{"model": {"slug": "gemini-2-5-pro-preview", "name": "Gemini 2.5 Pro Preview", "vendor": "google", "model_family": "gemini-2-5-pro-preview", "parameter_count_b": null, "context_length": 1048576, "homepage_url": null, "hf_model_id": null, "openrouter_id": "google/gemini-2.5-pro-preview", "card_summary": "google Gemini 2.5 Pro Preview on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 83.1, "input_price_per_million": 1.25, "output_price_per_million": 10.0}, "scores": [{"success_rate": 83.1, "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": "Aider polyglot leaderboard", "source": "aider_leaderboard", "source_url": "https://aider.chat/docs/leaderboards/", "observed_at": "2025-06-06T00:00:00+00:00", "harness": {"slug": "aider", "name": "Aider", "vendor": "Aider", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "gemini-2-5-pro-preview", "name": "Gemini 2.5 Pro Preview", "vendor": "google"}, "benchmark": {"slug": "aider-polyglot", "name": "Aider Polyglot"}}, {"success_rate": 22.22, "resolved_count": null, "total_count": null, "cost_usd": 4.052, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": 45, "is_harnessrl_measured": false, "eval_protocol": "HAL CORE-Bench Hard (HAL) accuracy", "source": "hal_site", "source_url": "https://hal.cs.princeton.edu/corebench_hard", "observed_at": null, "harness": {"slug": "core-agent", "name": "CORE-Agent", "vendor": null, "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "gemini-2-5-pro-preview", "name": "Gemini 2.5 Pro Preview", "vendor": "google"}, "benchmark": {"slug": "hal-corebench-hard", "name": "CORE-Bench Hard (HAL)"}}, {"success_rate": 4.44, "resolved_count": null, "total_count": null, "cost_usd": 0.6751, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": 45, "is_harnessrl_measured": false, "eval_protocol": "HAL CORE-Bench Hard (HAL) accuracy", "source": "hal_site", "source_url": "https://hal.cs.princeton.edu/corebench_hard", "observed_at": null, "harness": {"slug": "hal-generalist-agent", "name": "HAL Generalist Agent", "vendor": "Princeton PLI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "gemini-2-5-pro-preview", "name": "Gemini 2.5 Pro Preview", "vendor": "google"}, "benchmark": {"slug": "hal-corebench-hard", "name": "CORE-Bench Hard (HAL)"}}], "harnesses": [{"slug": "aider", "name": "Aider", "vendor": "Aider", "repo_url": "https://github.com/Aider-AI/aider", "openrouter_icon_url": "https://aider.chat/favicon.ico"}, {"slug": "core-agent", "name": "CORE-Agent", "vendor": null, "repo_url": null, "openrouter_icon_url": null}, {"slug": "hal-generalist-agent", "name": "HAL Generalist Agent", "vendor": "Princeton PLI", "repo_url": "https://github.com/princeton-pli/hal-harness", "openrouter_icon_url": null}]}