# openai/gpt-3

GPT-3: Language Models are Few-Shot Learners

Repository: https://github.com/openai/gpt-3
Canonical: https://ross.abutalabs.com/products/gpt-3
Homepage: https://arxiv.org/abs/2005.14165
License Family: other
Archived: true
Last push: 2020-09-18T22:06:11+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2298, "days_push": 2175, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 15718, forks 2244 (observed 2026-08-28T04:11:13.897689+00:00)

## What it is
The official OpenAI repository accompanying the GPT-3 paper 'Language Models are Few-Shot Learners', containing sample generations, synthetic task datasets, dataset statistics, and the model card. It is a research artifact rather than usable code, as the model weights and training code are not included.

## Use cases
- read the GPT-3 paper and understand few-shot learning
- find sample outputs from the 175B parameter model
- get synthetic word scramble and arithmetic datasets from the paper
- access the official GPT-3 model card
- study training dataset statistics and benchmark overlap

## When to choose
- you want the official artifacts, samples, and model card from the GPT-3 paper
- you need the synthetic datasets for the word scramble and arithmetic tasks
- you are researching few-shot learning in large language models

## When to avoid
- you want to run or fine-tune GPT-3 yourself - no code or weights are provided
- you need a maintained library or API client for using GPT models
- you want up-to-date model information

## Facets
- artifact type: dataset
- maturity: abandoned
- function: machine-learning, nlp, llm-training, data-generation
- domain: large-language-models, artificial-intelligence, tutorials
- platform: python
- tags: gpt-3, research-paper, few-shot-learning, language-models, openai, samples, model-card, natural-language-processing

## Member repositories
- openai/gpt-3 (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:13.897689+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:05:34.032356+00:00, confidence not recorded.
  - readme: https://github.com/openai/gpt-3 (fetched 2026-08-28T04:11:13.897689+00:00, sha e45e9c783b76)
  - homepage: https://arxiv.org/abs/2005.14165 (fetched 2026-08-29T08:03:54.509757+00:00, sha c2543a1f3688)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T08:03:54.522553+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T08:03:54.527332+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T08:03:54.529188+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T08:03:54.525608+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.