Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/GAL 120B

GAL 120B

Reported on 35 benchmarks across 7 tasks · 1 paper · 8 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical14 results

Protein Structure PredictiononCASPSeq
Validation perplexity· 2022-11-16
17.26
SOTA
Galactica: A Large Language Model for Science arXiv:2211.09085
Protein Structure PredictiononUniProtSeq
Validation perplexity· 2022-11-16
5.54
SOTA
Galactica: A Large Language Model for Science arXiv:2211.09085
Protein Structure PredictiononPaenSeq
Validation perplexity· 2022-11-16
3.14
SOTA
Galactica: A Large Language Model for Science arXiv:2211.09085
Protein Structure PredictiononCASPSimSeq
Validation perplexity· 2022-11-16
12.77
SOTA
Galactica: A Large Language Model for Science arXiv:2211.09085
Protein Function PredictiononUniProtSeq
ROUGE-L· 2022-11-16
0.252
SOTA
Galactica: A Large Language Model for Science arXiv:2211.09085
Protein Function PredictiononCASPSimSeq
ROUGE-L· 2022-11-16
0.252
SOTA
Galactica: A Large Language Model for Science arXiv:2211.09085
Protein Function PredictiononPaenSeq
ROUGE-L· 2022-11-16
0.272
SOTA
Galactica: A Large Language Model for Science arXiv:2211.09085
Atomistic Descriptiononclintox
Molecules (M)· 2022-11-16
2
best: 77 (ChemBERTa-2 (MTR-77M))
Galactica: A Large Language Model for Science arXiv:2211.09085
Atomistic Descriptiononclintox
ROC-AUC· 2022-11-16
82.6
best: 99.2 (Deep-CBN)
Galactica: A Large Language Model for Science arXiv:2211.09085
Atomistic DescriptiononBBBP
ROC-AUC· 2022-11-16
66.1
best: 96.4 (DumplingGNN)
Galactica: A Large Language Model for Science arXiv:2211.09085
Atomistic DescriptiononHIV dataset
AUC· 2022-11-16
0.745
best: 0.81 (DVMP)
Galactica: A Large Language Model for Science arXiv:2211.09085
Atomistic DescriptiononSIDER
ROC-AUC· 2022-11-16
63.2
best: 91.11 (BioAct-Het)
Galactica: A Large Language Model for Science arXiv:2211.09085
Atomistic DescriptiononTox21
ROC-AUC· 2022-11-16
68.9
best: 92.4 (Deep-CBN)
Galactica: A Large Language Model for Science arXiv:2211.09085
Atomistic DescriptiononBACE
ROC-AUC· 2022-11-16
61.7
best: 88.4 (MolXPT)
Galactica: A Large Language Model for Science arXiv:2211.09085

Natural Language Processing14 results

Stereotypical Bias AnalysisonCrowS-Pairs
Age· 2022-11-16
69
best: 70.1 (LLaMA 65B)
SOTA
Galactica: A Large Language Model for Science arXiv:2211.09085
Question AnsweringonTruthfulQA
MC1· 2022-11-16
0.26
best: 0.59 (GPT-4 (RLHF))
Galactica: A Large Language Model for Science arXiv:2211.09085
Bias DetectiononStereoSet
ICAT Score· 2022-11-16
65.6
best: 72.97 (GPT-2 (small))
Galactica: A Large Language Model for Science arXiv:2211.09085
Bias DetectiononStereoSet
LMS· 2022-11-16
75
best: 77.6 (GPT-3 (text-davinci-002))
Galactica: A Large Language Model for Science arXiv:2211.09085
Bias DetectiononStereoSet
SS· 2022-11-16
56.2
best: 60.8 (GPT-3 (text-davinci-002))
Galactica: A Large Language Model for Science arXiv:2211.09085
Stereotypical Bias AnalysisonCrowS-Pairs
Disability· 2022-11-16
66.7
best: 76.7 (GPT-3)
Galactica: A Large Language Model for Science arXiv:2211.09085
Stereotypical Bias AnalysisonCrowS-Pairs
Gender· 2022-11-16
51.9
best: 70.6 (LLaMA 65B)
Galactica: A Large Language Model for Science arXiv:2211.09085
Stereotypical Bias AnalysisonCrowS-Pairs
Nationality· 2022-11-16
51.6
best: 64.2 (LLaMA 65B)
Galactica: A Large Language Model for Science arXiv:2211.09085
Stereotypical Bias AnalysisonCrowS-Pairs
Overall· 2022-11-16
60.5
best: 69.5 (OPT-175B)
Galactica: A Large Language Model for Science arXiv:2211.09085
Stereotypical Bias AnalysisonCrowS-Pairs
Physical Appearance· 2022-11-16
58.7
best: 77.8 (LLaMA 65B)
Galactica: A Large Language Model for Science arXiv:2211.09085
Stereotypical Bias AnalysisonCrowS-Pairs
Race/Color· 2022-11-16
59.9
best: 68.6 (OPT-175B)
Galactica: A Large Language Model for Science arXiv:2211.09085
Stereotypical Bias AnalysisonCrowS-Pairs
Religion· 2022-11-16
51.9
best: 70.6 (LLaMA 65B)
Galactica: A Large Language Model for Science arXiv:2211.09085
Stereotypical Bias AnalysisonCrowS-Pairs
Sexual Orientation· 2022-11-16
77.4
best: 81 (LLaMA 65B)
Galactica: A Large Language Model for Science arXiv:2211.09085
Stereotypical Bias AnalysisonCrowS-Pairs
Socioeconomic status· 2022-11-16
65.7
best: 76.2 (OPT-175B)
Galactica: A Large Language Model for Science arXiv:2211.09085

Methodology7 results

Molecular Property Predictiononclintox
Molecules (M)· 2022-11-16
2
best: 77 (ChemBERTa-2 (MTR-77M))
Galactica: A Large Language Model for Science arXiv:2211.09085
Molecular Property Predictiononclintox
ROC-AUC· 2022-11-16
82.6
best: 99.2 (Deep-CBN)
Galactica: A Large Language Model for Science arXiv:2211.09085
Molecular Property PredictiononBBBP
ROC-AUC· 2022-11-16
66.1
best: 96.4 (DumplingGNN)
Galactica: A Large Language Model for Science arXiv:2211.09085
Molecular Property PredictiononHIV dataset
AUC· 2022-11-16
0.745
best: 0.81 (DVMP)
Galactica: A Large Language Model for Science arXiv:2211.09085
Molecular Property PredictiononSIDER
ROC-AUC· 2022-11-16
63.2
best: 91.11 (BioAct-Het)
Galactica: A Large Language Model for Science arXiv:2211.09085
Molecular Property PredictiononTox21
ROC-AUC· 2022-11-16
68.9
best: 92.4 (Deep-CBN)
Galactica: A Large Language Model for Science arXiv:2211.09085
Molecular Property PredictiononBACE
ROC-AUC· 2022-11-16
61.7
best: 88.4 (MolXPT)
Galactica: A Large Language Model for Science arXiv:2211.09085