{"model": {"slug": "deepseek-r1-may-2025", "name": "DeepSeek R1 (May 2025)", "vendor": "DeepSeek", "model_family": "deepseek-r1-may-2025", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek R1 (May 2025) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 8.89, "input_price_per_million": null, "output_price_per_million": null}, "scores": [{"success_rate": 8.89, "resolved_count": null, "total_count": null, "cost_usd": 0.1727, "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": "deepseek-r1-may-2025", "name": "DeepSeek R1 (May 2025)", "vendor": "DeepSeek"}, "benchmark": {"slug": "hal-corebench-hard", "name": "CORE-Bench Hard (HAL)"}}, {"success_rate": 8.75, "resolved_count": null, "total_count": null, "cost_usd": 0.606, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": 30, "is_harnessrl_measured": false, "eval_protocol": "HAL AssistantBench (HAL) accuracy", "source": "hal_site", "source_url": "https://hal.cs.princeton.edu/assistantbench", "observed_at": null, "harness": {"slug": "browser-use", "name": "Browser-Use", "vendor": null, "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "deepseek-r1-may-2025", "name": "DeepSeek R1 (May 2025)", "vendor": "DeepSeek"}, "benchmark": {"slug": "hal-assistantbench", "name": "AssistantBench (HAL)"}}, {"success_rate": 0.0, "resolved_count": null, "total_count": null, "cost_usd": 0.7202, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": 80, "is_harnessrl_measured": false, "eval_protocol": "HAL SciCode (HAL) accuracy", "source": "hal_site", "source_url": "https://hal.cs.princeton.edu/scicode", "observed_at": null, "harness": {"slug": "scicode-tool-calling-agent", "name": "Scicode Tool Calling Agent", "vendor": null, "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "deepseek-r1-may-2025", "name": "DeepSeek R1 (May 2025)", "vendor": "DeepSeek"}, "benchmark": {"slug": "hal-scicode", "name": "SciCode (HAL)"}}, {"success_rate": 0.0, "resolved_count": null, "total_count": null, "cost_usd": 0.0274, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": 80, "is_harnessrl_measured": false, "eval_protocol": "HAL SciCode (HAL) accuracy", "source": "hal_site", "source_url": "https://hal.cs.princeton.edu/scicode", "observed_at": null, "harness": {"slug": "scicode-zero-shot-agent", "name": "Scicode Zero Shot Agent", "vendor": null, "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "deepseek-r1-may-2025", "name": "DeepSeek R1 (May 2025)", "vendor": "DeepSeek"}, "benchmark": {"slug": "hal-scicode", "name": "SciCode (HAL)"}}], "harnesses": [{"slug": "browser-use", "name": "Browser-Use", "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}, {"slug": "scicode-tool-calling-agent", "name": "Scicode Tool Calling Agent", "vendor": null, "repo_url": null, "openrouter_icon_url": null}, {"slug": "scicode-zero-shot-agent", "name": "Scicode Zero Shot Agent", "vendor": null, "repo_url": null, "openrouter_icon_url": null}]}