Common Sense Reasoning
Benchmark List
All benchmarks related to this task
arc-easy
Best model: GAL 120B (0-shot)
Metrics
View Details
big-bench-known-unknowns
Best model: PaLM-540B (few-shot, k=5)
Metrics
View Details
big-bench-logical-sequence
Best model: Chinchilla-70B (few-shot, k=5)
Metrics
View Details
codah
Best model: BERT Large
Metrics
View Details
commonsenseqa
Best model: QA-GNN
Metrics
View Details
event2mind-test
Best model: EA-VQ-VAE
Metrics
View Details
record
Best model: ST-MoE-32B 269B (fine-tuned)
Metrics
View Details
russian-event2mind
Best model: araneum word2vec (skipgram) + GRU
Metrics
View Details
swag
Best model: DeBERTalarge
Metrics
View Details
visual-dialog-v0-9-1
Best model: NMN [kottur2018visual]
Metrics
View Details
winogavil
Best model: ViLT
Metrics
View Details
winogrande
Best model: PaLM 540B (0-shot)
Metrics
View Details
arc-challenge
Metrics
View Details
big-bench-disambiguation-qa
Metrics
View Details
big-bench-causal-judgment
Metrics
View Details
big-bench-date-understanding
Metrics
View Details
big-bench-sports-understanding
Metrics
View Details
big-bench-winowhy
Metrics
View Details
crowdsource-qa
Metrics
View Details
event2mind-dev
Metrics
View Details
parus
Metrics
View Details
rucos
Metrics
View Details
rwsd
Metrics
View Details
visual-dialog-v0-9
Metrics
View Details