MathCAMPS Logo

Llama 3 70B

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 0.95 - - -
K.NBT.A.1 0.96 - - -
K.OA.A.5 0.94 0.98 0.99 123
K.CC.C.7 0.98 - 0.84 98

Grade 1

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
1.OA.A.2 0.97 0.98 0.97 131
1.OA.A.1 0.97 0.98 0.96 136
1.OA.D.8 0.98 - - -

Grade 2

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
2.NBT.B.7 0.99 0.97 0.98 153
2.MD.B.5 0.95 0.85 0.95 144
2.NBT.B.6 0.95 0.91 0.98 140
2.OA.A.1 0.96 - - -
2.NBT.B.5 0.98 0.96 0.98 135
2.MD.C.8 0.99 0.97 0.99 154

Grade 3

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
3.OA.D.8 0.95 0.92 0.94 125
3.MD.D.8-quadrilateral 1.00 - - -
3.OA.A.4 1.00 - - -
3.MD.D.8-polygon 0.92 - - -
3.MD.D.8-triangle 1.00 - - -
3.NBT.A.2 1.00 0.97 0.96 155
3.OA.A.3 0.93 0.97 0.75 104
3.OA.C.7 0.97 0.97 0.84 124

Grade 4

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
4.NBT.B.4 0.95 0.95 0.97 130
4.OA.B.4 0.94 - - -
4.MD.A.2-decimal 0.88 0.91 0.94 117
4.MD.A.3 0.99 - 1.00 85
4.MD.A.2-fraction 0.48 0.67 0.88 59
4.NBT.B.6 0.74 - 0.84 63
4.NF.A.2 0.99 - 0.67 99
4.NBT.B.5 0.93 - 0.80 86
4.OA.A.3 0.78 0.85 0.94 83

Grade 5

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
5.OA.A.1 0.94 0.92 0.72 101
5.NBT.B.6 1.00 - 0.08 75
5.NF.A.1 0.25 0.28 0.74 48
5.NBT.B.5 0.71 - 0.87 63
5.NF.B.4 0.75 0.84 0.86 114
5.NBT.B.7 0.70 0.68 0.97 101
5.NF.A.2 0.62 0.62 0.86 104

Grade 6

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
6.EE.B.7 0.99 - - -
6.NS.B.2 0.88 - 0.09 45
6.EE.A.1 1.00 - 0.99 97
6.NS.B.3 0.60 0.67 0.89 86

Grade 7

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
7.NS.A.1-fraction 0.44 0.41 0.66 82
7.NS.A.2 0.93 0.78 0.90 162
7.NS.A.1-decimal 0.97 1.00 0.97 172
7.NS.A.3-fraction 0.47 0.80 0.84 58
7.NS.A.3-decimal 0.86 0.90 0.97 124

Grade 8

Standard Overall Acc. IFUP Acc. CFUP Acc. Total FUPs
8.EE.A.2 0.99 - - -
8.EE.C.8 0.00 - - -
8.EE.C.7 0.50 - - -