Stability AI·released 2023-04-191 source
stablelm-tuned-alpha-7b benchmark scores: 5 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 5 benchmarks·best result 31.6 on PIQA (self-reported)·0 of 5 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| PIQA | 31.6accuracy (%) | self-reported· optimizedT1 | 2023-04-19XGen-7B Technical Report |
| HellaSwag | 20.93accuracy (%) | self-reported· optimizedT1 | 2023-04-19XGen-7B Technical Report |
| OpenBookQA | 9.87accuracy (%) | self-reported· optimizedT1 | 2023-04-19XGen-7B Technical Report |
| Winogrande | 3accuracy (%) | self-reported· optimizedT1 | 2023-04-19XGen-7B Technical Report |
| ARC AI2 | 2.67accuracy (%) | self-reported· optimizedT1 | 2023-04-19XGen-7B Technical Report |
Claims drawn from cited facts, not live model generation.
Developed by Stability AI and released in 2023, this model is a compact 7-billion-parameter system, a scale that favors efficiency and lower deployment cost over the extra capability headroom of larger models.
3 cited facts
This model is scored on 5 tracked benchmarks and currently holds no top score on any of them. Because the record is self-reported, treat these figures as vendor claims rather than independently verified results.
3 cited facts
With an average gap of 72.18 points behind the state of the art on its benchmarks, this model sits well behind the leaders. It holds the top score on none of those benchmarks, so there is no category leadership yet.
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
stablelm-tuned-alpha-7b is an AI model developed by Stability AI, released 2023-04-19. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
stablelm-tuned-alpha-7b has recorded scores on 5 benchmarks, each shown with its evidence status.
stablelm-tuned-alpha-7b has recorded scores on 5 benchmarks — PIQA, OpenBookQA, Winogrande, ARC AI2, HellaSwag. The full table above shows each score with its evidence status.
0 of 5 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
stablelm-tuned-alpha-7b has 5 tracked claims: 5 self-reported.