A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks Paper • 2605.28556 • Published May 27 • 73
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning Paper • 2604.12374 • Published Apr 14 • 37
SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding Paper • 2604.09557 • Published Feb 10 • 13
view article Article Introducing SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding nvidia • Mar 19 • 47