{"harness": {"slug": "aime-coder-v1", "name": "Aime Coder V1", "vendor": "Swe Bench", "description": "AIME-Coder v1 is a research agent submission on SWE-bench Verified \u2014 typically a specialized coding agent or pipeline evaluated on the verified 500-issue split. Narrow research presence in the catalog is expected.\n\n`swe_bench_site` community row(s). Read model and source URL for the exact paper or release tied to the submission.", "card_summary": "AIME-Coder v1 agent \u2014 research harness on SWE-bench Verified.", "homepage_url": "https://www.swebench.com/verified", "repo_url": "https://github.com/SWE-bench/experiments/blob/main/evaluation/verified/20250514_aime_coder/README.md", "docs_url": null, "scaffold_code": null, "harbor_agent_name": null, "api_protocol": null, "status": "validated", "supports_rl": true, "score_count": 1, "best_success_rate": 66.4, "github_stars": 280, "popularity_tier": null, "hrl_score": 29.0, "hrl_rank": 33, "catalog_token_volume": null, "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/logos/20250514_aime_coder.png", "aa_coding_index": null, "aa_mean_cost_usd": null, "aa_mean_total_tokens": null}, "scores": [{"success_rate": 66.4, "resolved_count": 332, "total_count": 500, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-bench Verified public submission", "source": "swe_bench_site", "source_url": "https://github.com/SWE-bench/experiments/blob/main/evaluation/verified/20250514_aime_coder/README.md", "observed_at": "2025-05-14T00:00:00+00:00", "harness": {"slug": "aime-coder-v1", "name": "Aime Coder V1", "vendor": "Swe Bench", "repo_url": "https://github.com/SWE-bench/experiments/blob/main/evaluation/verified/20250514_aime_coder/README.md", "openrouter_icon_url": null}, "model": {"slug": "claude-3-7-sonnet", "name": "Claude 3.7 Sonnet", "vendor": "Anthropic"}, "benchmark": {"slug": "swe-bench-verified", "name": "SWE-bench Verified"}}], "benchmarks": [{"slug": "swe-bench-verified", "name": "SWE-bench Verified", "category": "eval"}]}