| machine-translation-on-wmt2016-german-english | FLAN 137B (few-shot, k=11) | #1 | BLEU score: 40.7 |
| machine-translation-on-wmt2016-german-english | FLAN 137B (zero-shot) | #2 | BLEU score: 38.9 |
| question-answering-on-naturalqa | FLAN 137B (zero-shot) | #1 | EM: 20.7 |
| question-answering-on-obqa | FLAN 137B (zero-shot) | #1 | Accuracy: 78.4 |
| question-answering-on-obqa | FLAN 137B (few-shot, k=16) | #2 | Accuracy: 78.2 |
| machine-translation-on-wmt2016-romanian-english | FLAN 137B (few-shot, k=9) | #2 | BLEU score: 38.1 |
| machine-translation-on-wmt2016-romanian-english | FLAN 137B (zero-shot) | #3 | BLEU score: 37.3 |
| question-answering-on-storycloze | FLAN 137B (few-shot, k=10) | #3 | Accuracy: 94.7 |
| question-answering-on-storycloze | FLAN 137B (zero-shot) | #5 | Accuracy: 93.4 |
| machine-translation-on-wmt2016-english-german | FLAN 137B (zero-shot) | #4 | BLEU score: 27.0 |
| machine-translation-on-wmt2016-english-german | FLAN 137B (few-shot, k=11) | #6 | BLEU score: 26.1 |
| common-sense-reasoning-on-record | FLAN 137B (prompt-tuned) | #8 | EM: 85.1 |
| common-sense-reasoning-on-record | FLAN 137B (zero-shot) | #11 | EM: 72.5 |
| question-answering-on-copa | FLAN 137B (prompt-tuned) | #8 | Accuracy: 94 |
| question-answering-on-copa | FLAN 137B (zero-shot) | #12 | Accuracy: 91 |
| question-answering-on-copa | FLAN 137B (few-shot, k=16) | #21 | Accuracy: 87 |
| question-answering-on-multirc | FLAN 137B (prompt-tuned) | #9 | F1: 83.4 |
| question-answering-on-multirc | FLAN 137B (zero-shot) | #10 | F1: 77.5 |
| question-answering-on-multirc | FLAN 137B (1-shot) | #12 | F1: 72.1 |
| natural-language-inference-on-rte | FLAN 137B (prompt-tuned) | #11 | Accuracy: 91.7% |
| natural-language-inference-on-rte | FLAN 137B (8-shot) | #27 | Accuracy: 84.5% |
| natural-language-inference-on-rte | FLAN 137B (0-shot) | #28 | Accuracy: 84.1% |
| common-sense-reasoning-on-arc-challenge | FLAN 137B (few-shot, k=13) | #12 | Accuracy: 63.8 |
| common-sense-reasoning-on-arc-challenge | FLAN 137B (zero-shot) | #13 | Accuracy: 63.1 |
| coreference-resolution-on-winograd-schema-challenge | FLAN 137B (prompt-tuned) | #13 | Accuracy: 86.5 |
| coreference-resolution-on-winograd-schema-challenge | FLAN 137B (zero-shot) | #17 | Accuracy: 80.8 |
| natural-language-inference-on-wnli | FLAN 137B (zero-shot) | #14 | Accuracy: 74.6 |
| natural-language-inference-on-wnli | FLAN 137B (few-shot, k=4) | #17 | Accuracy: 70.4 |
| question-answering-on-boolq | FLAN 137B (prompt-tuned) | #17 | Accuracy: 86.3 |
| question-answering-on-boolq | FLAN 137B (4-shot) | #27 | Accuracy: 84.6 |
| question-answering-on-boolq | FLAN 137B (0-shot) | #36 | Accuracy: 82.9 |
| sentiment-analysis-on-imdb | FLAN 137B (few-shot, k=2) | #17 | Accuracy: 95 |
| sentiment-analysis-on-imdb | FLAN 137B (zero-shot) | #21 | Accuracy: 94.3 |
| machine-translation-on-wmt2016-english-romanian | FLAN 137B (few-shot, k=9) | #18 | BLEU score: 20.5 |
| machine-translation-on-wmt2016-english-romanian | FLAN 137B (zero-shot) | #19 | BLEU score: 18.9 |
| common-sense-reasoning-on-arc-easy | FLAN 137B (few-shot, k=14) | #21 | Accuracy: 80.7 |
| common-sense-reasoning-on-arc-easy | FLAN 137B (0-shot) | #25 | Accuracy: 79.6 |
| question-answering-on-triviaqa | FLAN 137B (zero-shot) | #32 | EM: 56.7 |
| question-answering-on-piqa | FLAN 137B (few-shot, k=10) | #44 | Accuracy: 81.7 |
| question-answering-on-piqa | FLAN 137B (0-shot) | #57 | Accuracy: 80.5 |
| machine-translation-on-wmt2014-english-french | FLAN 137B (zero-shot) | #46 | BLEU score: 33.9 |
| machine-translation-on-wmt2014-english-french | FLAN 137B (few-shot, k=9) | #47 | BLEU score: 33.8 |
| common-sense-reasoning-on-winogrande | FLAN 137B (few-shot, k=16) | #67 | Accuracy: 72.8 |
| common-sense-reasoning-on-winogrande | FLAN 137B (0-shot) | #73 | Accuracy: 71.2 |
| sentence-completion-on-hellaswag | FLAN 137B (3-shot) | #153 | Accuracy: 59.2 |
| sentence-completion-on-hellaswag | FLAN 137B (0-shot) | #161 | Accuracy: 56.7 |