Unverified50% confidenceBenchmarkExact time
The average F1 scores across seven binary classification subtasks cluster between 70.4 and 79.2 across the models.
1
Sources
50%
Confidence
Long-term
Relevance
9/24/2026
First Seen
Sources
Related Claims
UnverifiedThe best F1 scores for sarcasm detection tasks on standard datasets (such as iSarcasm and the SemEval series) have long hovered in the 70%–80% range.72% similarUnverifiedThe model's F1 score is 72%, and the data has a severe class imbalance with a ratio of 89:11.70% similarUnverifiedIn a binary classification confusion matrix, the F1 score is the harmonic mean of precision and recall.70% similarUnverifiedF1 levels between 70 and 80 indicate that current model performance is more suitable as a research reference than as a directly deployable decision-assistance tool.66% similarUnverifiedMainstream GPU inference solutions based on the NVIDIA H100 can typically only achieve tens to one or two hundred tokens per second on models of equivalent scale.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/946199API
curl https://kongchang.com/api/v1/knowledge/claims/946199MCP
get_claim(id=946199)