Open Issues Need Help
View All on GitHub Help wanted: reproduce a score on your own hardware about 1 month ago
help wanted
nicedreamzapp/agent12 nicedreamzapp/agent12 Agent-12 — the local agent leaderboard. Filesystem-judged agent tasks on consumer hardware, with reference-validated judges.
Open project →
0
Agent-12 — the local agent leaderboard. Filesystem-judged agent tasks on consumer hardware, with reference-validated judges.
Python
#agent-benchmark#apple-silicon#benchmark#coding-agent#leaderboard#llm-evaluation#local-llm#mlx#ollama