MathCAMPS Logo

Mistral 7B

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 0.96 - - -
K.NBT.A.1 0.90 - - -
K.OA.A.5 0.87 0.90 0.99 116
K.CC.C.7 0.81 - 0.86 81

Grade 1

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
1.OA.A.2 0.94 0.93 0.97 126
1.OA.A.1 0.92 0.94 0.92 130
1.OA.D.8 0.95 - - -

Grade 2

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
2.NBT.B.7 0.91 0.59 0.87 139
2.MD.B.5 0.92 0.77 0.89 142
2.NBT.B.6 0.80 0.80 0.91 120
2.OA.A.1 0.94 - - -
2.NBT.B.5 0.95 0.90 0.99 132
2.MD.C.8 0.93 0.79 0.94 147

Grade 3

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
3.OA.D.8 0.92 0.84 0.94 122
3.MD.D.8-quadrilateral 0.85 - - -
3.OA.A.4 0.91 - - -
3.MD.D.8-polygon 0.59 - - -
3.MD.D.8-triangle 0.73 - - -
3.NBT.A.2 0.98 0.69 0.86 151
3.OA.A.3 0.88 0.97 0.71 99
3.OA.C.7 0.90 0.92 0.79 116

Grade 4

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
4.NBT.B.4 0.90 0.74 0.90 119
4.OA.B.4 0.56 - - -
4.MD.A.2-decimal 0.70 0.66 0.83 94
4.MD.A.3 0.51 - 0.76 41
4.MD.A.2-fraction 0.29 0.67 0.70 35
4.NBT.B.6 0.46 - 0.53 38
4.NF.A.2 0.77 - 0.75 77
4.NBT.B.5 0.77 - 0.71 73
4.OA.A.3 0.54 0.90 0.76 65

Grade 5

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
5.OA.A.1 0.59 0.50 0.73 63
5.NBT.B.6 0.60 - 0.06 50
5.NF.A.1 0.07 0.14 0.43 14
5.NBT.B.5 0.41 1.00 0.86 36
5.NF.B.4 0.55 0.54 0.72 84
5.NBT.B.7 0.56 0.47 0.83 81
5.NF.A.2 0.18 - 0.41 26

Grade 6

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
6.EE.B.7 0.86 - - -
6.NS.B.2 0.37 - 0.16 19
6.EE.A.1 0.98 - 0.92 95
6.NS.B.3 0.42 0.32 0.94 59

Grade 7

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
7.NS.A.1-fraction 0.07 0.17 0.71 13
7.NS.A.2 0.38 0.46 0.59 71
7.NS.A.1-decimal 0.91 0.59 0.81 160
7.NS.A.3-fraction 0.09 - 0.57 10
7.NS.A.3-decimal 0.79 0.80 0.89 116

Grade 8

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
8.EE.A.2 0.83 - - -
8.EE.C.8 0.00 - - -
8.EE.C.7 0.43 - - -