GPT-J-6B
GPT-J-6B.
11
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
EleutherAI Aug 2021
GPT-J-6B
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 | |
|---|---|---|---|---|
| WinoGrande | 64.5% | #61 of 76 | Claim in XGen-7B Technical Report, via Epoch AI | |
| HellaSwag | 66.2% | #53 of 63 | Claim in XGen-7B Technical Report, via Epoch AI | |
| BoolQ | 65.4% | #52 of 61 | Claim in XGen-7B Technical Report, via Epoch AI | |
| OpenBookQA | 38.2% | #35 of 41 | Claim in XGen-7B Technical Report, via Epoch AI | |
| PIQA | 75.4% | #51 of 58 | Claim in XGen-7B Technical Report, via Epoch AI | |
| ARC-Challenge | 36.3% | #66 of 75 | Claim in XGen-7B Technical Report, via Epoch AI | |
| MMLU | 25.7% | #84 of 85 | Claim in XGen-7B Technical Report, via Epoch AI | |
| TruthfulQA | 26.7% | #2 of 2 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HumanEval | 12.2% | #45 of 46 | Official leaderboard | |
| HumanEval+ | 11% | #45 of 46 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HELM Classic | 27.3 | #16 of 17 | Official leaderboard |