Updated daily at 05:00 UTC
- Released
- 27 Jan 2022
- Status
- Retired
- Retired
- 4 Jan 2024
- Context
- —
- Max output
- —
- Input per 1M tokens
- $2.00
- Output per 1M tokens
- $2.00
- Open weights
- No
- License
- proprietary
- Parameters
- 6.7B
- Knowledge cutoff
- —
- Reasoning
- No
- Modalities
- text → text
Category scores
Out of 100, from independent and third-party results only, by method category-2026-09-29.1.
Not enough independent results yet
Only independent and third-party results rank a model; self-reported and unattributed numbers never do.
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
Knowledge & reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| HellaSwag | Accuracy | 67.6% | Third party | — | — | Stanford HELM via Epoch AI |
Mathematics
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GSM8K | Exact match | 0.6% | Third party | — | — | Stanford HELM via Epoch AI |
Other GPT-3 versions
- babbage-00222 Aug 2023
- davinci-00222 Aug 2023
- text-ada-001 (InstructGPT)27 Jan 2022
- text-babbage-001 (InstructGPT)27 Jan 2022
- text-davinci-001 (InstructGPT)27 Jan 2022
- GPT-3 ada11 Jun 2020
- GPT-3 babbage11 Jun 2020
- GPT-3 curie11 Jun 2020
- GPT-3 davinci11 Jun 2020