{"harness": {"slug": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "description": "Personal AI assistant platform with terminal CLI and OpenRouter integration across messaging channels.", "card_summary": "OpenClaw OpenClaw coding agent harness.", "homepage_url": "https://openclaw.ai/", "repo_url": "https://github.com/openclaw/openclaw", "docs_url": null, "scaffold_code": null, "harbor_agent_name": null, "api_protocol": "openai", "status": "validated", "supports_rl": true, "score_count": 34, "best_success_rate": 67.2, "github_stars": null, "popularity_tier": "popular", "hrl_score": 87.0, "hrl_rank": 4, "catalog_token_volume": 4592638380486, "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": 67.2, "resolved_count": null, "total_count": null, "cost_usd": 0.9463, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "gpt-5-6", "name": "GPT-5.6", "vendor": "OpenAI"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 64.7, "resolved_count": null, "total_count": null, "cost_usd": 1.5992, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "claude-4-8-opus", "name": "Claude 4.8 Opus", "vendor": "Anthropic"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 62.2, "resolved_count": null, "total_count": null, "cost_usd": 1.29, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "claude-4-7-opus", "name": "Claude 4.7 Opus", "vendor": "Anthropic"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 62.0, "resolved_count": null, "total_count": null, "cost_usd": 1.4618, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "fable-5", "name": "Fable 5", "vendor": "Anthropic"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 58.2, "resolved_count": null, "total_count": null, "cost_usd": 0.63, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "gpt-5-5", "name": "GPT-5.5", "vendor": "openai"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 57.5, "resolved_count": null, "total_count": null, "cost_usd": 0.4738, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "grok-4-5", "name": "GROK 4.5", "vendor": "x-ai"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 56.2, "resolved_count": null, "total_count": null, "cost_usd": 0.4117, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "qwen3-8-max", "name": "Qwen3.8 Max", "vendor": "Qwen"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 54.8, "resolved_count": null, "total_count": null, "cost_usd": 0.3932, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "muse-spark-1-1", "name": "Muse Spark 1.1", "vendor": "meta"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 54.5, "resolved_count": null, "total_count": null, "cost_usd": 0.668, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "kimi-k3", "name": "KIMI K3", "vendor": "Moonshot"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 54.2, "resolved_count": null, "total_count": null, "cost_usd": 0.285, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "glm-5-2", "name": "GLM 5 2", "vendor": "Zhipu"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 51.6, "resolved_count": null, "total_count": null, "cost_usd": 1.35, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "claude-4-6-opus", "name": "Claude 4.6 Opus", "vendor": "Anthropic"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 50.3, "resolved_count": null, "total_count": null, "cost_usd": 0.33, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "gpt-5-4", "name": "GPT-5.4", "vendor": "openai"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 49.7, "resolved_count": null, "total_count": null, "cost_usd": 0.0355, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "hy3", "name": "Hy3", "vendor": "tencent"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 48.2, "resolved_count": null, "total_count": null, "cost_usd": 0.58, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "glm-5-1", "name": "GLM 5 1", "vendor": "Zhipu"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 48.0, "resolved_count": null, "total_count": null, "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": 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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "qwen3-8-27b", "name": "Qwen3.8 27B", "vendor": "qwen"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 47.6, "resolved_count": null, "total_count": null, "cost_usd": 0.101, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "muse-glimmer-30b", "name": "Muse Glimmer 30B", "vendor": "meta"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 46.9, "resolved_count": null, "total_count": null, "cost_usd": 1.2052, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "kimi-k2-7-code", "name": "KIMI K2.7 Code", "vendor": "moonshotai"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 44.7, "resolved_count": null, "total_count": null, "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": 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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "intern-s2-preview-397b", "name": "Intern S2 Preview 397B", "vendor": "InternLM"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 43.7, "resolved_count": null, "total_count": null, "cost_usd": 0.2, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "deepseek-v4-pro", "name": "DeepSeek V4 Pro", "vendor": "deepseek"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 43.2, "resolved_count": null, "total_count": null, "cost_usd": 0.3485, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "qwen3-6-27b", "name": "Qwen3.6 27B", "vendor": "qwen"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 43.0, "resolved_count": null, "total_count": null, "cost_usd": 0.21, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "mimo-v2-5-pro", "name": "MiMo V2.5 Pro", "vendor": "xiaomi"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 42.6, "resolved_count": null, "total_count": null, "cost_usd": 0.19, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "glm-5", "name": "GLM 5", "vendor": "z-ai"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 40.8, "resolved_count": null, "total_count": null, "cost_usd": 0.3, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "gemini-3-1-pro", "name": "Gemini 3.1 Pro", "vendor": "Google"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 40.2, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "mimo-v2-pro", "name": "MiMo V2 Pro", "vendor": "Xiaomi"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 37.6, "resolved_count": null, "total_count": null, "cost_usd": 0.0577, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "gemma-4-31b-it", "name": "Gemma 4 31B IT", "vendor": "google"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 34.5, "resolved_count": null, "total_count": null, "cost_usd": 0.37, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "qwen3-5-397b", "name": "Qwen3.5 397B", "vendor": "Qwen"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 34.0, "resolved_count": null, "total_count": null, "cost_usd": 0.19, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "deepseek-v3-2", "name": "DeepSeek V3.2", "vendor": "deepseek"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 33.9, "resolved_count": null, "total_count": null, "cost_usd": 0.25, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "glm-5-turbo", "name": "GLM 5 Turbo", "vendor": "z-ai"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 33.8, "resolved_count": null, "total_count": null, "cost_usd": 0.12, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "minimax-m2-7", "name": "MiniMax M2.7", "vendor": "minimax"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 30.8, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "kimi-k2-5", "name": "KIMI K2.5", "vendor": "moonshotai"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 30.8, "resolved_count": null, "total_count": null, "cost_usd": 0.17, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "mimo-v2-flash", "name": "MiMo V2 Flash", "vendor": "Xiaomi"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 27.1, "resolved_count": null, "total_count": null, "cost_usd": 0.16, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "minimax-m2-5", "name": "MiniMax M2.5", "vendor": "minimax"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 26.7, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "step-3-5-flash", "name": "Step 3.5 Flash", "vendor": "stepfun"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 19.3, "resolved_count": null, "total_count": null, "cost_usd": 0.16, "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": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, "model": {"slug": "grok-4-20-beta", "name": "GROK 4.20 Beta", "vendor": "xAI"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}], "benchmarks": [{"slug": "wildclawbench", "name": "WildClawBench", "category": "eval"}]}