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

MGSM

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical ReasoningMGSM
Accuracy91.7
194
Multilingual Mathematical ReasoningMGSM (test)
Accuracy93.4
57
Multilingual Mathematical ReasoningMGSM
Accuracy94.9
52
Mathematical ReasoningMGSM (test)
Accuracy (MGSM)75.6
49
Multilingual Mathematical ReasoningMGSM 1.0 (test)
Accuracy (ru)69.6
35
Mathematical ReasoningMGSM
Accuracy (Bn)75.7
30
ReasoningMGSM
Accuracy90
24
Multilingual mathematical reasoningMGSM
Speedup (de)6.08
20
Mathematical ReasoningMGSM Rev2
Random Baseline Score74.8
16
Mathematical ReasoningMGSM non-EU languages (test)
Accuracy91.4
16
Mathematical ReasoningMGSM 24 official EU languages
Accuracy93
14
Mathematical ReasoningMGSM Bangla
Accuracy (Original)0.88
13
Machine TranslationMGSM
Bn Score72.89
12
Mathematical ReasoningBn-MGSM (test)
Accuracy89.2
12
Mathematical ReasoningMGSM average (test)
Accuracy84.8
12
Natural Language UnderstandingMGSM
Accuracy6.2
11
MultilingualMGSM
MGSM Score87.47
10
Mathematical ReasoningMGSM-zh (test)
Accuracy79.6
10
Mathematical ReasoningMGSM Basque
Accuracy85.2
8
Mathematical ReasoningMGSM Code Switched P, I - (EN), Q(X) (Avg)
Language Consistency100
8
Mathematical ReasoningMGSM Monolingual P, I, Q - (X) (Avg)
Language Consistency100
8
STEMMGSM Zh
Pass@169.7
6
Multilingual Mathematical ReasoningMGSM 18 languages
Accuracy72.5
6
Mathematical ReasoningMGSM Thai
Score87.6
5
Mathematical ReasoningMGSM Māori
Accuracy41.6
4
Showing 25 of 28 rows