Ornith-1.0 9B

Not independently scored by Artificial Analysis

DeepReinforce's self-scaffolding agentic coder (MIT, Jun 2026), built on Gemma 4 / Qwen 3.5. Unusual idea: it learns its own agent scaffold — memory layout, retry logic, tool orchestration — during RL, rather than having engineers hard-code it. Coding-specialised, smallest of a family up to 397B.

BigCodeBench-Hard pass@1 12% (15/121), via local GPU (Ollama, num_ctx 16384). The brutal counterpart to HumanEval — where HumanEval saturates near the top, BCB-Hard spreads the field, so this is the number that actually separates coding ability. Agentic coder — a single-shot BCB understates its agent-loop behaviour; read the number as a floor.

~6 GB at Q4, fits an 8 GB card. Built for AGENTIC coding (multi-turn, tools), so a single-shot benchmark like our BCB-Hard likely understates it — read its number as a floor for how it behaves in an agent loop.