{"type":"post","id":"mixdog-open-source-coding-agent-publishes-terminal-bench-d16908","slug":"mixdog-open-source-coding-agent-publishes-terminal-bench-d16908","title":"Mixdog open-source coding agent publishes Terminal-Bench 2.1 runs claiming Codex CLI-level success with far fewer tokens","description":"Mixdog’s repository reports Terminal-Bench 2.1 results comparing its open-source desktop coding agent with Codex CLI and Claude Code.","retrieval_nugget":"Mixdog’s repository reports Terminal-Bench 2.1 results comparing its open-source desktop coding agent with Codex CLI and Claude Code. The project says it matched or exceeded those systems on task counts while using fewer tokens or costing less, offering a concrete but self-reported data point for teams evaluating agent-harness efficiency.","published_at":"2026-10-31","updated_at":"2026-10-31","record_date":"2026-10-31","date_kind":"published_at","topics":["codex","claude","claude-code"],"entities":["Mixdog","Terminal-Bench 2.1","Harbor","Codex CLI","Claude Code","GPT-5.6 Sol","GPT-6.1 Sol","Claude Opus 5"],"related_patterns":["agent-economics-moves-to-completed-work"],"novelty_label":"new_fact","what_changed":"Mixdog reports Terminal-Bench 2.1 runs claiming Codex CLI-level success with far fewer tokens; the archive covers Terminal-Bench benchmarks and a competing 2.1 cost-efficiency run, but not Mixdog’s results.","prior_refs":["memory:3cfbf130-0610-8389-a839-61675053b6de","memory:631d8c5e-dc4c-8987-aba5-674b0fcfaa76"],"source_url":"https://github.com/tribgames/mixdog","source_urls":["https://github.com/tribgames/mixdog"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:mixdog-open-source-coding-agent-publishes-terminal-bench-d16908","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/mixdog-open-source-coding-agent-publishes-terminal-bench-d16908/","markdown":"https://newruntime.com/posts/mixdog-open-source-coding-agent-publishes-terminal-bench-d16908.md","json":"https://newruntime.com/posts/mixdog-open-source-coding-agent-publishes-terminal-bench-d16908.json"},"next_reads":[{"type":"topic","path":"/topics/codex/","url":"https://newruntime.com/topics/codex/","title":"Codex","reason":"Explore the codex topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/codex.md","json_url":"https://newruntime.com/topics/codex.json"},{"type":"topic","path":"/topics/claude/","url":"https://newruntime.com/topics/claude/","title":"Claude","reason":"Explore the claude topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/claude.md","json_url":"https://newruntime.com/topics/claude.json"},{"type":"topic","path":"/topics/claude-code/","url":"https://newruntime.com/topics/claude-code/","title":"Claude Code","reason":"Explore the claude-code topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/claude-code.md","json_url":"https://newruntime.com/topics/claude-code.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}