| crass-ai-on-big-bench | Gopher-280B (few-shot, k=5) | #2 | Accuracy: 56.8 |
| memorization-on-big-bench-hindu-knowledge | Gopher-280B (few-shot, k=5) | #2 | Accuracy: 80 |
| word-sense-disambiguation-on-big-bench-anachronisms | Gopher-280B (few-shot, k=5) | #2 | Accuracy: 56.4 |
| common-sense-reasoning-on-big-bench-known-unknowns | Gopher-280B (few-shot, k=5) | #3 | Accuracy: 63.6 |
| common-sense-reasoning-on-big-bench-winowhy | Gopher-280B (few-shot, k=5) | #4 | Accuracy: 56.7 |
| logical-reasoning-on-big-bench-logic-grid-puzzle | Gopher-280B (few-shot, k=5) | #4 | Accuracy: 35.1 |
| logical-reasoning-on-big-bench-reasoning-about-colored-objects | Gopher-280B (few-shot, k=5) | #4 | Accuracy: 49.2 |
| logical-reasoning-on-big-bench-strategyqa | Gopher-280B (few-shot, k=5) | #4 | Accuracy: 61.0 |
| multiple-choice-question-answering-mcqa-on-big-bench-novel-concepts | Gopher-280B (few-shot, k=5) | #4 | Accuracy: 59.1 |
| common-sense-reasoning-on-big-bench-disambiguation-qa | Gopher-280B (few-shot, k=5) | #5 | Accuracy: 45.5 |
| logical-reasoning-on-big-bench-penguins-in-a-table | Gopher-280B (few-shot, k=5) | #5 | Accuracy: 40.6 |
| multiple-choice-question-answering-mcqa-on-big-bench-navigate | Gopher-280B (few-shot, k=5) | #5 | Accuracy: 51.1 |
| common-sense-reasoning-on-big-bench-sports-understanding | Gopher-280B (few-shot, k=5) | #6 | Accuracy: 54.9 |
| question-answering-on-truthfulqa | Gopher 280B (zero-shot, Our Prompt + Choices) | #6 | MC1: 0.295 |
| question-answering-on-truthfulqa | Gopher 7.1 (zero-shot, QA prompts) | #8 | MC1: 0.25 |
| question-answering-on-truthfulqa | Gopher 7.1B (zero-shot, Our Prompt + Choices) | #10 | MC1: 0.23 |
| question-answering-on-truthfulqa | Gopher 1.4 (zero-shot, QA prompts) | #11 | MC1: 0.23 |
| question-answering-on-truthfulqa | Gopher 1.4B (zero-shot, Our Prompt + Choices) | #13 | MC1: 0.217 |
| question-answering-on-truthfulqa | Gopher 280B (zero-shot, QA prompts) | #21 | MC1: 0. 27 |
| common-sense-reasoning-on-big-bench-causal-judgment | Gopher-280B (few-shot, k=5) | #8 | Accuracy: 50.8 |
| sarcasm-detection-on-big-bench-snarks | Gopher-280B (few-shot, k=5) | #8 | Accuracy: 48.3 |
| common-sense-reasoning-on-big-bench-date-understanding | Gopher-280B (few-shot, k=5) | #9 | Accuracy: 44.1 |
| logical-reasoning-on-big-bench-formal-fallacies-syllogisms-negation | Gopher-280B (few-shot, k=5) | #9 | Accuracy: 50.7 |
| logical-reasoning-on-big-bench-temporal-sequences | Gopher-280B (few-shot, k=5) | #9 | Accuracy: 19.0 |
| multiple-choice-question-answering-mcqa-on-big-bench-hyperbaton | Gopher-280B (few-shot, k=5) | #9 | Accuracy: 51.7 |
| multiple-choice-question-answering-mcqa-on-big-bench-movie-recommendation | Gopher-280B (few-shot, k=5) | #9 | Accuracy: 50.5 |
| multiple-choice-question-answering-mcqa-on-big-bench-ruin-names | Gopher-280B (few-shot, k=5) | #9 | Accuracy: 38.6 |
| language-modelling-on-lambada | Gopher 280B (zero-shot) | #16 | Accuracy: 74.5 |
| language-modelling-on-lambada | Gopher 7.1B (zero-shot) | #27 | Accuracy: 68.5 |
| language-modelling-on-lambada | Gopher 1.4B (zero-shot) | #35 | Accuracy: 62.1 |
| language-modelling-on-lambada | Gopher 417M (zero-shot) | #42 | Accuracy: 51.9 |
| language-modelling-on-lambada | Gopher 117M (zero-shot) | #60 | Accuracy: 41.2 |
| language-modelling-on-lambada | Gopher 44M (zero-shot) | #65 | Accuracy: 30.1 |
| question-answering-on-social-iqa | Gopher (zero-shot) | #20 | Accuracy: 50.6 |
| question-answering-on-piqa | Gopher 280B (0-shot) | #41 | Accuracy: 81.8 |
| question-answering-on-boolq | Gopher (zero-shot) | #47 | Accuracy: 79.3 |
| question-answering-on-natural-questions | Gopher (few-shot, k=64) | #48 | EM: 28.2 |
| multi-task-language-understanding-on-mmlu | Gopher 280B (5-shot) | #52 | Average (%): 60.0 |
| multi-task-language-understanding-on-mmlu | Gopher 7.1B (5-shot) | #83 | Average (%): 29.5 |
| multi-task-language-understanding-on-mmlu | Gopher 1.4B (5-shot) | #85 | Average (%): 27.3 |
| multi-task-language-understanding-on-mmlu | Gopher 417M (5-shot) | #86 | Average (%): 25.7 |
| common-sense-reasoning-on-winogrande | Gopher 280B (0-shot) | #79 | Accuracy: 70.1 |
| sentence-completion-on-hellaswag | Gopher 280B (0-shot) | #79 | Accuracy: 79.2 |