aone-agent
aone-agentaone-agent's pass rate on every board it ran on. Scores on different boards don't add up, so this page doesn't add them.
On each board
Terminal-Bench 2.0
terminal-bench@2.0qwen3-coder-480b-a35b-instruct-fp81.18.72-pre, full, 89 tasks, 5 attempts, open
27.2%19.8–35.1