Databricks·released 2023-04-111 source
Dolly 2.0-12b benchmark scores: 6 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 6 benchmarks·best result 61.07 on HellaSwag (self-reported)·0 of 6 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| HellaSwag | 61.07accuracy (%) | self-reported· optimizedT1 | 2023-04-11XGen-7B Technical Report |
| PIQA | 50.8accuracy (%) | self-reported· optimizedT1 | 2023-04-11XGen-7B Technical Report |
| Winogrande | 23.6accuracy (%) | self-reported· optimizedT1 | 2023-04-11XGen-7B Technical Report |
| ARC AI2 | 19.47accuracy (%) | self-reported· optimizedT1 | 2023-04-11XGen-7B Technical Report |
| OpenBookQA | 18.93accuracy (%) | self-reported· optimizedT1 | 2023-04-11XGen-7B Technical Report |
| MMLU | 1.6accuracy (%) | self-reported· optimizedT1 | 2023-04-11XGen-7B Technical Report |
Claims drawn from cited facts, not live model generation.
Developed by Databricks, this model is a mid-scale system with 12 billion parameters. Released in 2023, this mid-size scale offers a practical balance between capability and efficiency—more headroom than compact models but less expense than frontier-scale systems.
4 cited facts
This model is scored on 6 tracked benchmarks and currently holds no top score on any of them. Because these results are self-reported and not yet independently confirmed, treat them as claims rather than verified outcomes.
3 cited facts
With an average gap of 56.27 points behind the state-of-the-art leader, this model sits well behind the front of the pack. It holds the top score on none of the tracked benchmarks, reinforcing that it has not yet achieved category leadership.
2 cited facts
2 facts cross-checked across data sources: 2 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: curated_param_counts, epoch_benchmarks
Dolly 2.0-12b is an AI model developed by Databricks, released 2023-04-11. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Dolly 2.0-12b has recorded scores on 6 benchmarks, each shown with its evidence status.
Dolly 2.0-12b has recorded scores on 6 benchmarks — PIQA, OpenBookQA, Winogrande, MMLU, ARC AI2, HellaSwag. The full table above shows each score with its evidence status.
0 of 6 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
Dolly 2.0-12b has 6 tracked claims: 6 self-reported.