Dolly 2.0-12b
Dolly 2.0-12b.
9
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Databricks Apr 2023 Dolly 2.0-12b
Open weights
55.8
#255 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 | |
|---|---|---|---|---|
| FActScore precision | 21.7% | #1 of 2 | Official leaderboard | |
| HellaSwag | 70.8% | #46 of 63 | Claim in XGen-7B Technical Report, via Epoch AI | |
| OpenBookQA | 39.2% | #32 of 41 | Claim in XGen-7B Technical Report, via Epoch AI | |
| ARC-Challenge | 39.6% | #60 of 75 | Claim in XGen-7B Technical Report, via Epoch AI | |
| WinoGrande | 61.8% | #65 of 76 | Claim in XGen-7B Technical Report, via Epoch AI | |
| PIQA | 75.4% | #52 of 58 | Claim in XGen-7B Technical Report, via Epoch AI | |
| MMLU | 26.2% | #82 of 85 | Claim in XGen-7B Technical Report, via Epoch AI | |
| LMArena (Elo) | 983 | #333 of 335 | Official leaderboard | |
| BoolQ | 56.3% | #61 of 61 | Claim in XGen-7B Technical Report, via Epoch AI |
Databricks's models over time
Databricks'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)