OpenAIInstructGPT 175B
InstructGPT 175B is an OpenAI proprietary model, released 27 Jan 2022. It is not yet ranked: no independent benchmark results so far, only pricing and metadata.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- –
- Released
- 27 Jan 2022
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source |
|---|---|---|
| HellaSwagnot in index | 79.3%#28 | Epoch AI Benchmarking Hub |
| WinoGrandenot in index | 77.7%#24 | Epoch AI Benchmarking Hub |
| ARC (AI2 Challenge)not in index | 53.2%#42 | Epoch AI Benchmarking Hub |
| PIQAnot in index | 82.3%#20 | Epoch AI Benchmarking Hub |
| SuperGLUEnot in index | 71.8%#7 | Epoch AI Benchmarking Hub |
| ANLInot in index | 35.4%#11 | Epoch AI Benchmarking Hub |
| CommonsenseQA 2not in index | 52.9%#5 | Epoch AI Benchmarking Hub |
Knowledge
| Benchmark | not stated | Source |
|---|---|---|
| MMLUnot in index | 43.9%#100 | Epoch AI Benchmarking Hub |
| TriviaQAnot in index | 71.2%#28 | Epoch AI Benchmarking Hub |
| OpenBookQAnot in index | 65.4%#11 | Epoch AI Benchmarking Hub |
| LAMBADAnot in index | 86.4%#2 | Epoch AI Benchmarking Hub |
Multimodal
| Benchmark | not stated | Source |
|---|---|---|
| ScienceQAnot in index | 74.0%#6 | Epoch AI Benchmarking Hub |
See also
Data as of 19 Sept 2026. Compare with another model.
Cite as: BenchLeader, “InstructGPT 175B: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/text-davinci-001, data as of 19 Sept 2026.