Method Drift›Speculative decoding
Tracked
SpecThinking
Speculative decoding
present, but with little supersession signal in the knowledge base
0 papers critique it · 1 beat it on benchmarks
Beaten on benchmarks
Head-to-head results where a newer method reports beating SpecThinking. Values are copied from the source paper's tables — verify against the cited paper.
- Beyond Tokens: Semantic-Aware Speculative Decoding for Efficient Inference by Probing Internal States
SemanticSpec beats SpecThinking · Pass@1 [Draft: DeepseekR1-1.5B Target: DeepseekR1-32B Math-500]
0.910 vs 0.823
- Beyond Tokens: Semantic-Aware Speculative Decoding for Efficient Inference by Probing Internal States
SemanticSpec beats SpecThinking · Pass@1 [Draft: DeepseekR1-1.5B Target: QwQ-32B Math-500]
0.9217 vs 0.710
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.