{"model": {"slug": "gpt-5-6-xhigh", "name": "GPT-5.6 (xhigh)", "vendor": "OpenAI", "model_family": "gpt-5-6", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.6 Luna variant (xhigh tier) for frontier agent scores.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 70.79, "input_price_per_million": null, "output_price_per_million": null}, "scores": [{"success_rate": 70.79, "resolved_count": null, "total_count": null, "cost_usd": 1.2093171048466254, "input_tokens": 6575104, "output_tokens": 30840, "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": "codex", "name": "Codex", "vendor": "OpenAI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "gpt-5-6-xhigh", "name": "GPT-5.6 (xhigh)", "vendor": "OpenAI"}, "benchmark": {"slug": "terminal-bench-v2-1", "name": "Terminal-Bench v2.1 (AA component)"}}, {"success_rate": 56.64, "resolved_count": null, "total_count": null, "cost_usd": 1.2093171048466254, "input_tokens": 6575104, "output_tokens": 30840, "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": "codex", "name": "Codex", "vendor": "OpenAI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "gpt-5-6-xhigh", "name": "GPT-5.6 (xhigh)", "vendor": "OpenAI"}, "benchmark": {"slug": "deepswe", "name": "DeepSWE (AA component)"}}, {"success_rate": 31.45, "resolved_count": null, "total_count": null, "cost_usd": 1.2093171048466254, "input_tokens": 6575104, "output_tokens": 30840, "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": "codex", "name": "Codex", "vendor": "OpenAI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "gpt-5-6-xhigh", "name": "GPT-5.6 (xhigh)", "vendor": "OpenAI"}, "benchmark": {"slug": "swe-atlas-qna", "name": "SWE-Atlas-QnA (AA component)"}}], "harnesses": [{"slug": "codex", "name": "Codex", "vendor": "OpenAI", "repo_url": "https://github.com/openai/codex", "openrouter_icon_url": "https://openai.com/favicon.ico"}]}