Collection of Datasets and Evals from the "Making, not Taking, the Best of N" paper (https://arxiv.org/abs/2510.00931)
Ammar Khairi
ammar-cohere
AI & ML interests
Inference Optimisation
Recent Activity
upvoted an article about 9 hours ago
Talking to a 4-Year-Old: A Multilingual Benchmark for Children's AI Companions liked a model about 2 months ago
CohereLabs/cohere-transcribe-03-2026 updated a collection about 2 months ago
FusioN Datatsets