Method Drift›LLM reasoning / chain-of-thought
Superseded baseline#36 of 772 most-superseded
Block Universal Transformer
LLM reasoning / chain-of-thought
superseded — cited as a baseline and beaten by newer methods
1 papers critique it · 1 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites Block Universal Transformer as a baseline.
“Flattening the architecture by reusing a single Transformer block yields modest gains over the standard Transformer, but overall performance remains unsatisfactory.”
— Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens
Beaten on benchmarks
Head-to-head results where a newer method reports beating Block Universal Transformer. Values are copied from the source paper's tables — verify against the cited paper.
- Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens
SR² beats Block Universal Transformer · Sudoku-Extreme [Sudoku-Extreme]
66.63 vs 0
- Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens
SR² beats Block Universal Transformer · Maze-Hard [Maze-Hard]
93.7 vs 30.4
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.