MathCAMPS Logo

CodeLlama 13B

Performance on individual Common Core standards, grouped by grade level.
IFUP Acc. = Incremental Followup Accuracy, CFUP Acc. = Counterfactual Followup Accuracy, Total FUPs Seen = Number of followup questions a model sees, since a model only sees followups if it answers the main question correctly.

Grade K

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
K.OA.A.4 0.97 - - -
K.NBT.A.1 0.92 - - -
K.OA.A.5 0.90 0.90 0.93 119
K.CC.C.7 0.68 - 0.85 53

Grade 1

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
1.OA.A.2 0.96 0.92 0.93 129
1.OA.A.1 0.94 0.91 0.97 133
1.OA.D.8 0.86 - - -

Grade 2

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
2.NBT.B.7 0.82 0.68 0.86 122
2.MD.B.5 0.93 0.84 0.84 130
2.NBT.B.6 0.80 0.84 0.87 117
2.OA.A.1 0.84 - - -
2.NBT.B.5 0.90 0.89 0.90 121
2.MD.C.8 0.92 0.86 0.95 146

Grade 3

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
3.OA.D.8 0.85 0.84 0.91 107
3.MD.D.8-quadrilateral 0.51 - - -
3.OA.A.4 0.88 - - -
3.MD.D.8-polygon 0.40 - - -
3.MD.D.8-triangle 0.56 - - -
3.NBT.A.2 0.91 0.72 0.86 137
3.OA.A.3 0.92 0.87 0.67 100
3.OA.C.7 0.95 0.85 0.82 123

Grade 4

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
4.NBT.B.4 0.83 0.53 0.85 107
4.OA.B.4 0.19 - - -
4.MD.A.2-decimal 0.61 0.59 0.66 84
4.MD.A.3 0.31 - 0.65 23
4.MD.A.2-fraction 0.27 0.64 0.70 31
4.NBT.B.6 0.20 - 0.50 14
4.NF.A.2 0.54 - 0.73 15
4.NBT.B.5 0.43 - 0.55 40
4.OA.A.3 0.32 0.67 0.71 36

Grade 5

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
5.OA.A.1 0.44 0.27 0.62 45
5.NBT.B.6 0.44 - 0.03 35
5.NF.A.1 0.07 - - -
5.NBT.B.5 0.21 - 0.76 17
5.NF.B.4 0.40 0.40 0.58 34
5.NBT.B.7 0.51 0.24 0.88 71
5.NF.A.2 0.03 - - 3

Grade 6

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
6.EE.B.7 0.77 - - -
6.NS.B.2 0.25 - 0.15 13
6.EE.A.1 0.99 - 1.00 58
6.NS.B.3 0.42 0.57 0.84 48

Grade 7

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
7.NS.A.1-fraction 0.06 1.00 0.50 4
7.NS.A.2 0.14 0.25 0.71 15
7.NS.A.1-decimal 0.80 0.77 0.81 123
7.NS.A.3-fraction 0.02 - 1.00 1
7.NS.A.3-decimal 0.60 0.59 0.85 82

Grade 8

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
8.EE.A.2 0.68 - - -
8.EE.C.8 0.00 - - -
8.EE.C.7 0.34 - - -