Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MultiArith

Benchmarks

Task NameDataset NameSOTA ResultTrend
Arithmetic ReasoningMultiArith
Accuracy100
324
Mathematical ReasoningMultiArith
Accuracy100
143
Arithmetic ReasoningMultiArith (test)
Accuracy99.5
136
Math ReasoningMultiArith
Accuracy98.3
65
Math reasoningMultiArith (test)
Accuracy99.59
54
Mathematical ReasoningMultiArith
Original Accuracy99
40
Mathematical ReasoningMultiArith
Accuracy97.18
33
Mathematical reasoningMultiArith Out of Distribution
Top-1 Accuracy (Maj@1)100
30
Math ReasoningMultiArith
Accuracy99.3
29
Group Collusive Attack DetectionMultiArith
Detection Accuracy92
27
Question AnsweringMultiArith
Accuracy74.3
24
mathematical reasoningMultiArith
Accuracy99.15
19
Mathematical ReasoningMultiArith
Pass@1100
18
Arithmetic ReasoningMultiArith
Accuracy98.5
16
Mathematical ReasoningMultiArith
Accuracy100
16
Mathematical ReasoningMultiArith
Accuracy95
15
Follow-up Questioning ConsistencyMultiArith (unseen)
Average Success Count18.33
12
Mathematical ReasoningMultiArith
Accuracy43.33
10
Mathematical ReasoningMultiArith
Accuracy (Clean)99.44
8
Mathematical ReasoningMultiArith (val)
Tokens at Best Step (K)1,640
7
Arithmetic ReasoningMultiArith
Source Library Accuracy99.64
5
Mathematical ReasoningMultiArith
Pass@1 Rate82.5
5
Arithmetic ReasoningMultiArith-100 (pilot)
Accuracy100
3
Arithmetic ReasoningMultiArith numeric-remapping (attack set)
Accuracy100
3
Arithmetic ReasoningMultiArith baseline original
Correct Count593
3
Showing 25 of 29 rows