agentic-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.