{"model": {"slug": "glm-5", "name": "GLM 5", "vendor": "z-ai", "model_family": "glm-5", "parameter_count_b": null, "context_length": 204800, "homepage_url": null, "hf_model_id": null, "openrouter_id": "z-ai/glm-5", "card_summary": "z-ai GLM 5 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 11, "best_success_rate": 73.4, "input_price_per_million": 0.6, "output_price_per_million": 1.92}, "scores": [{"success_rate": 73.4, "resolved_count": null, "total_count": null, "cost_usd": 1.06, "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": "OpenHands SDK v1.11.5", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/58f92ff8-e886-40ab-a636-8337fc8c9bfe", "observed_at": "2026-07-31T11:38:58.577710", "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "glm-5", "name": "GLM 5", "vendor": "z-ai"}, "benchmark": {"slug": "openhands-swe-bench", "name": "SWE-bench (OpenHands Index)"}}, {"success_rate": 69.7, "resolved_count": 209, "total_count": 300, "cost_usd": 0.6424743668666667, "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 Multilingual (mini-SWE-agent)", "source": "swe_bench_site", "source_url": "https://z.ai", "observed_at": "2026-02-13T00:00:00+00:00", "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "glm-5", "name": "GLM 5", "vendor": "z-ai"}, "benchmark": {"slug": "swe-bench-multilingual", "name": "SWE-bench Multilingual"}}, {"success_rate": 62.96, "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": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "glm-5", "name": "GLM 5", "vendor": "z-ai"}, "benchmark": {"slug": "swe-rebench", "name": "SWE-rebench"}}, {"success_rate": 60.0, "resolved_count": null, "total_count": null, "cost_usd": 0.36, "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": "OpenHands SDK v1.11.5", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/c37cd7c9-3839-402d-bdf6-a0c10c4c085b", "observed_at": "2026-07-31T11:38:58.577710", "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "glm-5", "name": "GLM 5", "vendor": "z-ai"}, "benchmark": {"slug": "gaia", "name": "GAIA"}}, {"success_rate": 47.3, "resolved_count": null, "total_count": null, "cost_usd": 0.91, "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": "OpenHands SDK v1.11.5", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/a7d29286-6810-4ca8-8a11-21d6ae33822b", "observed_at": "2026-07-31T11:38:58.577710", "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "glm-5", "name": "GLM 5", "vendor": "z-ai"}, "benchmark": {"slug": "swt-bench", "name": "SWT-Bench"}}, {"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": null, "openrouter_icon_url": null}, "model": {"slug": "glm-5", "name": "GLM 5", "vendor": "z-ai"}, "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": null, "openrouter_icon_url": null}, "model": {"slug": "glm-5", "name": "GLM 5", "vendor": "z-ai"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 38.9, "resolved_count": null, "total_count": null, "cost_usd": 0.13, "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": "codex", "name": "Codex", "vendor": "OpenAI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "glm-5", "name": "GLM 5", "vendor": "z-ai"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 35.3, "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": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.11.5", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/756a9904-f7f3-4c23-a663-8a7dd853d6dd", "observed_at": "2026-07-31T11:38:58.577710", "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "glm-5", "name": "GLM 5", "vendor": "z-ai"}, "benchmark": {"slug": "swe-bench-multimodal", "name": "SWE-bench Multimodal (OpenHands Index)"}}, {"success_rate": 31.2, "resolved_count": null, "total_count": null, "cost_usd": 2.23, "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": "OpenHands SDK v1.11.5", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/76ea5306-b580-47c0-a9ad-67a1c995bfba", "observed_at": "2026-07-31T11:38:58.577710", "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "glm-5", "name": "GLM 5", "vendor": "z-ai"}, "benchmark": {"slug": "commit0", "name": "Commit0"}}, {"success_rate": 31.0, "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": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "glm-5", "name": "GLM 5", "vendor": "z-ai"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}], "harnesses": [{"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "repo_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico"}, {"slug": "codex", "name": "Codex", "vendor": "OpenAI", "repo_url": "https://github.com/openai/codex", "openrouter_icon_url": "https://openai.com/favicon.ico"}, {"slug": "hermes-agent", "name": "Hermes Agent", "vendor": "Nous Research", "repo_url": "https://github.com/NousResearch/hermes-agent", "openrouter_icon_url": null}, {"slug": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico"}, {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null}]}