XGen-7B
XGen-7B.
7
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
XGen-7B
Open weights
70.6
#247 of 256
Epoch Capabilities Index
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 | |
|---|---|---|---|---|
| HellaSwag | 74.2% | #41 of 63 | Claim in XGen-7B Technical Report, via Epoch AI | |
| OpenBookQA | 40.2% | #29 of 41 | Claim in XGen-7B Technical Report, via Epoch AI | |
| BoolQ | 74.3% | #45 of 61 | Claim in XGen-7B Technical Report, via Epoch AI | |
| ARC-Challenge | 41.2% | #58 of 75 | Claim in XGen-7B Technical Report, via Epoch AI | |
| WinoGrande | 64.9% | #59 of 76 | Claim in XGen-7B Technical Report, via Epoch AI | |
| PIQA | 75.5% | #50 of 58 | Claim in XGen-7B Technical Report, via Epoch AI | |
| MMLU | 36.3% | #74 of 85 | Claim in XGen-7B Technical Report, via Epoch AI |
Salesforce's models over time
Salesforce's models in color, against every other model on the Epoch Capabilities Index, by release date.
Source: Epoch Capabilities Index, Epoch AI (CC BY 4.0)