Tag
Box ran Claude Sonnet 5 through its agentic benchmark, finding it surpasses Sonnet 4.6 in complex enterprise tasks like due diligence and cost analysis. Sonnet 5 will soon be available in Box AI Studio.
A fine-tuned version of Gemma-4-12B, optimized for local coding and agentic tasks, achieving ~3.5x improvement over the base model on the tau2-bench telecom benchmark.
Qwen3.6-35B-A3B and Qwen3.5-9B models are officially on the Terminal-Bench 2.0 leaderboard, with little-coder achieving 24.6% on the 35B variant, surpassing Gemini 2.5 Pro and Qwen3-Coder-480B, while the 9B model shows that sub-10B local models can compete on hard agentic benchmarks.