Files
hack/tools/scripts/llm-key-hunter/results/_cache/content/actava-ai_leaderboard.json
T

1 line
9.2 KiB
JSON

{"repo": "actava-ai/leaderboard", "files": {"benchmarks/chi-bench/submissions/chi-bench-leaderboard-2026-05-15-openclaw-openrouter-deepseek-deepseek-v4-pro/trials/pa_provider/pa_t023_t023_o003_p01_new_referr__2au3wFv/result.json": {"9e6a294e020f7ad0d2d4295c396928a78dd5171d": {"t": 1785747170.3950412, "n": 4113, "h": "5debcca21dcc77c2", "c": "{\n \"id\": \"d5f9ab46-8ebd-43a0-8192-b06413a19b53\",\n \"task_name\": \"pa_t023_t023_o003_p01_new_referral_provider\",\n \"trial_name\": \"pa_t023_t023_o003_p01_new_referr__2au3wFv\",\n \"trial_uri\": \"file:///home/hlnchen/actava-bench-logs-backup/experiments/curated25_full_matrix/openclaw__openrouter_deepseek_deepseek_v4_pro/pa_provider/openclaw__openrouter_deepseek_deepseek_v4_pro__pa_provider/pa_t023_t023_o003_p01_new_referr__2au3wFv\",\n \"task_id\": {\n \"path\": \"/tmp/healthverse-modal-ani73tnk/pa_t023_t023_o003_p01_new_referral_provider\"\n },\n \"source\": \"healthverse-modal-ani73tnk\",\n \"task_checksum\": \"6dd32926422aa7cc2ac728fe7caccc558d2c60885b2f3965c7a5fa1d39937a10\",\n \"config\": {\n \"task\": {\n \"path\": \"/tmp/healthverse-modal-ani73tnk/pa_t023_t023_o003_p01_new_referral_provider\",\n \"git_url\": null,\n \"git_commit_id\": null,\n \"name\": null,\n \"ref\": null,\n \"overwrite\": false,\n \"download_dir\": null,\n \"source\": \"healthverse-modal-ani73tnk\"\n },\n \"trial_name\": \"pa_t023_t023_o003_p01_new_referr__2au3wFv\",\n \"trials_dir\": \"logs/experiments/curated25_full_matrix/openclaw__openrouter_deepseek_deepseek_v4_pro/pa_provider/openclaw__openrouter_deepseek_deepseek_v4_pro__pa_provider\",\n \"timeout_multiplier\": 1.0,\n \"agent_timeout_multiplier\": 2.0,\n \"verifier_timeout_multiplier\": null,\n \"agent_setup_timeout_multiplier\": null,\n \"environment_build_timeout_multiplier\": null,\n \"agent\": {\n \"name\": null,\n \"import_path\": \"healthverse.experiment.agents.openclaw_harness:OpenClawHarness\",\n \"model_name\": \"openrouter/deepseek/deepseek-v4-pro\",\n \"override_timeout_sec\": null,\n \"override_setup_timeout_sec\": null,\n \"max_timeout_sec\": null,\n \"kwargs\": {},\n \"env\": {\n \"ANTHROPIC_API_KEY\": \"sk-a****AAA\",\n \"OPENROUTER_API_KEY\": \"sk-o****ef8\",\n \"GROK_API_KEY\": \"xai-****weS\"\n }\n },\n \"environment\": {\n \"type\": null,\n \"import_path\": \"healthverse.experiment.modal_env:HealthverseModalEnvironment\",\n \"force_build\": false,\n \"delete\": true,\n \"override_cpus\": null,\n \"override_memory_mb\": null,\n \"override_storage_mb\": null,\n \"override_gpus\": null,\n \"suppress_override_warnings\": false,\n \"mounts_json\": null,\n \"env\": {},\n \"kwargs\": {\n \"sandbox_timeout_secs\": 86400\n }\n },\n \"verifier\": {\n \"override_timeout_sec\": null,\n \"max_timeout_sec\": null,\n \"env\": {},\n \"disable\": false\n },\n \"artifacts\": [],\n \"job_id\": \"910b90a6-7d68-4651-bc43-df4df8f1f62e\"\n },\n \"agent_info\": {\n \"name\": \"openclaw\",\n \"version\": \"OpenClaw 2026.4.29 (a448042)\",\n \"model_info\": {\n \"name\": \"deepseek/deepseek-v4-pro\",\n \"provider\": \"openrouter\"\n }\n },\n \"agent_result\": {\n \"n_input_tokens\": 10237462,\n \"n_cache_tokens\": 4838656,\n \"n_output_tokens\": 16514,\n \"cost_usd\": 2.3803879180000007,\n \"rollout_details\": null,\n \"metadata\": null\n },\n \"verifier_result\": {\n \"rewards\": {\n \"reward\": 0.0\n }\n },\n \"exception_info\": null,\n \"started_at\": \"2026-05-02T09:01:51.124370Z\",\n \"finished_at\": \"2026-05-02T09:30:39.341696Z\",\n \"environment_setup\": {\n \"started_at\": \"2026-05-02T09:01:51.125012Z\",\n \"finished_at\": \"2026-05-02T09:06:22.678554Z\"\n },\n \"agent_setup\": {\n \"started_at\": \"2026-05-02T09:06:22.678561Z\",\n \"finished_at\": \"2026-05-02T09:06:57.433307Z\"\n },\n \"agent_execution\": {\n \"started_at\": \"2026-05-02T09:06:57.433335Z\",\n \"finished_at\": \"2026-05-02T09:28:57.166177Z\"\n },\n \"verifier\": {\n \"started_at\": \"2026-05-02T09:29:11.153247Z\",\n \"finished_at\": \"2026-05-02T09:30:35.578219Z\"\n }\n}"}, "15ac538ca2dd969d0cff985a67aa7774b1b73294": {"t": 1785770928.1324685, "n": 4113, "h": "5debcca21dcc77c2", "c": "{\n \"id\": \"d5f9ab46-8ebd-43a0-8192-b06413a19b53\",\n \"task_name\": \"pa_t023_t023_o003_p01_new_referral_provider\",\n \"trial_name\": \"pa_t023_t023_o003_p01_new_referr__2au3wFv\",\n \"trial_uri\": \"file:///home/hlnchen/actava-bench-logs-backup/experiments/curated25_full_matrix/openclaw__openrouter_deepseek_deepseek_v4_pro/pa_provider/openclaw__openrouter_deepseek_deepseek_v4_pro__pa_provider/pa_t023_t023_o003_p01_new_referr__2au3wFv\",\n \"task_id\": {\n \"path\": \"/tmp/healthverse-modal-ani73tnk/pa_t023_t023_o003_p01_new_referral_provider\"\n },\n \"source\": \"healthverse-modal-ani73tnk\",\n \"task_checksum\": \"6dd32926422aa7cc2ac728fe7caccc558d2c60885b2f3965c7a5fa1d39937a10\",\n \"config\": {\n \"task\": {\n \"path\": \"/tmp/healthverse-modal-ani73tnk/pa_t023_t023_o003_p01_new_referral_provider\",\n \"git_url\": null,\n \"git_commit_id\": null,\n \"name\": null,\n \"ref\": null,\n \"overwrite\": false,\n \"download_dir\": null,\n \"source\": \"healthverse-modal-ani73tnk\"\n },\n \"trial_name\": \"pa_t023_t023_o003_p01_new_referr__2au3wFv\",\n \"trials_dir\": \"logs/experiments/curated25_full_matrix/openclaw__openrouter_deepseek_deepseek_v4_pro/pa_provider/openclaw__openrouter_deepseek_deepseek_v4_pro__pa_provider\",\n \"timeout_multiplier\": 1.0,\n \"agent_timeout_multiplier\": 2.0,\n \"verifier_timeout_multiplier\": null,\n \"agent_setup_timeout_multiplier\": null,\n \"environment_build_timeout_multiplier\": null,\n \"agent\": {\n \"name\": null,\n \"import_path\": \"healthverse.experiment.agents.openclaw_harness:OpenClawHarness\",\n \"model_name\": \"openrouter/deepseek/deepseek-v4-pro\",\n \"override_timeout_sec\": null,\n \"override_setup_timeout_sec\": null,\n \"max_timeout_sec\": null,\n \"kwargs\": {},\n \"env\": {\n \"ANTHROPIC_API_KEY\": \"sk-a****AAA\",\n \"OPENROUTER_API_KEY\": \"sk-o****ef8\",\n \"GROK_API_KEY\": \"xai-****weS\"\n }\n },\n \"environment\": {\n \"type\": null,\n \"import_path\": \"healthverse.experiment.modal_env:HealthverseModalEnvironment\",\n \"force_build\": false,\n \"delete\": true,\n \"override_cpus\": null,\n \"override_memory_mb\": null,\n \"override_storage_mb\": null,\n \"override_gpus\": null,\n \"suppress_override_warnings\": false,\n \"mounts_json\": null,\n \"env\": {},\n \"kwargs\": {\n \"sandbox_timeout_secs\": 86400\n }\n },\n \"verifier\": {\n \"override_timeout_sec\": null,\n \"max_timeout_sec\": null,\n \"env\": {},\n \"disable\": false\n },\n \"artifacts\": [],\n \"job_id\": \"910b90a6-7d68-4651-bc43-df4df8f1f62e\"\n },\n \"agent_info\": {\n \"name\": \"openclaw\",\n \"version\": \"OpenClaw 2026.4.29 (a448042)\",\n \"model_info\": {\n \"name\": \"deepseek/deepseek-v4-pro\",\n \"provider\": \"openrouter\"\n }\n },\n \"agent_result\": {\n \"n_input_tokens\": 10237462,\n \"n_cache_tokens\": 4838656,\n \"n_output_tokens\": 16514,\n \"cost_usd\": 2.3803879180000007,\n \"rollout_details\": null,\n \"metadata\": null\n },\n \"verifier_result\": {\n \"rewards\": {\n \"reward\": 0.0\n }\n },\n \"exception_info\": null,\n \"started_at\": \"2026-05-02T09:01:51.124370Z\",\n \"finished_at\": \"2026-05-02T09:30:39.341696Z\",\n \"environment_setup\": {\n \"started_at\": \"2026-05-02T09:01:51.125012Z\",\n \"finished_at\": \"2026-05-02T09:06:22.678554Z\"\n },\n \"agent_setup\": {\n \"started_at\": \"2026-05-02T09:06:22.678561Z\",\n \"finished_at\": \"2026-05-02T09:06:57.433307Z\"\n },\n \"agent_execution\": {\n \"started_at\": \"2026-05-02T09:06:57.433335Z\",\n \"finished_at\": \"2026-05-02T09:28:57.166177Z\"\n },\n \"verifier\": {\n \"started_at\": \"2026-05-02T09:29:11.153247Z\",\n \"finished_at\": \"2026-05-02T09:30:35.578219Z\"\n }\n}"}}}}