| # | target | instruction | output | task | code | output | result_Claude_2_1_cedar | result_gpt4 | result_capybara | result_llama_2_70b_chat | result_Gemini-1.5-Pro | result_chinchilla |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | {ModifiedText} | Apply a Caesar cipher with a shift of 5 to the following text. Preserve case, and leave non-alphabetic characters unchanged: "{InputText}" | Ymnx nx ozxy f yjxy . Ozxy f yjxy . | Caesar cipher with shift 5 | ModifiedText = ''.join(chr((ord(char) - 65 + 5) % 26 + 65) if char.isupper() else chr((ord(char) - 97 + 5) % 26 + 97) if char.islower() else char for char in InputText) | Ymnx nx ozxy f yjxy . Ozxy f yjxy . | 🟢 Ymnx nx ozxy f yjxy . Ozxy f yjxy . | 🔴 Ymnx nx ozyx f yjxy . Ozyx f yjxy . | 🟢 Ymnx nx ozxy f yjxy . Ozxy f yjxy . | 🔴 Sure! Here's the result of applying a Caesar cipher with a shift of 5 to the given text: ↵ ↵ "Gur... | 🔴 Ymnx nx mjwj f yjxy . Mjwj f yjxy . ↵ | 🟢 Ymnx nx ozxy f yjxy . Ozxy f yjxy . |
| 2 | {InputText} | Convert the following text from its mirror language back to English: "{ModifiedText}" | This is just a test . Just a test . | Convert from Mirror Language | ModifiedText = ''.join(chr(219 - ord(char)) if 'a' <= char <= 'z' else chr(155 - ord(char)) if 'A' <= char <= 'Z' else char for char in InputText) | This is just a test . Just a test . | 🟢 This is just a test. Just a test. | 🔴 This is the high . High the high . | 🔴 This is a mirror language: "This is just a test. Test a is this." | 🔴 Sure, I can help you with that! ↵ ↵ The text you provided is a mirrored version of the following s... | 🔴 This is a test . Test is a this ↵ | 🔴 This is not a valid question as the provided text is not in a mirror language. |
| 3 | {InputText} | Convert the text from mirror language, where each lowercase letter a-z is mirrored across 'm' and 'n'. Uppercase and non-alphabetic characters remain unchanged. Restore the text to English: {ModifiedText} | This is just a test . Just a test . | Convert from Mirror Language | ModifiedText = ''.join(chr(219 - ord(char)) if 'a' <= char <= 'z' else chr(155 - ord(char)) if 'A' <= char <= 'Z' else char for char in InputText) | This is just a test . Just a test . | 🟢 This is just a test . Just a test . | 🔴 This is just a test. Test a test. | 🔴 The text is "This is made by hand. Hand by made." | 🔴 Sure, here's the converted text: ↵ ↵ "Mirror mirror on the wall, who's the fairest of them all?" | 🔴 This is some text. Some is text. ↵ | 🔴 The is calm a calm . Calm a calm . |
| 4 | {InputText} | Convert this Pig Latin text back to English: "{ModifiedText}" | This is just a test . Just a test . | Convert from Pig Latin | ModifiedText = ' '.join(word[-3] + word[:-3] if word.endswith('ay') and len(word) > 2 else word for word in InputText.split()) | This is just a test . Just a test . | 🔴 "isThay isway ustjay away esttay. Ustjay away esttay." | 🟢 This is just a test. Just a test. | 🔴 "This is just a test. Just a test." -> "This is just a test. Just a test." | 🔴 "This is just a test. Just a test." | 🔴 Is response to your message was blocked for potentially violating safety policies. I apologize for... | 🟢 This is just a test. Just a test. |
| 5 | {InputText} | Convert this text from leetspeak to standard English: "{ModifiedText}" | This is just a test . Just a test . | Convert from leetspeak | ModifiedText = InputText.translate(str.maketrans('4310543105', 'AEIOUaeiou')) | This is just a test . Just a test . | 🟢 This is just a test. Just a test. | 🟢 This is just a test. Just a test. | 🟢 This is just a test. Just a test. | 🔴 Sure! Here's the conversion of the text from leetspeak to standard English: ↵ ↵ "This is just a te... | 🟢 This is just a test. Just a test. ↵ | 🟢 This is just a test. Just a test. |
| 6 | {ModifiedText} | Insert 'ithag' after each vowel in the following text: "{InputText}" | Thiithags iithags juithagst aithag teithagst . Juithagst aithag teithagst . | Convert to Gibberish | ModifiedText = ''.join(char + 'ithag' if char in 'aeiou' else char for char in InputText) | Thiithags iithags juithagst aithag teithagst . Juithagst aithag teithagst . | 🔴 Tithagis ithagis jithagust ithaga tithagestitag . Jithagust ithaga tithagestitag . | 🔴 Thithisag isag jusagth tagesthag . Jusagth tag tagesthag . | 🔴 Thithagis ithagjust aga tethagst . Juthagst aga tethagst . | 🔴 Sure, here's the text with "ithag" inserted after each vowel: ↵ ↵ "Thith is jithag a test. Jithag... | 🔴 Thithagis ithagas jithagust agath tithagest . Jithagust agath tithagest . ↵ | 🔴 Thithagis ithagjust a thitagest. Juthagust athagtest. |
| 7 | {ModifiedText} | Convert the following text to its mirror language, where each letter is replaced with its opposite (a<->z, b<->y, etc.): "{InputText}" | Tsrh rh qfhg z gvhg . Jfhg z gvhg . | Convert to Mirror Language | ModifiedText = ''.join(chr(219 - ord(char)) if char.islower() else char for char in InputText) | Tsrh rh qfhg z gvhg . Jfhg z gvhg . | 🔴 "Gsrh rh qfhg z gvhg . Qfhg z gvhg ." | 🔴 Gsrh rh qfhg z gvhg . Qfhg z gvhg . | 🔴 Gsrh rh kzhg z gvhg . Kzhg z gvhg . | 🔴 "Yzbfr qvq va gur bayl punenpgre." | 🔴 Gsrh rh yvxr d wdvg . Yvxr d wdvg . ↵ | 🔴 Gsrh rh kzhgr z gvhg . Kzhgr z gvhg . |
| 8 | {ModifiedText} | Convert this text to leetspeak: "{InputText}" | Th1s 1s j5st 4 t3st . J5st 4 t3st . | Convert to leetspeak | ModifiedText = InputText.translate(str.maketrans('AEIOUaeiou', '4310543105')) | Th1s 1s j5st 4 t3st . J5st 4 t3st . | 🔴 7h15 15 ju57 4 7357 . Ju57 4 7357 . | 🔴 7h15 15 ju57 4 7357. Ju57 4 7357. | 🔴 7|-|15 15 j(_)5+ 4 +35+ . j(_)5+ 4 +35+ . | 🔴 Dis be jus a test . Jus a test . | 🔴 7|-|15 15 Ju57 4 7357 . Ju57 4 7357 . ↵ | 🔴 7h15 15 jU57 4 7357 . jU57 4 7357 . |
| 9 | {ModifiedText} | Convert this text to pig latin: "{InputText}" | hisTay siay ustjay aay esttay . ustJay aay esttay . | Convert to pig latin | ModifiedText = ' '.join([word[1:]+word[0]+'ay' if word[0].isalpha() else word for word in InputText.split()]) | hisTay siay ustjay aay esttay . ustJay aay esttay . | 🔴 isThay isway ustjay away esttay . ustJay away esttay . | 🔴 is-Thay is-jay ust-jay a-way est-tay . ust-Jay a-way est-tay . | 🔴 Isthay isay ustjay aay esttay. Ustjay aay esttay. | 🔴 Iway amway estway ayay tayay. | 🔴 Isthay isay ustjay aay esttay . Ustjay aay esttay . ↵ | 🔴 Isthay isay ustjay aay esttay. Ustjay aay esttay. |
| 10 | {ModifiedText} | Translate the following text into Igpay Atinlay (Pig Latin with 'ay' after each word): "{InputText}" | Thisay isay justay aay testay .ay Justay aay testay .ay | Igpay Atinlay | ModifiedText = ' '.join(w + 'ay' for w in InputText.split()) | Thisay isay justay aay testay .ay Justay aay testay .ay | 🔴 Isthay isay ustjay aay esttay . Ustjay aay esttay . | 🔴 isThay isay ustjay aay esttay . ustJay aay esttay . | 🔴 Histay isay ustjay aay esttay. Ustjay aay esttay. | 🔴 Iway amway estay istay justay aay testay. | 🔴 Is response to your message was blocked for potentially violating safety policies. I apologize for... | 🔴 Isthay isay ustjay aay esttay. Ustjay aay esttay. |
| 11 | {InputText} | Reverse the Caesar cipher with a shift of 5 for the following text: "{ModifiedText}" | This is just a test . Just a test . | Reverse Caesar cipher with shift 5 | shift = -5; alphabet = string.ascii_lowercase; shifted_alphabet = alphabet[shift:] + alphabet[:shift]; table = str.maketrans(shifted_alphabet, alphabet); ModifiedText = InputText.translate(table) | This is just a test . Just a test . | 🔴 Here is the reversed Caesar cipher with a shift of 5: ↵ ↵ This is just a test . Just a test . | 🔴 Opij ij juss a sudd . Euss a sudd . | 🔴 "Only is love a game. Game a game." | 🔴 "Xllx nx ozxy f yjxy . Jzxy f yjxy ." | n/a | 🔴 Plane is just a joke. Joke a joke. |
| 12 | {ModifiedText} | Shift all vowels forward one in the order aeiou (circularly, so 'u' becomes 'a'): "{InputText}" | thos os jast e tist . jast e tist . | Vowel shift | ModifiedText = ''.join('aeiou'[('aeiou'.index(char) + 1) % 5] if char in 'aeiou' else char for char in InputText.lower()) | thos os jast e tist . jast e tist . | 🔴 "Thes es jast i tist . Jast i tist ." | 🔴 Thos os jast e tist . Jast e tist . | 🔴 Thas is jast e tist. Jast e tist. | 🔴 Sure! Here's the shifted sentence: "Ths s jst tst . Jst tst ." | n/a | 🔴 Thas as jist e tist. Jist e tist. |
| # | target | instruction | output | task | code | output | result_Claude_2_1_cedar | result_gpt4 | result_capybara | result_llama_2_70b_chat | result_Gemini-1.5-Pro | result_chinchilla |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | {ModifiedText} | Remove all but the first and last character of each word in this text: "{InputText}" | Ts is jt a tt . Jt a tt . | Remove all but the first and last character of each word | ModifiedText = ' '.join(word[0]+word[-1] if len(word)>1 else word for word in InputText.split()) | Ts is jt a tt . Jt a tt . | 🔴 T s j a t . J a t . | 🔴 T s j t a t . J t a t . | 🔴 Tis s js a tst. Jst a tst. | 🔴 T j t | n/a | 🔴 Ts s jt t . Jt a t . |
| 2 | {ModifiedText} | Remove the last letter from each word in this text: "{InputText}" | Thi i jus tes Jus tes | Remove last letter from each word | ModifiedText = ' '.join(word[:-1] for word in InputText.split()) | Thi i jus tes Jus tes | 🔴 Thi i jus a tes . Jus a tes . | 🔴 Thi i jus a tes . Jus a tes . | 🔴 Thi i jus a tes. Jus a tes. | 🔴 Sure, here's the text with the last letter removed from each word: ↵ ↵ "Ths is jst a tst . Jst a t... | n/a | 🔴 Thi is jus a tes. Jus a tes. |
| 3 | {ModifiedText} | Remove all punctuation from the following text: "{InputText}" | This is just a test Just a test | Remove punctuation | import string;ModifiedText = InputText.translate(str.maketrans('', '', string.punctuation)) | This is just a test Just a test | 🟢 This is just a test Just a test | 🟢 This is just a test Just a test | 🔴 This is just a test Just a test | 🔴 This is just a test Just a test | n/a | 🔴 This is just a test Just a test |
| 4 | {ModifiedText} | Remove all spaces in this text: "{InputText}" | Thisisjustatest.Justatest. | Remove spaces | ModifiedText = InputText.replace(' ', '') | Thisisjustatest.Justatest. | 🔴 "Thisisjustatest.Justatest." | n/a | 🟢 Thisisjustatest.Justatest. | 🔴 "Thisisjustatest.Justatest." | n/a | 🟢 Thisisjustatest.Justatest. |
| 5 | {ModifiedText} | Replace all instances of the character '{Char1}' in the following text with '{Char2}': "{InputText}" | This is just a test . Just a test . | Replace '{Char1}' with '{Char2}' | ModifiedText = InputText.replace(Char1, Char2) | This is just a test . Just a test . | 🟢 This is just a test . Just a test . | n/a | 🔴 "This is just a test . Just a test ." (after replacing 'c' with 'f') | 🔴 "This is just a ftest . Fjust a ftest ." | n/a | 🔴 "This is just a test . Just a test ." |
| 6 | {ModifiedText} | Replace all consonants in the following text with asterisks (*): "{InputText}" | **i* i* *u** a *e** . *u** a *e** . | Replace consonants with '*' | import re;ModifiedText = re.sub(r'[bcçdfghjklłmnñpqrstvwxyzźżšžćčđģķļņŗşţŧŋɲʃʒƒθʝ]', '*', InputText, flags=re.IGNORECASE) | **i* i* *u** a *e** . *u** a *e** . | 🔴 **** ** **** * **** . **** * **** . | n/a | 🔴 Th*s *s j**t * t**t . J**t * t**t . | 🔴 ***** **** ***** | n/a | 🔴 Th*s *s j**t * t**t . J**t * t**t . |
| 7 | {ModifiedText} | Replace all spaces in the following text with underscores: "{InputText}" | This_is_just_a_test_._Just_a_test_. | Replace spaces with underscores | ModifiedText = InputText.replace(' ', '_') | This_is_just_a_test_._Just_a_test_. | 🟢 This_is_just_a_test_._Just_a_test_. | n/a | 🟢 This_is_just_a_test_._Just_a_test_. | 🔴 This_is_just_a_test__Just_a_test__ | n/a | 🟢 This_is_just_a_test_._Just_a_test_. |
| 8 | {ModifiedText} | Replace all vowels in the following text with asterisks (*): "{InputText}" | Th*s *s j*st * t*st . J*st * t*st . | Replace vowels with '*' | import re;ModifiedText = re.sub(r'[aeiouAEIOUáÁéÉíÍóÓúÚàÀèÈìÌòÒùÙâÂêÊîÎôÔûÛäÄëËïÏöÖüÜãÃñÑõÕåÅœŒæÆ]', '*', InputText, flags=re.IGNORECASE) | Th*s *s j*st * t*st . J*st * t*st . | 🟢 Th*s *s j*st * t*st . J*st * t*st . | n/a | 🟢 Th*s *s j*st * t*st. J*st * t*st. | n/a | n/a | 🟢 Th*s *s j*st * t*st. J*st * t*st. |
| 9 | {ModifiedText} | Reverse the character order in every third word of the following text, starting with the first word: "{InputText}" | sihT is just a test . tsuJ a test . | Reverse character order in every third word | ModifiedText = ' '.join(w[::-1] if i%3==0 else w for i,w in enumerate(InputText.split())) | sihT is just a test . tsuJ a test . | 🔴 sihT is tsuj a test . tsuJ a test . | n/a | 🔴 This si just a .tset Just a .tset | n/a | n/a | 🔴 sihT is just a tset . Just a tset . |
| 10 | {ModifiedText} | Reverse character order in every other word in this text, starting with the first word: "{InputText}" | sihT is tsuj a tset . tsuJ a tset . | Reverse every other word | ModifiedText = ' '.join(w[::-1] if i%2==0 else w for i,w in enumerate(InputText.split())) | sihT is tsuj a tset . tsuJ a tset . | 🔴 sihT si tsuj a tset . tsuJ a tset . | n/a | 🔴 sihT is tsuj a tset . Just a tset . | n/a | n/a | 🔴 sihT si just a tset . Just a tset . |
| 11 | {ModifiedText} | Swap the case of all letters in the following text: "{InputText}" | tHIS IS JUST A TEST . jUST A TEST . | Swap case | ModifiedText = InputText.swapcase() | tHIS IS JUST A TEST . jUST A TEST . | 🟢 tHIS IS JUST A TEST . jUST A TEST . | n/a | 🟢 tHIS IS JUST A TEST . jUST A TEST . | n/a | n/a | 🟢 tHIS IS JUST A TEST . jUST A TEST . |
| # | target | instruction | output | task | code | output | result_Claude_2_1_cedar | result_gpt4 | result_capybara | result_llama_2_70b_chat | result_Gemini-1.5-Pro | result_chinchilla |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | {ModifiedText} | Change each letter to alternate case starting with lowercase, shuffle the words, and then reverse the string: "{InputText}" | sIhT . TsUj a sI TsUj . tSeT TsEt a | Alternate case and shuffle words | ModifiedText = ''.join([c.upper() if i % 2 else c.lower() for i, c in enumerate(' '.join(random.sample(InputText.split(), len(InputText.split()))))])[::-1] | sIhT . TsUj a sI TsUj . tSeT TsEt a | 🔴 .tSeT a tSuJ . tSeT a tSuJ sI sIhT | n/a | 🔴 . tseT a tsuJ . .TseT a tsuJ si sihT | n/a | n/a | 🔴 . tseT a tsuj . Tset a tsuj siht |
| 2 | {ModifiedText} | Double each letter in the text and then reverse the entire string: "{InputText}" | .. ttsseett aa ttssuuJJ .. ttsseett aa ttssuujj ssii ssiihhTT | Double each letter and reverse | ModifiedText = ''.join([c * 2 for c in InputText])[::-1] | .. ttsseett aa ttssuuJJ .. ttsseett aa ttssuujj ssii ssiihhTT | 🔴 TThhiiss iiss jjuusstt aa tteesstt .. JJuusstt aa tteesstt .. | n/a | 🔴 . tset a tsuJ . tset a tsuJ . tset a si sihT | n/a | n/a | 🔴 .tset a tsuJ .tset a tsuJ .tset a si sihT |
| 3 | {ModifiedText} | Encode each word in the text as its ASCII value, separated by dashes, then reverse the order of these codes: "{InputText}" | 64-611-511-101-611-79-611-511-711-47-64-611-511-101-611-79-611-511-711-601-511-... | Encode words as ASCII values | ModifiedText = '-'.join(['-'.join(str(ord(c)) for c in word) for word in InputText.split()])[::-1] | 64-611-511-101-611-79-611-511-711-47-64-611-511-101-611-79-611-511-711-601-511-... | 🔴 46-32-97-32-116-115-101-116-32-97-32-116-115-117-74-32-46-32-116-115-101-116-3... | n/a | 🔴 .46-116-115-101-116-32-46-116-115-101-116-32-97-32-116-115-101-116-32-115-105-... | n/a | n/a | 🔴 .46-116-115-101-116-32-46-116-115-101-116-32-97-32-116-115-101-116-32-105-115-... |
| 4 | {ModifiedText} | Extract the initials of each word, concatenate them, and reverse the string: "{InputText}" | .taJ.tajiT | Extract initials and reverse | ModifiedText = ''.join(word[0] for word in InputText.split())[::-1] | .taJ.tajiT | 🔴 .taJ.tsitsiT | n/a | 🔴 siat.Jat | n/a | n/a | 🔴 tijat.Jat. |
| 5 | {ModifiedText} | For each word in the text, interleave it with its reverse and then reverse the entire sentence order: "{InputText}" | .. ttessett aa JtussutJ .. ttessett aa jtussutj issi TshiihsT | Interleave words with their reverse | reversed_interleaved = [''.join(w[i//2] if i % 2 == 0 else w[~(i//2)] for i in range(2*len(w))) for w in InputText.split()]; ModifiedText = ' '.join(reversed_interleaved[::-1]) | .. ttessett aa JtussutJ .. ttessett aa jtussutj issi TshiihsT | 🔴 .tset a tsuJ . tset a tsuj si sihT | n/a | 🔴 . tset a tsuJ . tset a tsuJ . sihT si tsuj a tset . | n/a | n/a | 🔴 . tset a tsuJ . tset a tsuJ . sihT si tsuj a tset . tsuJ a tset . |
| 6 | {ModifiedText} | Remove all but the first and last word of each sentence, then reverse the order of the remaining sentences in this text: "{InputText}" | Just. Thistest | Remove all but the first and last word of each sentence and reverse sentence order | sentences = [sentence.split() for sentence in InputText.split('. ')];ModifiedText = ' '.join(sentence[0]+sentence[-1] for sentence in sentences[::-1]) | Just. Thistest | 🔴 test . ↵ This test | n/a | 🔴 Test. Test. This is. | n/a | n/a | 🔴 Test test. This is. |
| 7 | {ModifiedText} | Remove all but the first letter of each word, then reverse the order of the words in this text: "{InputText}" | . t a J . t a j i T | Remove all but the first letter of each word and reverse word order | ModifiedText = ' '.join(word[0] for word in InputText.split())[::-1] | . t a J . t a j i T | 🔴 . t a J . t a j s T | n/a | 🔴 tijat.jat | n/a | n/a | 🔴 Tijat. Ajt. |
| 8 | {ModifiedText} | Remove all but the last letter of each word, then reverse the resulting string: "{InputText}" | .tat.tatss | Remove all but the last letter of each word and reverse the string | ModifiedText = ''.join(word[-1] for word in InputText.split())[::-1] | .tat.tatss | 🔴 s.tset a tsuJ.tset a tsuj si sihT | n/a | 🔴 s t s e t a . t s e t . | n/a | n/a | 🔴 tseT. a .tseT a .si sihT |
| 9 | {ModifiedText} | Remove all vowels from the text, duplicate the remaining consonants, and then reverse the string: "{InputText}" | .. ttsstt ttssJJ .. ttsstt ttssjj ss sshhTT | Remove vowels and duplicate consonants | ModifiedText = ''.join(c*2 for c in InputText if c.lower() not in 'aeiou')[::-1] | .. ttsstt ttssJJ .. ttsstt ttssjj ss sshhTT | 🔴 Ths s jst tst . Jst tst . ↵ . tst tsstt . tsstt ttsssjj ss sshhtt | n/a | 🔴 tsTtstJsttstJsttst. | n/a | n/a | 🔴 .tsttJssttstJstt |
| 10 | {ModifiedText} | Replace each word in this text with its length, then reverse the resulting string: "{InputText}" | 1414141424 | Replace words with their length and reverse the string | ModifiedText = ''.join(str(len(word)) for word in InputText.split())[::-1] | 1414141424 | 🔴 4 2 4 1 4 1 4 1 4 1 4 1 4 2 4 1 | n/a | 🔴 . 6 . 4 tset a tsuJ . tset a tsuJ . 4 . 2 si sihT | n/a | n/a | 🔴 . . tset a tsuJ . tset a tsuJ si sihT |
| 11 | {ModifiedText} | Reverse the order of words and remove all spaces in this text: "{InputText}" | .testaJust.testajustisThis | Reverse word order and remove spaces | ModifiedText = ''.join(InputText.split()[::-1]) | .testaJust.testajustisThis | 🔴 .test.aJust.testajustisThis | n/a | 🔴 test.a Just test.a is This | n/a | n/a | 🔴 TestatestajustatestjustThis |
| 12 | {ModifiedText} | Scramble the inner letters of each word, leaving the first and last letters intact, then reverse the order of the words: "{InputText}" | . tset a tsuJ . test a tusj si shiT | Scramble inner letters of each word | ModifiedText = ' '.join(w[0] + ''.join(random.sample(w[1:-1], len(w) - 2)) + w[-1] if len(w) > 2 else w for w in InputText.split())[::-1] | . tset a tsuJ . test a tusj si shiT | 🔴 siTh si tjsu a tset . tsuJ a tset . | n/a | 🔴 Hist si tsuj a tset. Tsjut a tset. | n/a | n/a | 🔴 Hist si tsuj a tset. Tsuj a tset. |
| # | target | instruction | output | task | code | output | result_Claude_2_1_cedar | result_gpt4 | result_capybara | result_llama_2_70b_chat | result_Gemini-1.5-Pro | result_chinchilla |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | {InputText} | Add commas back into the following text at appropriate places: "{ModifiedText}" | This is just a test . Just a test . | Add back commas | ModifiedText = InputText.replace(',', '') | This is just a test . Just a test . | 🔴 "This is just a test, . Just a test, ." | n/a | n/a | n/a | n/a | 🔴 This is just a test, just a test. |
| 2 | {InputText} | Vowels have been removed from the following text: "{ModifiedText}". Add back the dropped vowels to restore the complete sentence. | This is just a test . Just a test . | Add back dropped vowels | import re;ModifiedText = re.sub(r'[aeiouAEIOUáÁéÉíÍóÓúÚàÀèÈìÌòÒùÙâÂêÊîÎôÔûÛäÄëËïÏöÖüÜãÃñÑõÕåÅœŒæÆ]', '', InputText) | This is just a test . Just a test . | 🟢 This is just a test. Just a test. | n/a | n/a | n/a | n/a | 🟢 This is just a test. Just a test. |
| 3 | {InputText} | Add spaces back into the following text where they are missing: "{ModifiedText}" | This is just a test . Just a test . | Add back spaces | ModifiedText = InputText.replace(' ', '') | This is just a test . Just a test . | 🟢 This is just a test. Just a test. | n/a | n/a | n/a | n/a | 🟢 This is just a test. Just a test. |
| 4 | {InputText} | All question marks are removed from the following: "{ModifiedText}". Put them back into the text. | This is just a test . Just a test . | Add question marks back into the text | ModifiedText = InputText.replace('?', '') | This is just a test . Just a test . | 🔴 "This is just a test? Just a test?" | n/a | n/a | n/a | n/a | 🔴 "This is just a test? Just a test?" |
| 5 | {InputText} | The words in the following text have been merged into a single block without spaces: "{ModifiedText}". Separate them back into the original sentence. | This is just a test . Just a test . | Add spaces back into the text | ModifiedText = ''.join(InputText.split()) | This is just a test . Just a test . | 🟢 This is just a test. Just a test. | n/a | n/a | n/a | n/a | 🟢 This is just a test. Just a test. |
| 6 | {InputText} | One character in this text has been changed to another character. Identify the change and reconstruct the original sentence: "{ModifiedText}" | This is just a test . Just a test . | Identify changed character | import random; chars = [c for c in InputText if c.isalpha()]; char_to_replace = random.choice(chars); replacement_char = random.choice([c for c in 'abcdefghijklmnopqrstuvwxyz' if c != char_to_replace]); ModifiedText = InputText.replace(char_to_replace, replacement_char, 1) | This is just a test . Just a test . | 🔴 "u" in "jrst" changed to "u". Original: "This is just a test . Just a test ." | n/a | n/a | n/a | n/a | 🔴 Change: "jrst" to "just" ↵ ↵ Reconstructed original sentence: "This is just a test. Just a test." |
| 7 | {InputText} | Reorder the words in the following text to form coherent sentences: "{ModifiedText}" | This is just a test . Just a test . | Reconstruct scrambled sentences | import random;words = InputText.split();random.shuffle(words);ModifiedText = ' '.join(words) | This is just a test . Just a test . | 🟢 This is just a test. Just a test. | n/a | n/a | n/a | n/a | 🔴 This is just a test. |
| 8 | {InputText} | All instances of the letter '{Char1}' have been removed from the following text: "{ModifiedText}". Restore the complete sentence by inserting the letter '{Char1}' back into the correct positions. | This is just a test . Just a test . | Restore missing letters '{Char1}' from words | ModifiedText = InputText.replace('Char1', '') | This is just a test . Just a test . | 🔴 This is just a test case. Just a test case. | n/a | n/a | n/a | n/a | 🔴 "This is just a test. Just a test." |
| 9 | {InputText} | Punctuation has been removed from the following text: "{ModifiedText}". Add the punctuation back into the text where it belongs. | This is just a test . Just a test . | Restore removed punctuation | ModifiedText = InputText.replace('.', '').replace(',', '').replace('?', '') | This is just a test . Just a test . | 🔴 "This is just a test. Just a test." | n/a | n/a | n/a | n/a | 🟢 This is just a test. Just a test. |
| 10 | {InputText} | A word in the following sentence is scrambled: "{ModifiedText}". Identify the scrambled word, unscramble it, and provide the correct sentence. | This is just a test . Just a test . | Unscramble a single word in a sentence | ModifiedText = InputText.replace('word', ''.join(random.sample('word', len('word')))) | This is just a test . Just a test . | 🔴 Sentence: "This is just a test . Just a tset ." ↵ Scrambled word: tset ↵ Unscrambled word: test | n/a | n/a | n/a | n/a | 🔴 Scrambled word: "just" ↵ Unscrambled word: "just" ↵ Correct sentence: "This is just a test. Just a... |
| 11 | {InputText} | Reorder the following scrambled words to form coherent sentences: "{ModifiedText}" | This is just a test . Just a test . | Unscramble words to form sentences | import random;words = InputText.split();random.shuffle(words);ModifiedText = ' '.join(words) | This is just a test . Just a test . | 🟢 This is just a test. Just a test. | n/a | n/a | n/a | n/a | 🔴 This is just a test. |
| # | target | instruction | output | task | code | output | result_Claude_2_1_cedar | result_gpt4 | result_capybara | result_llama_2_70b_chat | result_Gemini-1.5-Pro | result_chinchilla |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | {ModifiedText} | Add a number in parentheses after each word in this text indicating its position: "{InputText}" | This (1) is (2) just (3) a (4) test (5) . (6) Just (7) a (8) test (9) . (10) | Add word numbers | ModifiedText = ' '.join(f'{w} ({i+1})' for i,w in enumerate(InputText.split())) | This (1) is (2) just (3) a (4) test (5) . (6) Just (7) a (8) test (9) . (10) | 🔴 This(1) is(2) just(3) a(4) test(5) .(6) Just(7) a(8) test(9) .(10) | n/a | n/a | n/a | n/a | 🔴 This (1) is (2) just (3) a (4) test (5). Just (6) a (7) test (8). |
| 2 | {ModifiedText} | Count the number of consonants in the following text: "{InputText}" | 16 | Count consonants | ModifiedText = str(sum(c in 'bcdfghjklmnpqrstvwxyz' for c in InputText.lower())) | 16 | 🟢 16 | n/a | n/a | n/a | n/a | 🔴 17 |
| 3 | {ModifiedText} | Count the number of lowercase letters in the following text: "{InputText}" | 22 | Count lowercase letters | ModifiedText = str(sum(1 for c in InputText if c.islower())) | 22 | 🟢 22 | n/a | n/a | n/a | n/a | 🔴 16 |
| 4 | {ModifiedText} | Count the number of unique letters in the following text. Exclude numbers and special characters: "{InputText}" | 8 | Count unique letters | letters = set(InputText.lower()) - set(' 0123456789!@#$%^&*()-+=[]{} | \:;"'<>,.?/'); ModifiedText = str(len(letters)) | 8 | 🔴 10 | n/a | n/a | n/a | n/a |
| 5 | {ModifiedText} | Count the number of uppercase letters in the following text: "{InputText}" | 2 | Count uppercase letters | ModifiedText = str(sum(1 for c in InputText if c.isupper())) | 2 | 🟢 2 | n/a | n/a | n/a | n/a | 🔴 The number of uppercase letters in the given text is 2. |
| 6 | {ModifiedText} | Count the number of vowels in the following text: "{InputText}" | 8 | Count vowels | vowels = 'aeiou'; ModifiedText = str(sum(c in vowels for c in InputText.lower())) | 8 | 🔴 12 | n/a | n/a | n/a | n/a | 🔴 12 |
| 7 | {ModifiedText} | Identify all unique letters used in the following text: "{InputText}" | a.iustjeh | Find unique letters | ModifiedText = ''.join(set(InputText.lower()).difference(' ')) | a.iustjeh | 🔴 t,h,i,s,j,u,a,e,. | n/a | n/a | n/a | n/a | 🔴 T, h, i, s, a, j, u, s, t, e. |
| 8 | {ModifiedText} | Identify the first letter in the following text that does not repeat. If all letters repeat, return an empty response: "{InputText}" | h | First letter not repeating | from collections import Counter;letters = Counter(InputText.replace(' ', '').lower()); ModifiedText = next((letter for letter, count in letters.items() if count == 1), '') | h | 🟢 h | n/a | n/a | n/a | n/a | 🔴 i |
| 9 | {ModifiedText} | Find the last letter that appears more than once in the following text. If no letter repeats, return an empty response: "{InputText}" | . | Last repeating letter | from collections import Counter;letters = Counter(InputText.replace(' ', '').lower()); ModifiedText = next((letter for letter in reversed(InputText.lower()) if letters[letter] > 1), '') | . | 🔴 t | n/a | n/a | n/a | n/a | 🔴 t |
| 10 | {ModifiedText} | Find the first letter that appears exactly 3 times in the following text. Provide the letter. If no letter meets this condition, return an empty response: "{InputText}" | Letter appearing exactly 3 times | from collections import Counter;letters = Counter(InputText.replace(' ', '').lower()); ModifiedText = next((letter for letter, count in letters.items() if count == 3), '') | 🔴 s | n/a | n/a | n/a | n/a | n/a | ||
| 11 | {ModifiedText} | Find how many letters appear exactly 3 times in the following text. Provide the count: "{InputText}" | 0 | Letters appearing 3 times | from collections import Counter;import re;ModifiedText = str(sum(1 for v in Counter(InputText.replace(' ', '').lower()).values() if v == 3)) | 0 | 🔴 3 | n/a | n/a | n/a | n/a | n/a |
| # | target | instruction | output | task | code | output | result_Claude_2_1_cedar | result_gpt4 | result_capybara | result_llama_2_70b_chat | result_Gemini-1.5-Pro | result_chinchilla |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | {ModifiedText} | Add the word 'Note:' to the beginning of each sentence in the following text: "{InputText}" | Note: This is just a test .. Note: Just a test . | Add a specific word to the beginning of each sentence | import re;ModifiedText = '. '.join('Note: ' + s for s in re.split(r'(?<=[.!?]) ', InputText)) | Note: This is just a test .. Note: Just a test . | 🔴 Note: This is just a test. ↵ Note: Just a test. | n/a | n/a | n/a | n/a | n/a |
| 2 | {ModifiedText} | Alternate the case of letters in each sentence starting with uppercase for the first sentence and so on in the following text: "{InputText}" | THIS IS JUST A TEST .. just a test . | Alternate case by sentence | import re;ModifiedText = '. '.join(s.upper() if i % 2 == 0 else s.lower() for i, s in enumerate(re.split(r'(?<=[.!?]) ', InputText))) | THIS IS JUST A TEST .. just a test . | 🔴 ThIs iS JuSt a tEsT . jUsT A TeSt . | n/a | n/a | n/a | n/a | n/a |
| 3 | {ModifiedText} | Concatenate all sentences in reverse order into one continuous text in the following text: "{InputText}" | Just a test . This is just a test . | Concatenate sentences in reverse order | import re;ModifiedText = ' '.join(re.split(r'(?<=[.!?]) ', InputText)[::-1]) | Just a test . This is just a test . | 🔴 .test a Just . test a just is This | n/a | n/a | n/a | n/a | n/a |
| 4 | {ModifiedText} | Number each sentence sequentially starting with 1 in the following text: "{InputText}" | 1. This is just a test .. 2. Just a test . | Number each sentence | import re;ModifiedText = '. '.join(f'{i+1}. {s}' for i, s in enumerate(re.split(r'(?<=[.!?]) ', InputText))) | 1. This is just a test .. 2. Just a test . | 🔴 1. This is just a test. ↵ 2. Just a test. | n/a | n/a | n/a | n/a | n/a |
| 5 | {ModifiedText} | Remove the first and last word from each sentence in this text: "{InputText}" | is just a test a test | Remove first and last word from each sentence | import re;ModifiedText = ' '.join(' '.join(s.split()[1:-1]) for s in re.split(r'(?<=[.!?]) +', InputText)) | is just a test a test | 🔴 is just a test. a test | n/a | n/a | n/a | n/a | n/a |
| 6 | {ModifiedText} | Remove the second and second-to-last word from each sentence in this text: "{InputText}" | This just a . Just . | Remove second and second-to-last word from each sentence | import re;ModifiedText = ' '.join(' '.join(s.split()[0:1] + s.split()[2:-2] + s.split()[-1:]) for s in re.split(r'(?<=[.!?]) +', InputText)) | This just a . Just . | 🔴 "This just a . Just a ." | n/a | n/a | n/a | n/a | n/a |
| 7 | {ModifiedText} | Remove all sentences with 3 words or fewer and 10 words or more from the following text: "{InputText}" | This is just a test . Just a test . | Remove short and long sentences | import re;sentences = re.split(r'(?<=[.!?]) +', InputText);ModifiedText = ' '.join(s for s in sentences if 3 < len(s.split()) < 10) | This is just a test . Just a test . | 🔴 "This is just a test." | n/a | n/a | n/a | n/a | n/a |
| 8 | {ModifiedText} | Reverse the order of characters in each sentence of the following text, while keeping the original sentence order: "{InputText}" | . tset a tsuj si sihT . tset a tsuJ | Reverse character order in each sentence | import re;ModifiedText = ' '.join(s[::-1] for s in re.split(r'(?<=[.!?]) +', InputText)) | . tset a tsuj si sihT . tset a tsuJ | 🔴 .tset a tsuJ . tset a tsuj si sihT | n/a | n/a | n/a | n/a | n/a |
| 9 | {ModifiedText} | Reverse the order of sentences in the following text: "{InputText}" | Just a test . This is just a test . | Reverse sentence order | import re;ModifiedText = ' '.join(re.split(r'(?<=[.!?]) +', InputText)[::-1]) | Just a test . This is just a test . | 🟢 Just a test . This is just a test . | n/a | n/a | n/a | n/a | n/a |
| 10 | {ModifiedText} | Reverse the word order in each sentence of the following text, while keeping the original sentence order: "{InputText}" | . test a just is This . test a Just | Reverse word order in each sentence | import re;ModifiedText = ' '.join(' '.join(s.split()[::-1]) for s in re.split(r'(?<=[.!?]) +', InputText)) | . test a just is This . test a Just | 🔴 . test a Just . test a just is This | n/a | n/a | n/a | n/a | n/a |
| 11 | {ModifiedText} | Sort all the sentences in the following text by their length, from shortest to longest: "{InputText}" | Just a test . This is just a test . | Sort sentences by length | import re;ModifiedText = ' '.join(sorted(re.split(r'(?<=[.!?]) +', InputText), key=len)) | Just a test . This is just a test . | 🔴 1. This is just a test. ↵ 2. Just a test. | n/a | n/a | n/a | n/a | n/a |
| # | target | instruction | output | task | code | output | result_Claude_2_1_cedar | result_gpt4 | result_capybara | result_llama_2_70b_chat | result_Gemini-1.5-Pro | result_chinchilla |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | {ModifiedText} | Count the number of words in this text: "{InputText}" | 10 | Count words | ModifiedText = str(len(InputText.split())) | 10 | 🟢 10 | n/a | n/a | n/a | n/a | n/a |
| 2 | {ModifiedText} | Remove all words with 7 letters or more from the following text: "{InputText}" | This is just a test . Just a test . | Remove long words | ModifiedText = ' '.join(w for w in InputText.split() if len(w) < 7) | This is just a test . Just a test . | 🟢 This is just a test . Just a test . | n/a | n/a | n/a | n/a | n/a |
| 3 | {ModifiedText} | Remove all words with 3 letters or fewer and 7 letters or more from the following text: "{InputText}" | This just test Just test | Remove short and long words | ModifiedText = ' '.join(w for w in InputText.split() if 3 < len(w) < 7) | This just test Just test | 🔴 just test . Just test . | n/a | n/a | n/a | n/a | n/a |
| 4 | {ModifiedText} | Remove all words with 3 letters or fewer from the following text: "{InputText}" | This just test Just test | Remove short words | ModifiedText = ' '.join(w for w in InputText.split() if len(w) > 3) | This just test Just test | 🔴 This just test . Just test . | n/a | n/a | n/a | n/a | n/a |
| 5 | {ModifiedText} | Remove all words with odd length from this text: "{InputText}" | This is just test Just test | Remove words with odd length | ModifiedText = ' '.join(word for word in InputText.split() if len(word) % 2 == 0) | This is just test Just test | 🔴 is a . a . | n/a | n/a | n/a | n/a | n/a |
| 6 | {ModifiedText} | Replace each word with its index in the sentence in this text: "{InputText}" | 0 1 2 3 4 5 6 7 8 9 | Replace words with their index in the sentence | ModifiedText = ' '.join(str(i) for i in range(len(InputText.split()))) | 0 1 2 3 4 5 6 7 8 9 | 🔴 1 2 3 4 5 6 7 8 9 10 11 | n/a | n/a | n/a | n/a | n/a |
| 7 | {ModifiedText} | Replace each word with its last two letters in this text: "{InputText}" | is is st a st . st a st . | Replace words with their last two letters | ModifiedText = ' '.join(word[-2:] for word in InputText.split()) | is is st a st . st a st . | 🔴 is st a st . st a st . | n/a | n/a | n/a | n/a | n/a |
| 8 | {ModifiedText} | Replace each word with its length in this text: "{InputText}" | 4 2 4 1 4 1 4 1 4 1 | Replace words with their length | ModifiedText = ' '.join(str(len(word)) for word in InputText.split()) | 4 2 4 1 4 1 4 1 4 1 | 🔴 4 2 4 1 4 . 4 1 4 . | n/a | n/a | n/a | n/a | n/a |
| 9 | {ModifiedText} | Sort all the words in the following text alphabetically: "{InputText}" | . . Just This a a is just test test | Sort words alphabetically | ModifiedText = ' '.join(sorted(InputText.split())) | . . Just This a a is just test test | 🔴 . ↵ . ↵ a ↵ a ↵ is ↵ just ↵ just ↵ test ↵ test ↵ This | n/a | n/a | n/a | n/a | n/a |
| 10 | {ModifiedText} | Sort all the words in the following text by their length, from shortest to longest: "{InputText}" | a . a . is This just test Just test | Sort words by length | ModifiedText = ' '.join(sorted(InputText.split(), key=len)) | a . a . is This just test Just test | 🔴 a ↵ a ↵ . ↵ . ↵ is ↵ This ↵ just ↵ test ↵ Just ↵ test | n/a | n/a | n/a | n/a | n/a |
| 11 | {ModifiedText} | Sort all the words in the following text by their number of vowels, from least to most: "{InputText}" | . . This is just a test Just a test | Sort words by number of vowels | ModifiedText = ' '.join(sorted(InputText.split(), key=lambda w: sum(c in 'aeiou' for c in w))) | . . This is just a test Just a test | 🔴 a ↵ . ↵ . ↵ is ↵ This ↵ just ↵ test ↵ Just ↵ test | n/a | n/a | n/a | n/a | n/a |
| # | target | instruction | output | task | code | output | result_Claude_2_1_cedar | result_gpt4 | result_capybara | result_llama_2_70b_chat | result_Gemini-1.5-Pro | result_chinchilla |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | {ModifiedText} | Extract all consonants from the following text: "{InputText}" | iiuaeuae | Extract consonants | import re;ModifiedText = ''.join(re.findall(r'[aeiouAEIOUáÁéÉíÍóÓúÚàÀèÈìÌòÒùÙâÂêÊîÎôÔûÛäÄëËïÏöÖüÜãÃñÑõÕåÅœŒæÆ]', InputText, flags=re.IGNORECASE)) | iiuaeuae | 🔴 Thsjsttst.Jstttst. | n/a | n/a | n/a | n/a | n/a |
| 2 | {ModifiedText} | Extract the first word from each sentence in the following text: "{InputText}" | This Just | Extract first word from each sentence | import re; ModifiedText = ' '.join(sentence.split()[0] for sentence in re.split(r'(?<=[.!?]) +', InputText)) | This Just | 🔴 This ↵ Just | n/a | n/a | n/a | n/a | n/a |
| 3 | {ModifiedText} | Extract all unique words from the following text, disregarding case: "{InputText}" | this is just a test . | Extract unique words | words = InputText.lower().split(); ModifiedText = ' '.join(sorted(set(words), key=words.index)) | this is just a test . | 🔴 this ↵ is ↵ just ↵ a ↵ test | n/a | n/a | n/a | n/a | n/a |
| 4 | {ModifiedText} | Extract all vowels from the following text: "{InputText}" | iiuaeuae | Extract vowels | import re;ModifiedText = ''.join(re.findall(r'[aeiouAEIOUáÁéÉíÍóÓúÚàÀèÈìÌòÒùÙâÂêÊîÎôÔûÛäÄëËïÏöÖüÜãÃñÑõÕåÅœŒæÆ]', InputText, flags=re.IGNORECASE)) | iiuaeuae | 🔴 i i u a e . u a e . | n/a | n/a | n/a | n/a | n/a |
| 5 | {ModifiedText} | Identify all words in this text that contain the letter '{Char1}': "{InputText}" | Extract words containing a specific letter | ModifiedText = ' '.join(word for word in InputText.split() if Char1 in word) | 🔴 This ↵ test ↵ test | n/a | n/a | n/a | n/a | n/a | ||
| 6 | {ModifiedText} | Find all words in this text that end with the letter '{Char1}': "{InputText}" | Extract words ending with a specific letter | ModifiedText = ' '.join(word for word in InputText.split() if word.endswith(Char1)) | 🔴 Specific | n/a | n/a | n/a | n/a | n/a | ||
| 7 | {ModifiedText} | Extract all words in this text that are longer than 5 letters: "{InputText}" | Extract words longer than 5 letters | ModifiedText = ' '.join(word for word in InputText.split() if len(word) > 5) | 🔴 Extract | n/a | n/a | n/a | n/a | n/a | ||
| 8 | {ModifiedText} | Extract all words from the following text where the first and last letters are the same: "{InputText}" | test test | Extract words starting and ending with the same letter | ModifiedText = ' '.join(word for word in InputText.split() if word[0].lower() == word[-1].lower() and len(word) > 1) | test test | 🔴 is ↵ a ↵ test ↵ a ↵ test | n/a | n/a | n/a | n/a | n/a |
| 9 | {ModifiedText} | Extract all words from the following text that start with a vowel: "{InputText}" | is a a | Extract words starting with a vowel | ModifiedText = ' '.join(word for word in InputText.split() if word[0].lower() in 'aeiou') | is a a | 🔴 is ↵ a ↵ a | n/a | n/a | n/a | n/a | n/a |
| 10 | {ModifiedText} | Extract all words from the following text that have an even number of characters: "{InputText}" | This is just test Just test | Extract words with even length | ModifiedText = ' '.join(word for word in InputText.split() if len(word) % 2 == 0) | This is just test Just test | 🔴 is ↵ just ↵ test ↵ Just ↵ test | n/a | n/a | n/a | n/a | n/a |
| 11 | {ModifiedText} | Extract all words in this text that do not contain the letter '{Char1}': "{InputText}" | This is just a test . Just a test . | Extract words without the letter 'e' | ModifiedText = ' '.join(word for word in InputText.split() if Char1 not in word.lower()) | This is just a test . Just a test . | 🔴 This ↵ is ↵ just ↵ a ↵ test ↵ . ↵ Just ↵ a ↵ test ↵ . | n/a | n/a | n/a | n/a | n/a |
| # | target | instruction | output | task | code | output | result_Claude_2_1_cedar | result_gpt4 | result_capybara | result_llama_2_70b_chat | result_Gemini-1.5-Pro | result_chinchilla |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | {ModifiedText} | Create an acronym from the following text by taking the first letter of each word and capitalizing it: "{InputText}" | TIJAT.JAT. | Acronymize | ModifiedText = ''.join(w[0].upper() for w in InputText.split()) | TIJAT.JAT. | 🟢 TIJAT.JAT. | n/a | n/a | n/a | n/a | n/a |
| 2 | {ModifiedText} | Make every fourth word bold in this text by using Markdown syntax: "{InputText}" | This is just **a** test . Just **a** test . | Bold every fourth word in Markdown | ModifiedText = ' '.join(''+w+'' if (i+1)%4==0 else w for i, w in enumerate(InputText.split())) | This is just **a** test . Just **a** test . | 🔴 This **is just a** test **. Just a** test **.** | n/a | n/a | n/a | n/a | n/a |
| 3 | {ModifiedText} | Capitalize all words in this text: "{InputText}" | This Is Just A Test . Just A Test . | Capitalize all words | ModifiedText = InputText.title() | This Is Just A Test . Just A Test . | 🔴 "This Is Just A Test . Just A Test ." | n/a | n/a | n/a | n/a | n/a |
| 4 | {ModifiedText} | Capitalize every fourth word in this text, starting with the first word: "{InputText}" | This is just a Test . Just a Test . | Capitalize every fourth word | ModifiedText = ' '.join(w.capitalize() if i%4==0 else w for i,w in enumerate(InputText.split())) | This is just a Test . Just a Test . | 🔴 This is just A test . Just a test . | n/a | n/a | n/a | n/a | n/a |
| 5 | {ModifiedText} | Capitalize every other word in this text, starting with the first word: "{InputText}" | This is Just a Test . Just a Test . | Capitalize every other word | ModifiedText = ' '.join(w.capitalize() if i%2==0 else w for i,w in enumerate(InputText.split())) | This is Just a Test . Just a Test . | 🔴 ThIs iS JuSt a tEsT . jUsT A TeSt . | n/a | n/a | n/a | n/a | n/a |
| 6 | {ModifiedText} | Convert this text to camel case: "{InputText}" | ThisIsJustATest.JustATest. | Convert to camel case | ModifiedText = InputText.title().replace(' ', '') | ThisIsJustATest.JustATest. | 🔴 thisIsJustATest.JustATest. | n/a | n/a | n/a | n/a | n/a |
| 7 | {ModifiedText} | Convert every third word to inline code in Markdown in this text: "{InputText}" | This is `just` a test `.` Just a `test` . | Convert to inline code in Markdown | ModifiedText = ' '.join(''+w+'' if (i+1)%3==0 else w for i, w in enumerate(InputText.split())) |
This is `just` a test `.` Just a `test` . | 🔴 This `is` just a `test` . Just `a` test . | n/a | n/a | n/a | n/a | n/a |
| 8 | {ModifiedText} | Create a Markdown bullet list, where each item is a sentence from the following text: "{InputText}" | * This is just a test .* Just a test . | Create a Markdown bullet list from sentences | import re;ModifiedText = ''.join('* '+s for s in re.split(r'(?<=[.!?]) +', InputText)) | * This is just a test .* Just a test . | 🔴 - This is just a test . ↵ - Just a test . | n/a | n/a | n/a | n/a | n/a |
| 9 | {ModifiedText} | Italicize and bold alternate words in this text using Markdown syntax, starting with italicizing the first word: "{InputText}" | *This* **is** *just* **a** *test* **.** *Just* **a** *test* **.** | Italicize and bold alternate words in Markdown | import re;ModifiedText = ' '.join(''+w+'' if i%2==0 else ''+w+'' for i, w in enumerate(InputText.split())) | *This* **is** *just* **a** *test* **.** *Just* **a** *test* **.** | 🔴 *__This__ is __just__ a __test__ . __Just__ a __test__ .* | n/a | n/a | n/a | n/a | n/a |
| 10 | {ModifiedText} | Italicize every third word in this text by using Markdown syntax: "{InputText}" | This is *just* a test *.* Just a *test* . | Italicize every third word in Markdown | ModifiedText = ' '.join(''+w+'' if (i+1)%3==0 else w for i, w in enumerate(InputText.split())) | This is *just* a test *.* Just a *test* . | 🔴 This *is just a* test . *Just a test* . | n/a | n/a | n/a | n/a | n/a |
| 11 | {ModifiedText} | Strike through every fifth word in this text by using Markdown syntax: "{InputText}" | This is just a |
Strike through every fifth word in Markdown | ModifiedText = ' '.join(' |
This is just a |
🔴 This is |
n/a | n/a | n/a | n/a | n/a |
| # | target | instruction | output | task | code | output | result_Claude_2_1_cedar | result_gpt4 | result_capybara | result_llama_2_70b_chat | result_Gemini-1.5-Pro | result_chinchilla |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | {ModifiedText} | Alternate the casing of words in this text, starting with lowercase: "{InputText}" | this IS just A test . just A test . | Alternate word casing | ModifiedText = ' '.join(w.lower() if i % 2 == 0 else w.upper() for i, w in enumerate(InputText.split())) | this IS just A test . just A test . | 🔴 tHiS Is jUsT A TeSt . jUsT A tEsT . | n/a | n/a | n/a | n/a | n/a |
| 2 | {ModifiedText} | Capitalize every third word in this text, starting with the first word: "{InputText}" | THIS is just A test . JUST a test . | Capitalize every Nth word | ModifiedText = ' '.join(w.upper() if i % 3 == 0 else w for i, w in enumerate(InputText.split())) | THIS is just A test . JUST a test . | 🔴 This is just A test . Just a test . | n/a | n/a | n/a | n/a | n/a |
| 3 | {ModifiedText} | Double each word in the following text: "{InputText}" | ThisThis isis justjust aa testtest .. JustJust aa testtest .. | Double each word | ModifiedText = ' '.join(w+w for w in InputText.split()) | ThisThis isis justjust aa testtest .. JustJust aa testtest .. | 🔴 This This is is just just a a test test . . Just Just a a test test . . | n/a | n/a | n/a | n/a | n/a |
| 4 | {ModifiedText} | Double every vowel in the following text: "{InputText}" | Thiis iis juust aa teest . Juust aa teest . | Double every vowel | ModifiedText = ''.join(c * 2 if c in 'aeiouAEIOU' else c for c in InputText) | Thiis iis juust aa teest . Juust aa teest . | 🔴 "Thiis iis juust aa teest . Juust aa teest ." | n/a | n/a | n/a | n/a | n/a |
| 5 | {ModifiedText} | Remove all but the first and last word from this text: "{InputText}" | This . | Remove all but the first and last word | words = InputText.split();ModifiedText = words[0] + ' ' + words[-1] | This . | 🔴 This test. | n/a | n/a | n/a | n/a | n/a |
| 6 | {ModifiedText} | Remove every other word from the following text, starting with the second word: "{InputText}" | This just test Just test | Remove every other word | ModifiedText = ' '.join(w for i, w in enumerate(InputText.split()) if i % 2 == 0) | This just test Just test | 🔴 This just test a . | n/a | n/a | n/a | n/a | n/a |
| 7 | {ModifiedText} | Remove all words containing '{Char1}' from this text: "{InputText}" | This is just a test . Just a test . | Remove words containing '{Char1}' | ModifiedText = ' '.join(word for word in InputText.split() if 'Char1' not in word) | This is just a test . Just a test . | 🟢 This is just a test . Just a test . | n/a | n/a | n/a | n/a | n/a |
| 8 | {ModifiedText} | Remove all words that are shorter than 4 letters in this text: "{InputText}" | This just test Just test | Remove words shorter than N letters | ModifiedText = ' '.join(w for w in InputText.split() if len(w) >= 4) | This just test Just test | 🔴 This just test. Just test. | n/a | n/a | n/a | n/a | n/a |
| 9 | {ModifiedText} | Replace all vowels in the following text with asterisks: "{InputText}" | Th*s *s j*st * t*st . J*st * t*st . | Replace vowels with '*' | ModifiedText = ''.join('*' if c in 'aeiouAEIOU' else c for c in InputText) | Th*s *s j*st * t*st . J*st * t*st . | 🟢 Th*s *s j*st * t*st . J*st * t*st . | n/a | n/a | n/a | n/a | n/a |
| 10 | {ModifiedText} | Reverse the letters of each word in the following text: "{InputText}" | Reverse each word's letters | ModifiedText = ' '.join(w[::-1] for w in InputText.split()) | n/a | n/a | n/a | n/a | n/a | n/a | ||
| 11 | {ModifiedText} | Reverse the order of letters in every second word in this text: "{InputText}" | Reverse the order of letters in every second word | ModifiedText = ' '.join(w[::-1] if i % 2 else w for i, w in enumerate(InputText.split())) | n/a | n/a | n/a | n/a | n/a | n/a |