0.98 / 68.63 ± 0.74

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

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

3483

49

2048

True

9,059 ± 1,947 / 2,201 ± 728

3.60

3.45

3.68

3.40

4.59

4.16

3.30

3.46

2.77

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

61.56 ± 0.49 / 13.64 ± 0.97

17.92 ± 1.52 / 37.22 ± 1.29

10.79 ± 2.32 / 40.86 ± 1.85

1.70 ± 1.10 / 26.14 ± 0.76

53.78 ± 2.43 / 49.41 ± 2.56

55.14 ± 1.27 / 51.07 ± 1.78

26.21 ± 1.63 / 43.33 ± 1.46

57.11 ± 1.08 / 10.81 ± 0.52

3.90 ± 1.45 / 43.86 ± 4.21

2.42 ± 1.39 / 41.58 ± 3.89

24.86 ± 1.34 / 45.77 ± 1.85

10.36 ± 1.15 / 29.64 ± 1.06

5.85 ± 1.57 / 27.84 ± 1.21

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

45.16 ± 0.70 / 11.84 ± 0.27

7.58 ± 0.88 / 28.54 ± 0.85

3.79 ± 0.85 / 27.39 ± 0.57

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

49.32 ± 3.71 / 8.01 ± 2.04

1.37 ± 1.11 / 25.57 ± 1.36

-4.04 ± 3.58 / 50.55 ± 3.65

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

60.81 ± 0.38 / 15.92 ± 0.54

6.89 ± 0.76 / 28.82 ± 0.69

4.79 ± 0.91 / 28.40 ± 0.78

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

59.56 ± 1.09 / 15.20 ± 0.56

7.38 ± 1.06 / 29.60 ± 0.71

2.69 ± 0.56 / 25.85 ± 0.33

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

67.46 ± 0.31 / 23.04 ± 0.42

14.10 ± 0.93 / 34.24 ± 0.84

10.67 ± 0.81 / 32.66 ± 0.64

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

3.65

3.36

4.07

3.43

4.29

4.07

3.61

3.43

2.97

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

62.50 ± 0.59 / 15.45 ± 0.50

13.46 ± 2.03 / 33.24 ± 1.59

15.31 ± 3.62 / 43.65 ± 2.19

6.00 ± 1.15 / 29.24 ± 0.76

53.93 ± 3.93 / 48.95 ± 4.17

54.04 ± 1.83 / 49.74 ± 2.48

23.83 ± 3.47 / 45.39 ± 3.46

50.59 ± 3.68 / 7.28 ± 1.97

3.91 ± 1.46 / 42.54 ± 4.53

1.55 ± 2.39 / 40.63 ± 4.26

2.37 ± 0.20 / 12.14 ± 1.07

8.68 ± 1.17 / 31.15 ± 0.84

6.19 ± 0.85 / 29.29 ± 0.77

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

41.31 ± 2.13 / 7.20 ± 1.44

7.41 ± 0.75 / 30.14 ± 0.39

5.42 ± 0.79 / 29.15 ± 0.59

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

58.58 ± 4.00 / 12.91 ± 2.09

2.11 ± 1.02 / 27.80 ± 1.02

-4.75 ± 2.84 / 50.40 ± 4.21

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

45.88 ± 3.36 / 8.30 ± 1.98

8.73 ± 1.03 / 31.46 ± 0.70

6.18 ± 1.33 / 29.78 ± 1.02

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

52.50 ± 2.95 / 10.11 ± 2.12

9.22 ± 0.79 / 31.06 ± 0.75

4.45 ± 1.38 / 28.26 ± 1.08

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

56.62 ± 3.70 / 13.80 ± 2.77

16.29 ± 0.76 / 36.25 ± 0.61

10.37 ± 1.17 / 32.60 ± 0.89

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0

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

1711

49

8192

True

15,971 ± 3,654 / 3,609 ± 1,197

3.75

3.63

4.15

3.41

4.34

4.48

3.54

3.89

2.57

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

61.76 ± 1.10 / 15.33 ± 1.17

22.03 ± 1.83 / 37.29 ± 1.77

12.61 ± 2.43 / 41.82 ± 1.61

2.06 ± 0.89 / 26.03 ± 0.67

37.60 ± 2.17 / 29.30 ± 2.43

38.38 ± 2.48 / 30.13 ± 2.95

24.05 ± 3.58 / 40.36 ± 4.22

48.55 ± 6.18 / 8.21 ± 1.30

3.56 ± 1.93 / 38.60 ± 3.52

2.61 ± 2.57 / 38.57 ± 3.89

13.58 ± 3.16 / 25.34 ± 5.83

9.52 ± 1.13 / 30.72 ± 1.12

3.62 ± 1.22 / 27.07 ± 1.15

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

54.50 ± 1.26 / 12.92 ± 0.48

8.61 ± 1.25 / 29.95 ± 1.28

4.51 ± 0.96 / 27.64 ± 0.87

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

60.43 ± 2.70 / 15.28 ± 1.36

1.93 ± 1.38 / 25.06 ± 1.16

3.27 ± 2.97 / 54.02 ± 1.79

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

59.91 ± 0.84 / 16.05 ± 0.61

12.30 ± 1.16 / 32.60 ± 1.27

6.28 ± 1.36 / 27.82 ± 1.17

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

60.35 ± 1.16 / 13.63 ± 0.63

13.39 ± 0.96 / 34.55 ± 0.65

4.57 ± 0.96 / 27.42 ± 0.73

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

62.45 ± 5.62 / 19.60 ± 1.85

32.90 ± 0.96 / 49.16 ± 0.95

25.32 ± 2.12 / 42.50 ± 2.39

13.1.0

13.3.0

13.1.0

13.3.0

13.1.0

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

1657

128

4096

True

15,009 ± 4,072 / 2,702 ± 878

3.76

3.52

3.81

3.34

4.63

4.64

3.37

3.65

3.14

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

63.91 ± 1.29 / 18.26 ± 1.57

2.54 ± 1.89 / 25.25 ± 1.06

17.85 ± 2.63 / 40.98 ± 1.12

0.52 ± 0.97 / 25.60 ± 0.68

31.43 ± 1.78 / 30.82 ± 2.35

36.92 ± 1.75 / 37.80 ± 1.67

30.63 ± 1.48 / 37.24 ± 1.90

59.45 ± 1.98 / 10.85 ± 1.59

0.98 ± 1.59 / 42.00 ± 2.28

1.67 ± 1.96 / 34.92 ± 1.93

33.24 ± 2.51 / 55.11 ± 2.82

1.85 ± 1.02 / 24.15 ± 0.66

-1.18 ± 1.33 / 24.23 ± 0.94

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

63.23 ± 0.51 / 17.40 ± 0.45

3.39 ± 0.48 / 25.11 ± 0.71

0.54 ± 0.72 / 25.45 ± 0.45

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

56.76 ± 2.66 / 9.80 ± 1.05

0.59 ± 0.49 / 23.09 ± 0.56

1.87 ± 3.67 / 49.58 ± 3.20

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

64.64 ± 0.93 / 17.38 ± 1.77

2.60 ± 0.88 / 26.76 ± 0.79

1.46 ± 1.09 / 26.00 ± 0.95

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

61.96 ± 0.80 / 14.66 ± 0.48

2.53 ± 1.10 / 25.95 ± 1.10

1.04 ± 0.74 / 25.13 ± 0.68

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

67.24 ± 0.36 / 21.22 ± 0.36

3.93 ± 0.84 / 28.88 ± 0.73

1.26 ± 1.14 / 25.56 ± 0.82

13.1.0

13.3.0

13.1.0

13.3.0

13.1.0

HuggingFaceTB/SmolLM2-1.7B (few-shot)

1711

49

8192

True

16,249 ± 3,690 / 3,689 ± 1,226

3.83

3.81

4.08

3.35

4.43

4.65

3.55

3.94

2.84

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

61.62 ± 0.72 / 14.36 ± 0.73

19.65 ± 1.47 / 36.46 ± 1.24

19.01 ± 2.56 / 46.27 ± 1.71

1.34 ± 1.16 / 25.88 ± 0.65

26.70 ± 4.42 / 24.56 ± 2.10

28.23 ± 3.78 / 28.27 ± 2.80

23.25 ± 4.16 / 36.07 ± 4.20

56.31 ± 2.34 / 9.78 ± 0.93

-0.47 ± 1.05 / 33.93 ± 0.92

0.26 ± 0.74 / 33.32 ± 0.79

13.40 ± 2.83 / 26.51 ± 4.94

11.12 ± 0.88 / 33.35 ± 0.75

2.53 ± 0.82 / 26.29 ± 0.74

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

57.04 ± 0.95 / 13.24 ± 1.09

10.86 ± 1.20 / 31.65 ± 1.09

2.53 ± 0.98 / 26.17 ± 0.78

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

57.52 ± 4.61 / 13.43 ± 2.11

3.16 ± 0.85 / 26.13 ± 0.67

-1.83 ± 3.11 / 49.80 ± 1.96

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

64.25 ± 1.99 / 18.90 ± 2.50

15.15 ± 0.67 / 35.75 ± 0.46

6.23 ± 0.96 / 28.39 ± 0.87

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

58.31 ± 1.50 / 13.08 ± 0.51

14.32 ± 0.71 / 35.65 ± 0.50

3.87 ± 1.02 / 27.14 ± 0.66

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

65.06 ± 0.87 / 20.12 ± 0.51

34.02 ± 0.87 / 50.12 ± 0.76

22.81 ± 1.86 / 41.37 ± 1.41

13.1.0

13.3.0

13.1.0

13.3.0

13.1.0

HuggingFaceTB/SmolLM2-360M (few-shot)

362

49

8192

True

22,023 ± 6,203 / 3,675 ± 1,231

4.37

4.33

4.65

4.32

4.82

4.88

4.08

4.20

3.68

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

56.85 ± 1.37 / 10.17 ± 1.17

-0.03 ± 0.59 / 23.99 ± 0.76

6.03 ± 3.05 / 37.58 ± 1.59

0.20 ± 0.86 / 25.12 ± 0.70

26.60 ± 1.99 / 23.60 ± 2.05

23.70 ± 1.58 / 23.04 ± 2.17

6.21 ± 2.55 / 23.74 ± 3.28

48.59 ± 1.59 / 6.80 ± 0.45

-0.39 ± 0.76 / 33.40 ± 0.31

0.21 ± 0.41 / 35.33 ± 3.02

4.65 ± 1.00 / 10.23 ± 1.68

-1.13 ± 0.96 / 21.80 ± 0.52

-0.51 ± 0.40 / 24.82 ± 0.86

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

45.57 ± 0.97 / 9.20 ± 0.68

0.69 ± 0.65 / 22.10 ± 0.54

0.68 ± 0.79 / 25.25 ± 0.76

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

51.93 ± 3.96 / 8.48 ± 0.87

0.95 ± 1.48 / 22.52 ± 1.05

2.90 ± 2.91 / 56.72 ± 0.69

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

57.06 ± 3.46 / 11.78 ± 1.69

0.32 ± 0.94 / 22.52 ± 0.61

-0.65 ± 0.72 / 24.04 ± 0.46

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

53.89 ± 2.61 / 10.53 ± 0.37

-0.45 ± 1.59 / 24.24 ± 0.79

-0.31 ± 1.39 / 23.58 ± 0.40

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

62.20 ± 1.04 / 17.61 ± 0.50

0.12 ± 1.55 / 23.00 ± 0.82

0.13 ± 1.34 / 24.53 ± 0.49

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

4.43

4.42

4.66

4.44

4.83

4.89

4.34

4.35

3.54

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

55.39 ± 0.68 / 10.01 ± 0.63

0.28 ± 0.93 / 23.92 ± 0.72

3.55 ± 3.45 / 35.45 ± 1.54

-0.41 ± 1.41 / 25.02 ± 0.71

20.37 ± 5.55 / 21.57 ± 3.57

21.27 ± 5.10 / 22.34 ± 4.41

7.60 ± 2.24 / 26.47 ± 2.89

49.27 ± 1.15 / 7.39 ± 0.36

1.31 ± 1.92 / 45.75 ± 3.36

0.51 ± 1.81 / 38.71 ± 2.95

4.80 ± 1.18 / 10.53 ± 2.12

-0.90 ± 0.97 / 21.85 ± 0.55

-1.00 ± 0.70 / 24.21 ± 0.55

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

37.49 ± 0.77 / 9.36 ± 0.25

-0.00 ± 0.96 / 22.03 ± 0.45

0.78 ± 1.51 / 25.50 ± 0.87

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

50.00 ± 3.22 / 7.84 ± 0.71

-0.11 ± 0.95 / 22.28 ± 0.83

2.51 ± 3.01 / 51.41 ± 3.27

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

46.31 ± 1.46 / 8.68 ± 0.61

0.84 ± 0.81 / 22.50 ± 0.61

0.01 ± 1.07 / 24.43 ± 0.50

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

50.53 ± 2.03 / 9.14 ± 0.47

1.30 ± 0.75 / 24.43 ± 0.78

-0.36 ± 0.85 / 24.09 ± 0.49

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

57.73 ± 4.93 / 15.68 ± 1.21

0.11 ± 1.23 / 23.20 ± 0.56

-0.06 ± 0.39 / 24.60 ± 0.44

13.1.0

13.3.0

13.1.0

13.3.0

13.1.0

HuggingFaceTB/SmolLM2-135M (few-shot)

135

49

8192

True

26,346 ± 7,812 / 4,082 ± 1,372

4.61

4.72

4.54

4.44

4.75

4.97

4.48

4.61

4.40

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

47.44 ± 1.55 / 6.04 ± 0.58

-0.58 ± 2.44 / 25.72 ± 1.40

10.99 ± 5.42 / 38.26 ± 1.92

-0.51 ± 1.30 / 24.79 ± 0.70

24.37 ± 2.17 / 26.91 ± 2.28

24.69 ± 1.85 / 27.60 ± 2.48

8.84 ± 4.19 / 29.74 ± 3.45

53.61 ± 2.33 / 6.64 ± 0.79

-1.20 ± 1.10 / 36.09 ± 3.06

-0.50 ± 1.21 / 36.68 ± 3.16

0.16 ± 0.13 / 2.31 ± 0.44

-0.81 ± 0.69 / 24.67 ± 1.24

-0.71 ± 1.01 / 24.42 ± 0.63

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

51.51 ± 1.96 / 11.46 ± 0.73

0.02 ± 1.30 / 25.25 ± 0.94

0.04 ± 0.79 / 24.92 ± 0.73

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

52.66 ± 3.89 / 8.73 ± 0.71

1.21 ± 0.80 / 26.20 ± 1.03

1.69 ± 2.26 / 49.46 ± 3.56

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

54.79 ± 2.10 / 8.47 ± 1.10

-0.32 ± 0.88 / 25.45 ± 0.97

0.18 ± 0.99 / 25.72 ± 0.91

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

52.46 ± 1.93 / 9.47 ± 0.33

0.33 ± 0.71 / 25.12 ± 0.63

-0.10 ± 0.85 / 24.87 ± 0.65

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

52.05 ± 1.59 / 12.74 ± 1.04

1.51 ± 0.81 / 25.05 ± 0.75

-0.76 ± 0.97 / 24.52 ± 0.59

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

4.63

4.46

4.65

4.57

4.93

4.87

4.56

4.69

4.28

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

56.53 ± 0.95 / 8.45 ± 0.77

1.05 ± 1.51 / 26.37 ± 0.83

10.81 ± 4.60 / 38.73 ± 1.77

-0.50 ± 0.85 / 24.15 ± 0.67

20.89 ± 2.55 / 22.28 ± 2.32

19.62 ± 1.91 / 21.82 ± 2.35

2.78 ± 4.25 / 26.17 ± 3.37

53.93 ± 2.39 / 6.60 ± 0.99

-0.98 ± 1.80 / 40.63 ± 4.03

0.93 ± 2.26 / 40.91 ± 4.95

0.15 ± 0.13 / 2.19 ± 0.57

-0.48 ± 1.78 / 25.53 ± 1.87

-0.53 ± 0.95 / 24.68 ± 0.62

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

38.30 ± 1.88 / 8.09 ± 0.47

0.30 ± 0.87 / 25.76 ± 0.77

0.06 ± 1.19 / 24.33 ± 0.53

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

50.30 ± 4.32 / 7.82 ± 0.77

1.10 ± 1.16 / 25.43 ± 1.07

-0.07 ± 3.01 / 46.28 ± 3.42

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

49.41 ± 1.73 / 7.27 ± 0.41

-1.46 ± 0.84 / 24.84 ± 0.68

-0.18 ± 1.25 / 24.79 ± 1.02

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

54.82 ± 3.44 / 9.74 ± 0.58

1.36 ± 1.10 / 25.96 ± 0.81

0.34 ± 1.33 / 25.40 ± 0.83

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

52.96 ± 1.38 / 14.23 ± 0.78

1.34 ± 0.74 / 25.67 ± 1.03

0.10 ± 1.29 / 24.71 ± 0.69

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

5.15

5.18

5.09

4.90

5.40

5.37

4.93

5.09

5.25

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

42.82 ± 0.93 / 0.20 ± 0.02

4.55 ± 2.15 / 25.74 ± 1.15

-1.17 ± 3.12 / 34.84 ± 1.63

-1.26 ± 1.34 / 24.88 ± 0.69

0.00 ± 0.00 / 0.00 ± 0.00

0.00 ± 0.00 / 9.59 ± 0.29

41.98 ± 0.64 / 0.21 ± 0.04

0.00 ± 0.00 / 33.25 ± 0.30

0.00 ± 0.00 / 32.79 ± 0.34

0.00 ± 0.00 / 0.09 ± 0.03

1.14 ± 1.04 / 24.51 ± 0.78

0.64 ± 1.18 / 24.68 ± 0.55

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

40.82 ± 1.17 / 0.34 ± 0.05

1.19 ± 1.32 / 24.74 ± 1.06

1.55 ± 0.84 / 25.30 ± 0.69

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

36.58 ± 2.96 / 0.16 ± 0.02

-0.00 ± 1.73 / 24.71 ± 1.42

0.00 ± 0.00 / 43.48 ± 0.89

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

37.66 ± 0.76 / 0.15 ± 0.02

0.87 ± 0.51 / 24.67 ± 0.61

1.95 ± 1.33 / 25.62 ± 0.89

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

43.74 ± 0.57 / 0.22 ± 0.04

0.32 ± 0.67 / 24.79 ± 0.61

1.73 ± 1.07 / 26.61 ± 0.61

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

44.80 ± 0.36 / 0.32 ± 0.04

-0.69 ± 0.77 / 22.76 ± 0.40

0.37 ± 0.95 / 24.71 ± 0.44

13.0.0

13.3.0

13.0.0

13.3.0

13.0.0