Neo-6B (QA + WS)
Reported on 6 benchmarks across 2 tasks · 1 paper · 1 SOTA
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Natural Language Processing6 results
- Accuracy· 2022-10-05SOTA87.8
- Accuracy· 2022-10-0584best: 100 (PaLM 540B (finetuned) )
- EM· 2022-10-0519.6best: 64 (Atlas (full, Wiki-dec-2018 index))
- F1· 2022-10-0563.8best: 90.1 (PaLM 540B (finetuned) )
- Accuracy· 2022-10-0567.2best: 99.87 (Mistral-Nemo 12B (HPT))
- Accuracy· 2022-10-0577.9best: 100 (PaLM 540B (fine-tuned))