GPT-2 (1.5B)
GPT-2 (1.5B).
9
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
OpenAI Nov 2019
GPT-2 (1.5B)
Open weights
No Epoch Capabilities Index score yet
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 | |
|---|---|---|---|---|
| TruthfulQA | 29.5% | #1 of 2 | Official leaderboard | |
| WinoGrande | 58.3% | #69 of 76 | Collected by Epoch AI, source not named | |
| BoolQ | 61.8% | #57 of 61 | Claim in Textbooks Are All You Need II: phi-1.5 technical report, via Epoch AI | |
| PIQA | 70.5% | #56 of 58 | Claim in Textbooks Are All You Need II: phi-1.5 technical report, via Epoch AI | |
| ARC-Challenge | 25% | #75 of 75 | Claim in Textbooks Are All You Need II: phi-1.5 technical report, via Epoch AI | |
| HellaSwag | 40% | #63 of 63 | Claim in Textbooks Are All You Need II: phi-1.5 technical report, via Epoch AI | |
| OpenBookQA | 22.4% | #41 of 41 | Claim in Textbooks Are All You Need II: phi-1.5 technical report, via Epoch AI |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| METR Time Horizon | 0.1 min | #31 of 31 | Official leaderboard | |
| METR Time Horizon 1.1 | 0.1 min | #26 of 26 | Official leaderboard |