{"harness": {"slug": "muse-code", "name": "Muse Code", "vendor": "Muse", "description": "Muse Code is a coding-agent product line with public benchmark submissions pairing Muse's harness with frontier models. Rows appear on Artificial Analysis coding-agent components and occasional SWE-bench Verified community tables.\n\nAs a vendor product harness, scores reflect Muse's agent stack (tools, prompts, retrieval) plus the disclosed model. Compare against other product CLIs rather than minimal bash-only baselines when the question is vendor competitiveness.\n\nCatalog scores use `artificialanalysis` and `swe_bench_site` sources. This page does not publish Muse's internal eval configs \u2014 only linked public leaderboard snapshots.", "card_summary": "Muse coding agent \u2014 SWE-bench Verified and Artificial Analysis leaderboard presence.", "homepage_url": "https://muse.ai", "repo_url": null, "docs_url": null, "scaffold_code": null, "harbor_agent_name": null, "api_protocol": null, "status": "validated", "supports_rl": true, "score_count": 3, "best_success_rate": 81.65, "github_stars": null, "popularity_tier": "popular", "hrl_score": 53.0, "hrl_rank": 10, "catalog_token_volume": null, "openrouter_icon_url": null, "leaderboard_icon_url": null, "aa_coding_index": 0.6164044159758908, "aa_mean_cost_usd": 2.072823051942741, "aa_mean_total_tokens": 19963139}, "scores": [{"success_rate": 81.65, "resolved_count": null, "total_count": null, "cost_usd": 2.072823051942741, "input_tokens": 10093761, "output_tokens": 58305, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": null, "is_harnessrl_measured": false, "eval_protocol": "Artificial Analysis Coding Agent Index component (pass@1)", "source": "artificialanalysis", "source_url": "https://artificialanalysis.ai/agents/coding-agents", "observed_at": "2026-08-27T21:54:11.189561+00:00", "harness": {"slug": "muse-code", "name": "Muse Code", "vendor": "Muse", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "muse-spark-1-2-xhigh", "name": "Muse Spark 1 2 Xhigh", "vendor": "Muse"}, "benchmark": {"slug": "terminal-bench-v2-1", "name": "Terminal-Bench v2.1 (AA component)"}}, {"success_rate": 58.11, "resolved_count": null, "total_count": null, "cost_usd": 2.072823051942741, "input_tokens": 10093761, "output_tokens": 58305, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": null, "is_harnessrl_measured": false, "eval_protocol": "Artificial Analysis Coding Agent Index component (pass@1)", "source": "artificialanalysis", "source_url": "https://artificialanalysis.ai/agents/coding-agents", "observed_at": "2026-08-27T21:54:11.189561+00:00", "harness": {"slug": "muse-code", "name": "Muse Code", "vendor": "Muse", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "muse-spark-1-2-xhigh", "name": "Muse Spark 1 2 Xhigh", "vendor": "Muse"}, "benchmark": {"slug": "deepswe", "name": "DeepSWE (AA component)"}}, {"success_rate": 45.16, "resolved_count": null, "total_count": null, "cost_usd": 2.072823051942741, "input_tokens": 10093761, "output_tokens": 58305, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": null, "is_harnessrl_measured": false, "eval_protocol": "Artificial Analysis Coding Agent Index component (pass@1)", "source": "artificialanalysis", "source_url": "https://artificialanalysis.ai/agents/coding-agents", "observed_at": "2026-08-27T21:54:11.189561+00:00", "harness": {"slug": "muse-code", "name": "Muse Code", "vendor": "Muse", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "muse-spark-1-2-xhigh", "name": "Muse Spark 1 2 Xhigh", "vendor": "Muse"}, "benchmark": {"slug": "swe-atlas-qna", "name": "SWE-Atlas-QnA (AA component)"}}], "benchmarks": [{"slug": "deepswe", "name": "DeepSWE (AA component)", "category": "eval"}, {"slug": "swe-atlas-qna", "name": "SWE-Atlas-QnA (AA component)", "category": "eval"}, {"slug": "terminal-bench-v2-1", "name": "Terminal-Bench v2.1 (AA component)", "category": "eval"}]}