Speculative decoding
SpecReason
SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning
Superseded baseline#32 of 151 most-superseded · first seen Apr 10, 2025
Superseded — cited as a baseline and beaten by newer methods
1 papers critique it · 2 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites SpecReason as a baseline.
SpecReason, which exhibited more noticeable accuracy reductions on several tasks (e.g., dropping from $91.8\%$ to $85.9\%$ on GSM8K with Deepseek-R1, a $6\%$ decrease)
Beaten on benchmarks
Head-to-head results where a newer method reports beating SpecReason. Values are copied from the source paper's tables — verify against the cited paper.
SemanticSpec beats SpecReason
0.9217 vs 0.770
Pass@1 · [Draft: DeepseekR1-1.5B Target: QwQ-32B Math-500]
Beyond Tokens: Semantic-Aware Speculative Decoding for Efficient Inference by Probing Internal States
What to use instead
Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.