Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Instruction Induction

Benchmarks

Task NameDataset NameSOTA ResultTrend
Instruction InductionInstruction Induction
Avg Execution Score38.7
17
Instruction InductionInstruction Induction (test)
Active to Passive100
10
Instruction InductionInstruction Induction 1.0 (test)
Active to Passive100
9
Instruction InductionInstruction Induction (test)
Antonyms0.852
6
14-task averageInstruction Induction (test)
Mean Score69.95
4
word_in_contextInstruction Induction word_in_context (test)
Mean Accuracy61
4
translation_en-frInstruction Induction translation_en-fr (test)
Mean Score81.8
4
translation_en-esInstruction Induction translation_en-es (test)
Mean Score85.4
4
translation_en-deInstruction Induction translation_en-de (test)
Average Score85
4
taxonomy_animalInstruction Induction taxonomy_animal (test)
Mean Accuracy89
4
synonymsInstruction Induction synonyms (test)
Mean Score27.8
4
sentimentInstruction Induction sentiment (test)
Mean Accuracy88.8
4
sentence_similarityInstruction Induction sentence_similarity (test)
Mean Score22.2
4
second_word_letterInstruction Induction second_word_letter (test)
Mean Accuracy94.2
4
rhymesInstruction Induction rhymes (test)
Mean Score65
4
orthography_starts_withInstruction Induction orthography_starts_with (test)
Mean Accuracy0.686
4
negationInstruction Induction negation (test)
Mean Score78.2
4
informal_to_formalInstruction Induction informal_to_formal (test)
Mean Score61.26
4
antonymsInstruction Induction antonyms (test)
Mean Score78.8
4
Showing 19 of 19 rows