Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Speculative Decoding Inference on PubMedQA
Loading...
182.24
Throughput (tokens/s)
EvoSpec
153.1512
160.7031
168.255
175.8069
Apr 17, 2026
Throughput (tokens/s)
Updated 6d ago
Evaluation Results
Method
Method
Links
Throughput (tokens/s)
EvoSpec
Static Vocabulary Size...
2026.04
182.24
EvoSpec
Static Vocabulary Size...
2026.04
181.31
EvoSpec
Static Vocabulary Size...
2026.04
180.98
CORAL
2026.04
178.11
EvoSpec
Static Vocabulary Size...
2026.04
171.53
EvoSpec
Static Vocabulary Size...
2026.04
169.98
EvoSpec
Static Vocabulary Size...
2026.04
168.37
FR-Spec
Static Vocabulary Size...
2026.04
160.56
EAGLE-3
2026.04
160.41
EvoSpec
Static Vocabulary Size...
2026.04
157.4
EvoSpec
Static Vocabulary Size...
2026.04
154.99
EvoSpec
Static Vocabulary Size...
2026.04
154.27
Feedback
Search any
task
Search any
task