InstructGPT 175B
InstructGPT 175B places in the top three on LAMBADA.
OpenAI Released 27 Jan 2022
13
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
OpenAI Jan 2022
InstructGPT 175B
Closed weights
No Epoch Capabilities Index score yet
- ANLI 35.4% #11 /11
- CommonsenseQA 2.0 52.9% #5 /6
- LAMBADA 86.4% #2 /26
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LAMBADA | 86.4% | #2 of 26 | Epoch AI | |
| OpenBookQA | 65.4% | #11 of 41 | Epoch AI | |
| WinoGrande | 77.7% | #25 of 76 | Epoch AI | |
| PIQA | 82.3% | #20 of 58 | Epoch AI | |
| HellaSwag | 79.3% | #28 of 74 | Epoch AI | |
| ARC-Challenge | 53.2% | #41 of 75 | Epoch AI | |
| BoolQ | 77.5% | #44 of 75 | Epoch AI | |
| TriviaQA | 71.2% | #28 of 38 | Epoch AI | |
| CommonsenseQA 2.0 | 52.9% | #5 of 6 | Epoch AI | |
| MMLU | 43.9% | #106 of 127 | Epoch AI | |
| SuperGLUE | 71.8% | #7 of 8 | Epoch AI | |
| ANLI | 35.4% | #11 of 11 | Epoch AI |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ScienceQA | 74% | #6 of 23 | Epoch AI |