{"harness": {"slug": "hermes-agent", "name": "Hermes Agent", "vendor": "Nous Research", "description": "Autonomous terminal agent with tool use, skills, and multi-platform messaging gateway. Top OpenRouter coding CLI by reported token volume.", "card_summary": "Nous Research Hermes Agent coding agent harness.", "homepage_url": "https://hermes-agent.nousresearch.com/", "repo_url": "https://github.com/NousResearch/hermes-agent", "docs_url": null, "scaffold_code": null, "harbor_agent_name": null, "api_protocol": "openai", "status": "validated", "supports_rl": true, "score_count": 4, "best_success_rate": 50.7, "github_stars": null, "popularity_tier": "super_popular", "hrl_score": 100.0, "hrl_rank": 1, "catalog_token_volume": 45629506448921, "openrouter_icon_url": null, "leaderboard_icon_url": null, "aa_coding_index": null, "aa_mean_cost_usd": null, "aa_mean_total_tokens": null}, "scores": [{"success_rate": 50.7, "resolved_count": null, "total_count": null, "cost_usd": 0.44, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": 60, "is_harnessrl_measured": false, "eval_protocol": "WildClawBench overall score (60 tasks)", "source": "wildclawbench_site", "source_url": "https://github.com/internlm/WildClawBench", "observed_at": null, "harness": {"slug": "hermes-agent", "name": "Hermes Agent", "vendor": "Nous Research", "repo_url": "https://github.com/NousResearch/hermes-agent", "openrouter_icon_url": null}, "model": {"slug": "gpt-5-4", "name": "GPT-5.4", "vendor": "openai"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 48.1, "resolved_count": null, "total_count": null, "cost_usd": 0.26, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": 60, "is_harnessrl_measured": false, "eval_protocol": "WildClawBench overall score (60 tasks)", "source": "wildclawbench_site", "source_url": "https://github.com/internlm/WildClawBench", "observed_at": null, "harness": {"slug": "hermes-agent", "name": "Hermes Agent", "vendor": "Nous Research", "repo_url": "https://github.com/NousResearch/hermes-agent", "openrouter_icon_url": null}, "model": {"slug": "mimo-v2-pro", "name": "MiMo V2 Pro", "vendor": "Xiaomi"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 46.4, "resolved_count": null, "total_count": null, "cost_usd": 0.44, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": 60, "is_harnessrl_measured": false, "eval_protocol": "WildClawBench overall score (60 tasks)", "source": "wildclawbench_site", "source_url": "https://github.com/internlm/WildClawBench", "observed_at": null, "harness": {"slug": "hermes-agent", "name": "Hermes Agent", "vendor": "Nous Research", "repo_url": "https://github.com/NousResearch/hermes-agent", "openrouter_icon_url": null}, "model": {"slug": "glm-5", "name": "GLM 5", "vendor": "z-ai"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 37.1, "resolved_count": null, "total_count": null, "cost_usd": 0.11, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": 60, "is_harnessrl_measured": false, "eval_protocol": "WildClawBench overall score (60 tasks)", "source": "wildclawbench_site", "source_url": "https://github.com/internlm/WildClawBench", "observed_at": null, "harness": {"slug": "hermes-agent", "name": "Hermes Agent", "vendor": "Nous Research", "repo_url": "https://github.com/NousResearch/hermes-agent", "openrouter_icon_url": null}, "model": {"slug": "minimax-m2-7", "name": "MiniMax M2.7", "vendor": "minimax"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}], "benchmarks": [{"slug": "wildclawbench", "name": "WildClawBench", "category": "eval"}]}