Together AI·released 2023-05-041 source
RedPajama-INCITE-7B-Base 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 60.4 on HellaSwag (self-reported)·0 of 6 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| HellaSwag | 60.4accuracy (%) | self-reported· optimizedT1 | 2023-05-04XGen-7B Technical Report |
| PIQA | 53.8accuracy (%) | self-reported· optimizedT1 | 2023-05-04XGen-7B Technical Report |
| Winogrande | 27.6accuracy (%) | self-reported· optimizedT1 | 2023-05-04XGen-7B Technical Report |
| OpenBookQA | 20accuracy (%) | self-reported· optimizedT1 | 2023-05-04XGen-7B Technical Report |
| ARC AI2 | 18.8accuracy (%) | self-reported· optimizedT1 | 2023-05-04XGen-7B Technical Report |
| MMLU | 1.73accuracy (%) | self-reported· optimizedT1 | 2023-05-04XGen-7B Technical Report |
Claims drawn from cited facts, not live model generation.
Developed by Together AI, this model is a mid-size, 7-billion-parameter system released in 2023. Its mid-size scale balances efficiency and lower cost while offering less headroom than a frontier-scale model.
4 cited facts
This model is tracked on 6 benchmarks and currently holds no top score on any of them. The record is self-reported: the figures come from the vendor and have not been independently confirmed, so they should be read as claims rather than verified results.
3 cited facts
On average, this model trails the SOTA leader by 55.13 points on the disclosed harness, a wide gap that places it well behind the front of the pack. It holds the top score on none of the tracked benchmarks (0), confirming 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
RedPajama-INCITE-7B-Base is an AI model developed by Together AI, released 2023-05-04. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
RedPajama-INCITE-7B-Base has recorded scores on 6 benchmarks, each shown with its evidence status.
RedPajama-INCITE-7B-Base 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.
RedPajama-INCITE-7B-Base has 6 tracked claims: 6 self-reported.